diff --git a/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/CHANGELOG.md b/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/CHANGELOG.md index 49615216c..578661d09 100644 --- a/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/CHANGELOG.md +++ b/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/CHANGELOG.md @@ -1,5 +1,15 @@ # Changelog +## [0.4] 2024-08-13 + +### Added + +- Workflow reort + +### Changed + +- Expose Busco lineage database parameter +- Fix bug that was causing issues when merging the assembly statistics ## [0.3.8] 2024-04-23 diff --git a/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/Purge-duplicate-contigs-VGP-tests.yml b/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/Purge-duplicate-contigs-VGP-tests.yml index d0439c476..9d16908f2 100644 --- a/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/Purge-duplicate-contigs-VGP-tests.yml +++ b/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/Purge-duplicate-contigs-VGP-tests.yml @@ -27,6 +27,7 @@ - class: File identifier: yeast_reads_sub1.fastq.gz location: https://zenodo.org/records/10047837/files/Pacbio%20Reads%20Collection%20-%20Trimmed_yeast_reads_sub1.fastq.gz.fastq.gz?download=1 + Database for Busco Lineage: v5 Lineage: vertebrata_odb10 Name of primary assembly: Primary Name of alternate assembly: Alternate diff --git a/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/Purge-duplicate-contigs-VGP6.ga b/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/Purge-duplicate-contigs-VGP6.ga index a004fd2a2..e6b6960f2 100644 --- a/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/Purge-duplicate-contigs-VGP6.ga +++ b/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/Purge-duplicate-contigs-VGP6.ga @@ -15,8 +15,11 @@ ], "format-version": "0.1", "license": "CC-BY-4.0", - "release": "0.3.8", + "release": "0.4", "name": "Purge-duplicate-contigs-VGP6", + "report": { + "markdown": "\n# Workflow Execution Report\n\nTime workflow was invoked\n\n```galaxy\ninvocation_time()\n```\n\n```galaxy\ngenerate_galaxy_version()\n```\n\n## Merqury results\n\nMerqury QV:\n\n```galaxy\nhistory_dataset_as_table(output=\"merqury_QV\")\n```\n\nMerqury completeness:\n\n```galaxy\nhistory_dataset_as_table(output=\"merqury_stats\")\n```\n\nMerqury plots:\n\nspectra-cn:\n\n\n```galaxy\nhistory_dataset_as_image(output=\"output_merqury.spectra-cn.fl\")\n```\n\n\nspectra-asm:\n\n\n```galaxy\nhistory_dataset_as_image(output=\"output_merqury.spectra-asm.fl\")\n```\n\n\nhap1/Primary spectra-cn:\n\n\n```galaxy\nhistory_dataset_as_image(output=\"output_merqury.assembly_01.spectra-cn.fl\")\n```\n\n\nhap2/alternate spectra-cn:\n\n```galaxy\nhistory_dataset_as_image(output=\"output_merqury.assembly_02.spectra-cn.fl\")\n```\n\n\n\n\n## BUSCO results (Vertebrata database)\n\nPurged hap1/primary Assembly\n\n\n```galaxy\nhistory_dataset_as_image(output=\"Busco on Purged Primary assembly: summary image\")\n```\n\n\n## Assembly statistics\n\n\n```galaxy\nhistory_dataset_as_table(output=\"clean_stats\")\n```\n\n\n## Nx and Size plots\n\n\n```galaxy\nhistory_dataset_as_image(output=\"Nx Plot\")\n```\n\n\n```galaxy\nhistory_dataset_as_image(output=\"Size Plot\")\n```\n\n\n\n## Current Workflow\n```galaxy\nworkflow_display()\n```\n" + }, "steps": { "0": { "annotation": "A simple list containing PacBio data in either fasta or fastq formats with trimmed adapters. These are usually generated by contiging workflows and have tag \"trimmed_hifi\" associated with them.\n", @@ -181,11 +184,44 @@ "workflow_outputs": [] }, "6": { - "annotation": "Taxonomic lineage for the organism being assembled for Busco analysis.\n", + "annotation": "", "content_id": null, "errors": null, "id": 6, "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "Database for Busco Lineage" + } + ], + "label": "Database for Busco Lineage", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 265.7339336519477, + "top": 639.7798327397703 + }, + "tool_id": null, + "tool_state": "{\"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "b9c24106-80b7-46ba-9f50-1dcfc7d434d7", + "when": null, + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "c7d6dfcd-5f5a-410e-b4cf-ce62dcbd7569" + } + ] + }, + "7": { + "annotation": "Taxonomic lineage for the organism being assembled for Busco analysis.\n", + "content_id": null, + "errors": null, + "id": 7, + "input_connections": {}, "inputs": [ { "description": "Taxonomic lineage for the organism being assembled for Busco analysis.\n", @@ -196,8 +232,8 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 216.70703125, - "top": 631.06640625 + "left": 294.03105732816533, + "top": 746.4774503653352 }, "tool_id": null, "tool_state": "{\"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", @@ -205,13 +241,19 @@ "type": "parameter_input", "uuid": "a489e27a-9a41-41e2-ab57-db2e855b1018", "when": null, - "workflow_outputs": [] + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "312c40bd-ea21-4624-842a-85f8369b8dfb" + } + ] }, - "7": { + "8": { "annotation": "", "content_id": null, "errors": null, - "id": 7, + "id": 8, "input_connections": {}, "inputs": [ { @@ -232,13 +274,19 @@ "type": "data_input", "uuid": "f53ab5b0-6b4d-43ea-8876-a1e2476fc7c6", "when": null, - "workflow_outputs": [] + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "ed6c5809-74a5-41e2-9efc-49af166df64c" + } + ] }, - "8": { + "9": { "annotation": "", "content_id": null, "errors": null, - "id": 8, + "id": 9, "input_connections": {}, "inputs": [ { @@ -259,13 +307,19 @@ "type": "parameter_input", "uuid": "2952f3e6-cc98-4cbe-ac46-32adb482ff3d", "when": null, - "workflow_outputs": [] + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "d52023b4-c747-4c66-82f6-5f017ee6413f" + } + ] }, - "9": { + "10": { "annotation": "", "content_id": null, "errors": null, - "id": 9, + "id": 10, "input_connections": {}, "inputs": [ { @@ -286,13 +340,19 @@ "type": "parameter_input", "uuid": "fd024c72-fe6c-4cd9-ac28-c8e86eaafc4f", "when": null, - "workflow_outputs": [] + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "0861bf3a-8855-4817-a9d4-b12e4d6d9089" + } + ] }, - "10": { + "11": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/minimap2/minimap2/2.28+galaxy0", "errors": null, - "id": 10, + "id": 11, "input_connections": { "fastq_input|fastq_input1": { "id": 0, @@ -344,11 +404,11 @@ "when": null, "workflow_outputs": [] }, - "11": { + "12": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/purge_dups/purge_dups/1.2.6+galaxy0", "errors": null, - "id": 11, + "id": 12, "input_connections": { "function_select|input": { "id": 1, @@ -389,11 +449,11 @@ "when": null, "workflow_outputs": [] }, - "12": { + "13": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/devteam/column_maker/Add_a_column1/2.0", "errors": null, - "id": 12, + "id": 13, "input_connections": { "input": { "id": 4, @@ -434,11 +494,11 @@ "when": null, "workflow_outputs": [] }, - "13": { + "14": { "annotation": "", "content_id": "param_value_from_file", "errors": null, - "id": 13, + "id": 14, "input_connections": { "input1": { "id": 5, @@ -481,18 +541,96 @@ } ] }, - "14": { + "15": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/compose_text_param/compose_text_param/0.1.1", + "errors": null, + "id": 15, + "input_connections": { + "components_1|param_type|component_value": { + "id": 9, + "output_name": "output" + } + }, + "inputs": [], + "label": "Awk command for primary assembly", + "name": "Compose text parameter value", + "outputs": [ + { + "name": "out1", + "type": "expression.json" + } + ], + "position": { + "left": 4651.365068171187, + "top": 984.2645791215833 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/compose_text_param/compose_text_param/0.1.1", + "tool_shed_repository": { + "changeset_revision": "e188c9826e0f", + "name": "compose_text_param", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"components\": [{\"__index__\": 0, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \"BEGIN{print \\\"Metric\\\\t\"}}, {\"__index__\": 1, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 2, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \"\\\"}; {print}; \"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.1.1", + "type": "tool", + "uuid": "6cc103fa-7ff9-4594-a380-2a740d05fd85", + "when": null, + "workflow_outputs": [] + }, + "16": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/compose_text_param/compose_text_param/0.1.1", + "errors": null, + "id": 16, + "input_connections": { + "components_1|param_type|component_value": { + "id": 10, + "output_name": "output" + } + }, + "inputs": [], + "label": "Awk command for alternate assembly 2", + "name": "Compose text parameter value", + "outputs": [ + { + "name": "out1", + "type": "expression.json" + } + ], + "position": { + "left": 4644.5776730115, + "top": 504.2187556460902 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/compose_text_param/compose_text_param/0.1.1", + "tool_shed_repository": { + "changeset_revision": "e188c9826e0f", + "name": "compose_text_param", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"components\": [{\"__index__\": 0, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \"BEGIN{print \\\"Metric\\\\t\"}}, {\"__index__\": 1, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 2, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \"\\\"}; {print}; \"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.1.1", + "type": "tool", + "uuid": "4b54a0ae-8c81-4f58-9902-470660558866", + "when": null, + "workflow_outputs": [] + }, + "17": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/minimap2/minimap2/2.28+galaxy0", "errors": null, - "id": 14, + "id": 17, "input_connections": { "fastq_input|fastq_input1": { - "id": 11, + "id": 12, "output_name": "split_fasta" }, "reference_source|ref_file": { - "id": 11, + "id": 12, "output_name": "split_fasta" } }, @@ -532,14 +670,14 @@ "when": null, "workflow_outputs": [] }, - "15": { + "18": { "annotation": "", "content_id": "Cut1", "errors": null, - "id": 15, + "id": 18, "input_connections": { "input": { - "id": 12, + "id": 13, "output_name": "out_file1" } }, @@ -565,14 +703,14 @@ "when": null, "workflow_outputs": [] }, - "16": { + "19": { "annotation": "", "content_id": "Cut1", "errors": null, - "id": 16, + "id": 19, "input_connections": { "input": { - "id": 12, + "id": 13, "output_name": "out_file1" } }, @@ -598,14 +736,14 @@ "when": null, "workflow_outputs": [] }, - "17": { + "20": { "annotation": "", "content_id": "param_value_from_file", "errors": null, - "id": 17, + "id": 20, "input_connections": { "input1": { - "id": 15, + "id": 18, "output_name": "out_file1" } }, @@ -658,14 +796,14 @@ "when": null, "workflow_outputs": [] }, - "18": { + "21": { "annotation": "", "content_id": "param_value_from_file", "errors": null, - "id": 18, + "id": 21, "input_connections": { "input1": { - "id": 16, + "id": 19, "output_name": "out_file1" } }, @@ -697,22 +835,22 @@ "when": null, "workflow_outputs": [] }, - "19": { + "22": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/purge_dups/purge_dups/1.2.6+galaxy0", "errors": null, - "id": 19, + "id": 22, "input_connections": { "function_select|input": { - "id": 10, + "id": 11, "output_name": "alignment_output" }, "function_select|section_calcuts|transition": { - "id": 18, + "id": 21, "output_name": "integer_param" }, "function_select|section_calcuts|upper_depth": { - "id": 17, + "id": 20, "output_name": "integer_param" } }, @@ -818,22 +956,22 @@ } ] }, - "20": { + "23": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/purge_dups/purge_dups/1.2.6+galaxy0", "errors": null, - "id": 20, + "id": 23, "input_connections": { "function_select|coverage": { - "id": 19, + "id": 22, "output_name": "pbcstat_cov" }, "function_select|cutoffs": { - "id": 19, + "id": 22, "output_name": "calcuts_cutoff" }, "function_select|input": { - "id": 14, + "id": 17, "output_name": "alignment_output" } }, @@ -884,14 +1022,14 @@ "when": null, "workflow_outputs": [] }, - "21": { + "24": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/purge_dups/purge_dups/1.2.6+galaxy0", "errors": null, - "id": 21, + "id": 24, "input_connections": { "function_select|bed_input": { - "id": 20, + "id": 23, "output_name": "purge_dups_bed" }, "function_select|fasta_input": { @@ -966,14 +1104,14 @@ } ] }, - "22": { + "25": { "annotation": "", "content_id": "cat1", "errors": null, - "id": 22, + "id": 25, "input_connections": { "input1": { - "id": 21, + "id": 24, "output_name": "get_seqs_hap" }, "queries_0|input2": { @@ -1016,19 +1154,23 @@ "when": null, "workflow_outputs": [] }, - "23": { + "26": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/busco/busco/5.5.0+galaxy0", "errors": null, - "id": 23, + "id": 26, "input_connections": { "input": { - "id": 21, + "id": 24, "output_name": "get_seqs_purged" }, - "lineage|lineage_dataset": { + "lineage_conditional|cached_db": { "id": 6, "output_name": "output" + }, + "lineage|lineage_dataset": { + "id": 7, + "output_name": "output" } }, "inputs": [], @@ -1104,36 +1246,36 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"adv\": {\"evalue\": \"0.001\", \"limit\": \"3\", \"contig_break\": \"10\"}, \"busco_mode\": {\"mode\": \"geno\", \"__current_case__\": 0, \"miniprot\": false, \"use_augustus\": {\"use_augustus_selector\": \"no\", \"__current_case__\": 0}}, \"input\": {\"__class__\": \"RuntimeValue\"}, \"lineage\": {\"lineage_mode\": \"select_lineage\", \"__current_case__\": 1, \"lineage_dataset\": {\"__class__\": \"ConnectedValue\"}}, \"lineage_conditional\": {\"selector\": \"download\", \"__current_case__\": 1}, \"outputs\": [\"short_summary\", \"missing\", \"image\", \"gff\"], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"adv\": {\"evalue\": \"0.001\", \"limit\": \"3\", \"contig_break\": \"10\"}, \"busco_mode\": {\"mode\": \"geno\", \"__current_case__\": 0, \"miniprot\": false, \"use_augustus\": {\"use_augustus_selector\": \"no\", \"__current_case__\": 0}}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"lineage\": {\"lineage_mode\": \"select_lineage\", \"__current_case__\": 1, \"lineage_dataset\": {\"__class__\": \"ConnectedValue\"}}, \"lineage_conditional\": {\"selector\": \"cached\", \"__current_case__\": 0, \"cached_db\": {\"__class__\": \"ConnectedValue\"}}, \"outputs\": [\"short_summary\", \"missing\", \"image\", \"gff\"], \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "5.5.0+galaxy0", "type": "tool", "uuid": "88073363-2f5c-4486-a23a-1cfdc4f5e6a6", "when": null, "workflow_outputs": [ - { - "label": "Busco on Purged Primary assembly: summary image", - "output_name": "summary_image", - "uuid": "d1ecf9fe-3f76-465d-bcac-cf5b4986a8e8" - }, { "label": "Busco on Purged Primary assembly: short summary", "output_name": "busco_sum", "uuid": "87515aeb-4e2e-494f-a271-44013d0944e4" + }, + { + "label": "Busco on Purged Primary assembly: summary image", + "output_name": "summary_image", + "uuid": "d1ecf9fe-3f76-465d-bcac-cf5b4986a8e8" } ] }, - "24": { + "27": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/gfastats/gfastats/1.3.6+galaxy0", "errors": null, - "id": 24, + "id": 27, "input_connections": { "input_file": { - "id": 21, + "id": 24, "output_name": "get_seqs_purged" }, "mode_condition|swiss_army_knife": { - "id": 7, + "id": 8, "output_name": "output" } }, @@ -1179,18 +1321,18 @@ } ] }, - "25": { + "28": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/gfastats/gfastats/1.3.6+galaxy0", "errors": null, - "id": 25, + "id": 28, "input_connections": { "input_file": { - "id": 21, + "id": 24, "output_name": "get_seqs_purged" }, "mode_condition|statistics_condition|expected_genomesize": { - "id": 13, + "id": 14, "output_name": "integer_param" } }, @@ -1230,14 +1372,14 @@ "when": null, "workflow_outputs": [] }, - "26": { + "29": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/gfastats/gfastats/1.3.6+galaxy0", "errors": null, - "id": 26, + "id": 29, "input_connections": { "input_file": { - "id": 21, + "id": 24, "output_name": "get_seqs_purged" } }, @@ -1277,18 +1419,18 @@ "when": null, "workflow_outputs": [] }, - "27": { + "30": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/minimap2/minimap2/2.28+galaxy0", "errors": null, - "id": 27, + "id": 30, "input_connections": { "fastq_input|fastq_input1": { "id": 0, "output_name": "output" }, "reference_source|ref_file": { - "id": 22, + "id": 25, "output_name": "out_file1" } }, @@ -1335,14 +1477,14 @@ "when": null, "workflow_outputs": [] }, - "28": { + "31": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/purge_dups/purge_dups/1.2.6+galaxy0", "errors": null, - "id": 28, + "id": 31, "input_connections": { "function_select|input": { - "id": 22, + "id": 25, "output_name": "out_file1" } }, @@ -1387,14 +1529,18 @@ "when": null, "workflow_outputs": [] }, - "29": { + "32": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.3+galaxy1", "errors": null, - "id": 29, + "id": 32, "input_connections": { + "code": { + "id": 15, + "output_name": "out1" + }, "infile": { - "id": 25, + "id": 28, "output_name": "stats" } }, @@ -1425,19 +1571,19 @@ "owner": "bgruening", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"code\": \"BEGIN{print \\\"Metric\\\\tPrimary\\\"}; {print}; \", \"infile\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"code\": {\"__class__\": \"ConnectedValue\"}, \"infile\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "9.3+galaxy1", "type": "tool", "uuid": "8ad0b9e5-e002-402d-9d3a-ec20c331f864", "when": null, "workflow_outputs": [] }, - "30": { + "33": { "annotation": "", - "id": 30, + "id": 33, "input_connections": { "gfa_stats": { - "id": 26, + "id": 29, "input_subworkflow_step_id": 0, "output_name": "stats" } @@ -1800,7 +1946,7 @@ ] } }, - "tags": "", + "tags": [], "uuid": "a9f43eb4-7587-49e4-aee4-7fabb96cc753" }, "tool_id": null, @@ -1809,22 +1955,22 @@ "when": null, "workflow_outputs": [] }, - "31": { + "34": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/purge_dups/purge_dups/1.2.6+galaxy0", "errors": null, - "id": 31, + "id": 34, "input_connections": { "function_select|input": { - "id": 27, + "id": 30, "output_name": "alignment_output" }, "function_select|section_calcuts|transition": { - "id": 18, + "id": 21, "output_name": "integer_param" }, "function_select|section_calcuts|upper_depth": { - "id": 17, + "id": 20, "output_name": "integer_param" } }, @@ -1937,18 +2083,18 @@ } ] }, - "32": { + "35": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/minimap2/minimap2/2.28+galaxy0", "errors": null, - "id": 32, + "id": 35, "input_connections": { "fastq_input|fastq_input1": { - "id": 28, + "id": 31, "output_name": "split_fasta" }, "reference_source|ref_file": { - "id": 28, + "id": 31, "output_name": "split_fasta" } }, @@ -1995,22 +2141,22 @@ "when": null, "workflow_outputs": [] }, - "33": { + "36": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/purge_dups/purge_dups/1.2.6+galaxy0", "errors": null, - "id": 33, + "id": 36, "input_connections": { "function_select|coverage": { - "id": 31, + "id": 34, "output_name": "pbcstat_cov" }, "function_select|cutoffs": { - "id": 31, + "id": 34, "output_name": "calcuts_cutoff" }, "function_select|input": { - "id": 32, + "id": 35, "output_name": "alignment_output" } }, @@ -2061,18 +2207,18 @@ "when": null, "workflow_outputs": [] }, - "34": { + "37": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/purge_dups/purge_dups/1.2.6+galaxy0", "errors": null, - "id": 34, + "id": 37, "input_connections": { "function_select|bed_input": { - "id": 33, + "id": 36, "output_name": "purge_dups_bed" }, "function_select|fasta_input": { - "id": 22, + "id": 25, "output_name": "out_file1" } }, @@ -2136,18 +2282,18 @@ } ] }, - "35": { + "38": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/gfastats/gfastats/1.3.6+galaxy0", "errors": null, - "id": 35, + "id": 38, "input_connections": { "input_file": { - "id": 34, + "id": 37, "output_name": "get_seqs_purged" }, "mode_condition|statistics_condition|expected_genomesize": { - "id": 13, + "id": 14, "output_name": "integer_param" } }, @@ -2187,14 +2333,14 @@ "when": null, "workflow_outputs": [] }, - "36": { + "39": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/gfastats/gfastats/1.3.6+galaxy0", "errors": null, - "id": 36, + "id": 39, "input_connections": { "input_file": { - "id": 34, + "id": 37, "output_name": "get_seqs_purged" } }, @@ -2234,18 +2380,18 @@ "when": null, "workflow_outputs": [] }, - "37": { + "40": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/merqury/merqury/1.3+galaxy4", "errors": null, - "id": 37, + "id": 40, "input_connections": { "mode|assembly_options|assembly_01": { - "id": 21, + "id": 24, "output_name": "get_seqs_purged" }, "mode|assembly_options|assembly_02": { - "id": 34, + "id": 37, "output_name": "get_seqs_purged" }, "mode|meryldb_F1": { @@ -2351,30 +2497,30 @@ "uuid": "133c60bc-4171-44b4-bf22-c70c623265b2", "when": null, "workflow_outputs": [ - { - "label": "Merqury on Phased assemblies: Images", - "output_name": "png_files", - "uuid": "ff9cfc96-449e-41d8-9c10-7f586ab6f479" - }, { "label": "Merqury on Phased assemblies: stats", "output_name": "stats_files", "uuid": "70f44477-6a3b-4ac4-b01a-f812ea880bae" + }, + { + "label": "Merqury on Phased assemblies: Images", + "output_name": "png_files", + "uuid": "ff9cfc96-449e-41d8-9c10-7f586ab6f479" } ] }, - "38": { + "41": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/gfastats/gfastats/1.3.6+galaxy0", "errors": null, - "id": 38, + "id": 41, "input_connections": { "input_file": { - "id": 34, + "id": 37, "output_name": "get_seqs_purged" }, "mode_condition|swiss_army_knife": { - "id": 7, + "id": 8, "output_name": "output" } }, @@ -2388,8 +2534,8 @@ } ], "position": { - "left": 5040.296875, - "top": 1349.00390625 + "left": 5015.859874326301, + "top": 1255.3651332174506 }, "post_job_actions": { "TagDatasetActionoutput": { @@ -2420,14 +2566,18 @@ } ] }, - "39": { + "42": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.3+galaxy1", "errors": null, - "id": 39, + "id": 42, "input_connections": { + "code": { + "id": 16, + "output_name": "out1" + }, "infile": { - "id": 35, + "id": 38, "output_name": "stats" } }, @@ -2458,19 +2608,19 @@ "owner": "bgruening", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"code\": \"BEGIN{print \\\"Metric\\\\tAlternate\\\"}; {print}; \", \"infile\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"code\": {\"__class__\": \"ConnectedValue\"}, \"infile\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "9.3+galaxy1", "type": "tool", "uuid": "ed133b72-e945-4fe5-91d6-c71efa30678c", "when": null, "workflow_outputs": [] }, - "40": { + "43": { "annotation": "", - "id": 40, + "id": 43, "input_connections": { "gfa_stats": { - "id": 36, + "id": 39, "input_subworkflow_step_id": 0, "output_name": "stats" } @@ -2833,7 +2983,7 @@ ] } }, - "tags": "", + "tags": [], "uuid": "7a0c200d-3c99-48e2-a4f7-5e86715448b9" }, "tool_id": null, @@ -2842,84 +2992,340 @@ "when": null, "workflow_outputs": [] }, - "41": { + "44": { "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_easyjoin_tool/9.3+galaxy1", + "content_id": "__EXTRACT_DATASET__", "errors": null, - "id": 41, + "id": 44, "input_connections": { - "infile1": { - "id": 29, - "output_name": "outfile" - }, - "infile2": { - "id": 39, - "output_name": "outfile" + "input": { + "id": 40, + "output_name": "qv_files" } }, "inputs": [], - "label": null, - "name": "Join", + "label": "merqury_QV", + "name": "Extract dataset", "outputs": [ { "name": "output", - "type": "input" + "type": "data" } ], "position": { - "left": 5646.44140625, - "top": 850.56640625 + "left": 5380.134532792207, + "top": 1426.0925046670234 }, "post_job_actions": { - "TagDatasetActionoutput": { - "action_arguments": { - "tags": "gfastats_p1_p2" - }, - "action_type": "TagDatasetAction", + "HideDatasetActionoutput": { + "action_arguments": {}, + "action_type": "HideDatasetAction", "output_name": "output" } }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_easyjoin_tool/9.3+galaxy1", - "tool_shed_repository": { - "changeset_revision": "fbf99087e067", - "name": "text_processing", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" + "tool_id": "__EXTRACT_DATASET__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"which\": {\"which_dataset\": \"by_identifier\", \"__current_case__\": 1, \"identifier\": \"output_merqury\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.1", + "type": "tool", + "uuid": "7d4f1ffc-5e09-4db5-aebd-1d1c9383e6b8", + "when": null, + "workflow_outputs": [ + { + "label": "merqury_QV", + "output_name": "output", + "uuid": "2f152e08-eaf2-4539-802c-cec3b72e6afe" + } + ] + }, + "45": { + "annotation": "", + "content_id": "__EXTRACT_DATASET__", + "errors": null, + "id": 45, + "input_connections": { + "input": { + "id": 40, + "output_name": "png_files" + } }, - "tool_state": "{\"column1\": \"1\", \"column2\": \"1\", \"empty_string_filler\": \"0\", \"header\": true, \"ignore_case\": false, \"infile1\": {\"__class__\": \"ConnectedValue\"}, \"infile2\": {\"__class__\": \"ConnectedValue\"}, \"jointype\": \"-a 1 -a 2\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "9.3+galaxy1", + "inputs": [], + "label": "output_merqury.spectra-cn.fl", + "name": "Extract dataset", + "outputs": [ + { + "name": "output", + "type": "data" + } + ], + "position": { + "left": 5383.847035629067, + "top": 1539.9431415667343 + }, + "post_job_actions": { + "HideDatasetActionoutput": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "output" + } + }, + "tool_id": "__EXTRACT_DATASET__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"which\": {\"which_dataset\": \"by_identifier\", \"__current_case__\": 1, \"identifier\": \"output_merqury.spectra-cn.fl\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.1", "type": "tool", - "uuid": "c620558f-324d-40cf-86b6-7460b52d49bf", + "uuid": "706cf485-92c5-43c3-8a04-23af75cf56c8", "when": null, "workflow_outputs": [ { - "label": "Assembly stats on Primary and alternate assemblies", + "label": "output_merqury.spectra-cn.fl", "output_name": "output", - "uuid": "36aaeacd-4752-43cb-9000-f859290c9ed2" + "uuid": "f34e855e-09ed-4da3-970c-ec7ad337c651" } ] }, - "42": { + "46": { "annotation": "", - "id": 42, + "content_id": "__EXTRACT_DATASET__", + "errors": null, + "id": 46, "input_connections": { - "Alternate data": { + "input": { + "id": 40, + "output_name": "png_files" + } + }, + "inputs": [], + "label": "output_merqury.spectra-asm.fl", + "name": "Extract dataset", + "outputs": [ + { + "name": "output", + "type": "data" + } + ], + "position": { + "left": 5392.201156836791, + "top": 1705.0261196501608 + }, + "post_job_actions": { + "HideDatasetActionoutput": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "output" + } + }, + "tool_id": "__EXTRACT_DATASET__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"which\": {\"which_dataset\": \"by_identifier\", \"__current_case__\": 1, \"identifier\": \"output_merqury.spectra-asm.fl\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.1", + "type": "tool", + "uuid": "4edba3bb-2444-4d91-87cc-50acc24923e9", + "when": null, + "workflow_outputs": [ + { + "label": "output_merqury.spectra-asm.fl", + "output_name": "output", + "uuid": "71ffd225-48bd-4e96-8025-ebaa2ea02bad" + } + ] + }, + "47": { + "annotation": "", + "content_id": "__EXTRACT_DATASET__", + "errors": null, + "id": 47, + "input_connections": { + "input": { + "id": 40, + "output_name": "png_files" + } + }, + "inputs": [], + "label": "output_merqury.assembly_01.spectra-cn.fl", + "name": "Extract dataset", + "outputs": [ + { + "name": "output", + "type": "data" + } + ], + "position": { + "left": 5353.028840865742, + "top": 1867.990707717229 + }, + "post_job_actions": { + "HideDatasetActionoutput": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "output" + } + }, + "tool_id": "__EXTRACT_DATASET__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"which\": {\"which_dataset\": \"by_identifier\", \"__current_case__\": 1, \"identifier\": \"output_merqury.assembly_01.spectra-cn.fl\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.1", + "type": "tool", + "uuid": "41fd4355-7ef4-43be-b71c-0c4a897ddc5e", + "when": null, + "workflow_outputs": [ + { + "label": "output_merqury.assembly_01.spectra-cn.fl", + "output_name": "output", + "uuid": "05b7387f-ab38-403e-ab71-b1d65e1cb025" + } + ] + }, + "48": { + "annotation": "", + "content_id": "__EXTRACT_DATASET__", + "errors": null, + "id": 48, + "input_connections": { + "input": { "id": 40, + "output_name": "stats_files" + } + }, + "inputs": [], + "label": "merqury_stats", + "name": "Extract dataset", + "outputs": [ + { + "name": "output", + "type": "data" + } + ], + "position": { + "left": 5343.486929912844, + "top": 2088.537692922351 + }, + "post_job_actions": { + "HideDatasetActionoutput": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "output" + } + }, + "tool_id": "__EXTRACT_DATASET__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"which\": {\"which_dataset\": \"first\", \"__current_case__\": 0}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.1", + "type": "tool", + "uuid": "5a62f7c5-2e97-44d8-8002-ab66dd0cd17c", + "when": null, + "workflow_outputs": [ + { + "label": "merqury_stats", + "output_name": "output", + "uuid": "bd69aaf0-461e-4c12-a8ad-48d97de3b00c" + } + ] + }, + "49": { + "annotation": "", + "content_id": "__EXTRACT_DATASET__", + "errors": null, + "id": 49, + "input_connections": { + "input": { + "id": 40, + "output_name": "png_files" + } + }, + "inputs": [], + "label": "output_merqury.assembly_02.spectra-cn.fl", + "name": "Extract dataset", + "outputs": [ + { + "name": "output", + "type": "data" + } + ], + "position": { + "left": 5608.286176870008, + "top": 1876.5434537656731 + }, + "post_job_actions": { + "HideDatasetActionoutput": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "output" + } + }, + "tool_id": "__EXTRACT_DATASET__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"which\": {\"which_dataset\": \"by_identifier\", \"__current_case__\": 1, \"identifier\": \"output_merqury.assembly_02.spectra-cn.fl\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.1", + "type": "tool", + "uuid": "035085e5-6b04-4a50-bb0a-6b3477528921", + "when": null, + "workflow_outputs": [ + { + "label": "output_merqury.assembly_02.spectra-cn.fl", + "output_name": "output", + "uuid": "8bf731d1-0eee-4877-b93c-6989cec7d77f" + } + ] + }, + "50": { + "annotation": "", + "content_id": "join1", + "errors": null, + "id": 50, + "input_connections": { + "input1": { + "id": 32, + "output_name": "outfile" + }, + "input2": { + "id": 42, + "output_name": "outfile" + } + }, + "inputs": [], + "label": null, + "name": "Join two Datasets", + "outputs": [ + { + "name": "out_file1", + "type": "tabular" + } + ], + "position": { + "left": 5636.118290732048, + "top": 1129.4974470583106 + }, + "post_job_actions": { + "HideDatasetActionout_file1": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "join1", + "tool_state": "{\"field1\": \"1\", \"field2\": \"1\", \"fill_empty_columns\": {\"fill_empty_columns_switch\": \"fill_empty\", \"__current_case__\": 1, \"fill_columns_by\": \"fill_unjoined_only\", \"do_fill_empty_columns\": {\"column_fill_type\": \"single_fill_value\", \"__current_case__\": 0, \"fill_value\": \".\"}}, \"header\": \"\", \"input1\": {\"__class__\": \"ConnectedValue\"}, \"input2\": {\"__class__\": \"ConnectedValue\"}, \"partial\": \"-p\", \"unmatched\": \"-u\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.1.3", + "type": "tool", + "uuid": "ac5c2ad5-434a-4c52-802b-eb14db33b07d", + "when": null, + "workflow_outputs": [] + }, + "51": { + "annotation": "", + "id": 51, + "input_connections": { + "Alternate data": { + "id": 43, "input_subworkflow_step_id": 1, "output_name": "gfastats data for plotting" }, "Name of alternate assembly": { - "id": 9, + "id": 10, "input_subworkflow_step_id": 3, "output_name": "output" }, "Name of primary assembly": { - "id": 8, + "id": 9, "input_subworkflow_step_id": 2, "output_name": "output" }, "Primary data": { - "id": 30, + "id": 33, "input_subworkflow_step_id": 0, "output_name": "gfastats data for plotting" } @@ -3417,7 +3823,7 @@ ] } }, - "tags": "", + "tags": [], "uuid": "b7f76989-26b9-4071-964c-ea77f10a94e7" }, "tool_id": null, @@ -3426,14 +3832,135 @@ "when": null, "workflow_outputs": [ { - "label": "Nx Plot", - "output_name": "Nx Plot", - "uuid": "a15bf8fc-7eae-497b-9f75-ddaf474ade51" + "label": null, + "output_name": "2:output", + "uuid": "c3c7dd49-e85e-49a3-a21e-87f8c8b59e11" + }, + { + "label": null, + "output_name": "3:output", + "uuid": "5ff717c7-df51-4c28-8605-f55a07c3a949" }, { "label": "Size Plot", "output_name": "Size Plot", "uuid": "b5516866-8b4f-41b8-a19a-12e1362d344c" + }, + { + "label": "Nx Plot", + "output_name": "Nx Plot", + "uuid": "a15bf8fc-7eae-497b-9f75-ddaf474ade51" + } + ] + }, + "52": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_cut_tool/9.3+galaxy1", + "errors": null, + "id": 52, + "input_connections": { + "input": { + "id": 50, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": null, + "name": "Advanced Cut", + "outputs": [ + { + "name": "output", + "type": "tabular" + } + ], + "position": { + "left": 5984.510589781477, + "top": 1063.1774682487087 + }, + "post_job_actions": { + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "Assembly statistics for purged assemblies" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + }, + "TagDatasetActionoutput": { + "action_arguments": { + "tags": "gfastats_p1_p2" + }, + "action_type": "TagDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_cut_tool/9.3+galaxy1", + "tool_shed_repository": { + "changeset_revision": "fbf99087e067", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"complement\": \"--complement\", \"cut_type_options\": {\"cut_element\": \"-f\", \"__current_case__\": 0, \"delimiter\": \"\", \"colnames_option\": {\"header\": \"N\", \"__current_case__\": 1, \"list\": [\"3\"]}}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "9.3+galaxy1", + "type": "tool", + "uuid": "1963d91c-104e-4845-8045-6ae47c991241", + "when": null, + "workflow_outputs": [ + { + "label": "Assembly statistics for purged assemblies", + "output_name": "output", + "uuid": "5c1dae47-1920-41b6-b86f-8627ea5e5721" + } + ] + }, + "53": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_find_and_replace/9.3+galaxy1", + "errors": null, + "id": 53, + "input_connections": { + "infile": { + "id": 52, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Replace", + "outputs": [ + { + "name": "outfile", + "type": "input" + } + ], + "position": { + "left": 6339.231196702902, + "top": 1019.7029697491412 + }, + "post_job_actions": { + "HideDatasetActionoutfile": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "outfile" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_find_and_replace/9.3+galaxy1", + "tool_shed_repository": { + "changeset_revision": "fbf99087e067", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"find_and_replace\": [{\"__index__\": 0, \"find_pattern\": \"#\", \"replace_pattern\": \"Number of\", \"is_regex\": false, \"global\": true, \"caseinsensitive\": false, \"wholewords\": false, \"skip_first_line\": false, \"searchwhere\": {\"searchwhere_select\": \"line\", \"__current_case__\": 0}}], \"infile\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "9.3+galaxy1", + "type": "tool", + "uuid": "94fb5ab8-0ebf-4302-992f-b8ca42b01780", + "when": null, + "workflow_outputs": [ + { + "label": "clean_stats", + "output_name": "outfile", + "uuid": "a022ab8b-306a-4035-8604-810d39f1bde7" } ] } @@ -3441,6 +3968,6 @@ "tags": [ "VGP_curated" ], - "uuid": "4818fdda-7a91-481a-a62f-ccab45a3c0f1", - "version": 2 + "uuid": "b5d0e4ae-3041-4cbe-9d0e-a1140e5469dd", + "version": 10 } \ No newline at end of file diff --git a/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/README.md b/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/README.md index b2d6c9577..9aeae97b2 100644 --- a/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/README.md +++ b/workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/README.md @@ -11,9 +11,11 @@ This workflow is the 6th workflow of the VGP pipeline. It is meant to be run aft 4. K-mer database [meryldb] (Generated by the k-mer profiling workflow) 5. Genomescope model parameters [txt] (Generated by the k-mer profiling workflow) 6. Estimated Genome Size [txt] -7. Name of first haplotype -8. Name of second haplotype -9. Lineage of you species for Busco Orthologs +7. Database for busco lineage (recommended: latest) +8. Lineage of your species for Busco Orthologs (recommended: vertebrata) +9. Name of first haplotype +10. Name of second haplotype + ## Outputs