From a8871e1c6fa0d9bc168b2b95342d801db2761350 Mon Sep 17 00:00:00 2001 From: Lucille Delisle Date: Fri, 8 Nov 2024 16:08:35 +0100 Subject: [PATCH 1/9] add workflows --- ...it_collection_by_pattern_in_identifiers.ga | 243 +++++++ ...t_collection_using_comma_separated_list.ga | 650 ++++++++++++++++++ .../Split_collection_using_tabular.ga | 360 ++++++++++ 3 files changed, 1253 insertions(+) create mode 100644 workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers.ga create mode 100644 workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga create mode 100644 workflows/data-manipulation/split-collection/Split_collection_using_tabular.ga diff --git a/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers.ga b/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers.ga new file mode 100644 index 000000000..8e5f1a268 --- /dev/null +++ b/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers.ga @@ -0,0 +1,243 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "This workflow takes a collection and returns 2 collections. One with the items which contains the pattern, one with the items which do not contains the pattern.", + "comments": [], + "creator": [ + { + "class": "Person", + "identifier": "https://orcid.org/0000-0002-1964-4960", + "name": "Lucille Delisle" + } + ], + "format-version": "0.1", + "license": "MIT", + "name": "Split collection by pattern in identifiers", + "report": { + "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" + }, + "steps": { + "0": { + "annotation": "Collection you want to split into 2", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "Collection you want to split into 2", + "name": "Input Dataset Collection" + } + ], + "label": "Input Dataset Collection", + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 0, + "top": 72 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list\"}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "3065a6b3-a33e-4eb3-97d7-13681b2b4e40", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "pattern used to select the items in the collection", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "pattern used to select the items in the collection", + "name": "pattern" + } + ], + "label": "pattern", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 43, + "top": 177.5 + }, + "tool_id": null, + "tool_state": "{\"parameter_type\": \"text\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "3070ffe4-0f1a-47f4-92a2-98024da29942", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.2", + "errors": null, + "id": 2, + "input_connections": { + "input_collection": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Extract element identifiers", + "outputs": [ + { + "name": "output", + "type": "txt" + } + ], + "position": { + "left": 299, + "top": 0 + }, + "post_job_actions": { + "HideDatasetActionoutput": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.2", + "tool_shed_repository": { + "changeset_revision": "d3c07d270a50", + "name": "collection_element_identifiers", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"tabular\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"input_collection\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.0.2", + "type": "tool", + "uuid": "0abdf45b-5993-4645-ae05-a9f5f0efa1f8", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_grep_tool/9.3+galaxy1", + "errors": null, + "id": 3, + "input_connections": { + "infile": { + "id": 2, + "output_name": "output" + }, + "url_paste": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [], + "label": "Select identifiers with pattern", + "name": "Search in textfiles", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 577, + "top": 106 + }, + "post_job_actions": { + "HideDatasetActionoutput": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_grep_tool/9.3+galaxy1", + "tool_shed_repository": { + "changeset_revision": "86755160afbf", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"case_sensitive\": \"-i\", \"color\": \"NOCOLOR\", \"infile\": {\"__class__\": \"ConnectedValue\"}, \"invert\": \"\", \"lines_after\": \"0\", \"lines_before\": \"0\", \"regex_type\": \"-P\", \"url_paste\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "9.3+galaxy1", + "type": "tool", + "uuid": "ec998903-14ca-463e-bbde-1d0ff8c5d0f8", + "when": null, + "workflow_outputs": [] + }, + "4": { + "annotation": "", + "content_id": "__FILTER_FROM_FILE__", + "errors": null, + "id": 4, + "input_connections": { + "how|filter_source": { + "id": 3, + "output_name": "output" + }, + "input": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter collection", + "name": "how" + } + ], + "label": "Split collection into 2", + "name": "Filter collection", + "outputs": [ + { + "name": "output_filtered", + "type": "input" + }, + { + "name": "output_discarded", + "type": "input" + } + ], + "position": { + "left": 797, + "top": 106 + }, + "post_job_actions": { + "RenameDatasetActionoutput_discarded": { + "action_arguments": { + "newname": "not ${pattern}" + }, + "action_type": "RenameDatasetAction", + "output_name": "output_discarded" + }, + "RenameDatasetActionoutput_filtered": { + "action_arguments": { + "newname": "${pattern}" + }, + "action_type": "RenameDatasetAction", + "output_name": "output_filtered" + } + }, + "tool_id": "__FILTER_FROM_FILE__", + "tool_state": "{\"how\": {\"how_filter\": \"remove_if_absent\", \"__current_case__\": 0, \"filter_source\": {\"__class__\": \"ConnectedValue\"}}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.0", + "type": "tool", + "uuid": "68b2babb-f4c1-4e5f-ba3c-e00704baa798", + "when": null, + "workflow_outputs": [ + { + "label": "unselected_collection", + "output_name": "output_discarded", + "uuid": "c94a017b-41bd-41a1-9eb5-c2a26c475c53" + }, + { + "label": "selected_collection", + "output_name": "output_filtered", + "uuid": "5a70e977-f0fc-48ca-8ec1-947b2da01a67" + } + ] + } + }, + "tags": [], + "uuid": "67c71ce5-ce8e-4d09-8e6c-e45d2ced17b6", + "version": 3 +} \ No newline at end of file diff --git a/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga b/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga new file mode 100644 index 000000000..43b145b29 --- /dev/null +++ b/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga @@ -0,0 +1,650 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "This workflow takes a collection and a comma separated list of groups and returns 2 collections: One with the items whose group assignment is the same as the first one and one with the others.", + "comments": [], + "creator": [ + { + "class": "Person", + "identifier": "https://orcid.org/0000-0002-1964-4960", + "name": "Lucille Delisle" + } + ], + "format-version": "0.1", + "license": "MIT", + "name": "Split collection using comma separated list", + "report": { + "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" + }, + "steps": { + "0": { + "annotation": "Collection you want to split into 2", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "Collection you want to split into 2", + "name": "Input Dataset Collection" + } + ], + "label": "Input Dataset Collection", + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 0.0, + "top": 0.0 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list\"}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "4f2d0e0f-4447-4dd1-bbe5-84d1a979e629", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "groups of each element of the collection separated by comma (no space), for example \"1,1,2,2\".", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "groups of each element of the collection separated by comma (no space), for example \"1,1,2,2\".", + "name": "Groups" + } + ], + "label": "Groups", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 43.36489535152572, + "top": 107.76678920335333 + }, + "tool_id": null, + "tool_state": "{\"parameter_type\": \"text\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "922bc93b-0f1e-40d8-bfa3-e4d4590ebe03", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.2", + "errors": null, + "id": 2, + "input_connections": { + "input_collection": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Extract element identifiers", + "outputs": [ + { + "name": "output", + "type": "txt" + } + ], + "position": { + "left": 369.4518201104032, + "top": 149.48743551496034 + }, + "post_job_actions": { + "HideDatasetActionoutput": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.2", + "tool_shed_repository": { + "changeset_revision": "d3c07d270a50", + "name": "collection_element_identifiers", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"tabular\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"input_collection\": null, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.0.2", + "type": "tool", + "uuid": "7e1054de-eff3-4ff4-86f4-780c051fc43b", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_text_file_with_recurring_lines/9.3+galaxy1", + "errors": null, + "id": 3, + "input_connections": { + "token_set_0|line": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [], + "label": "Create a dataset from text", + "name": "Create text file", + "outputs": [ + { + "name": "outfile", + "type": "txt" + } + ], + "position": { + "left": 369.4518201104032, + "top": 269.48743551496034 + }, + "post_job_actions": { + "HideDatasetActionoutfile": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "outfile" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_text_file_with_recurring_lines/9.3+galaxy1", + "tool_shed_repository": { + "changeset_revision": "86755160afbf", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"token_set\": [{\"__index__\": 0, \"line\": {\"__class__\": \"ConnectedValue\"}, \"repeat_select\": {\"repeat_select_opts\": \"user\", \"__current_case__\": 0, \"times\": \"1\"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "9.3+galaxy1", + "type": "tool", + "uuid": "2c2568c6-f100-4605-857f-294894573667", + "when": null, + "workflow_outputs": [] + }, + "4": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_find_and_replace/9.3+galaxy1", + "errors": null, + "id": 4, + "input_connections": { + "infile": { + "id": 3, + "output_name": "outfile" + } + }, + "inputs": [], + "label": "Replace comma by back to line", + "name": "Replace", + "outputs": [ + { + "name": "outfile", + "type": "input" + } + ], + "position": { + "left": 598.458507122122, + "top": 299.48743551496034 + }, + "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": "86755160afbf", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"find_and_replace\": [{\"__index__\": 0, \"find_pattern\": \",\", \"replace_pattern\": \"\\\\n\", \"is_regex\": true, \"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": "2502370a-2f9a-4e41-9134-686639873761", + "when": null, + "workflow_outputs": [] + }, + "5": { + "annotation": "", + "content_id": "Paste1", + "errors": null, + "id": 5, + "input_connections": { + "input1": { + "id": 2, + "output_name": "output" + }, + "input2": { + "id": 4, + "output_name": "outfile" + } + }, + "inputs": [], + "label": "Put side by side identifiers and groups", + "name": "Paste", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 809.4518201104032, + "top": 149.48743551496034 + }, + "post_job_actions": { + "ChangeDatatypeActionout_file1": { + "action_arguments": { + "newtype": "tabular" + }, + "action_type": "ChangeDatatypeAction", + "output_name": "out_file1" + }, + "HideDatasetActionout_file1": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Paste1", + "tool_state": "{\"__input_ext\": \"txt\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"delimiter\": \"T\", \"input1\": {\"__class__\": \"ConnectedValue\"}, \"input2\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.0", + "type": "tool", + "uuid": "8bca840e-00ad-4b75-b2c4-16a506dc6397", + "when": null, + "workflow_outputs": [] + }, + "6": { + "annotation": "", + "id": 6, + "input_connections": { + "Input Dataset Collection": { + "id": 0, + "input_subworkflow_step_id": 0, + "output_name": "output" + }, + "identifier mapping": { + "id": 5, + "input_subworkflow_step_id": 1, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": null, + "name": "Split collection using tabular", + "outputs": [], + "position": { + "left": 1056.0418201104033, + "top": 153.98743551496034 + }, + "subworkflow": { + "a_galaxy_workflow": "true", + "annotation": "", + "comments": [], + "creator": [ + { + "class": "Person", + "identifier": "https://orcid.org/0000-0002-1964-4960", + "name": "Lucille Delisle" + } + ], + "format-version": "0.1", + "license": "MIT", + "name": "Split collection using tabular", + "report": { + "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" + }, + "steps": { + "0": { + "annotation": "Collection you want to split into 2", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "Collection you want to split into 2", + "name": "Input Dataset Collection" + } + ], + "label": "Input Dataset Collection", + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 0, + "top": 0 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list\"}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "25938412-e737-4d0c-892f-497a548ce40b", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "tabular where first column matches identifers of input collection and second column indicates the group", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "tabular where first column matches identifers of input collection and second column indicates the group", + "name": "identifier mapping" + } + ], + "label": "identifier mapping", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 76, + "top": 114.5 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"format\": [\"tabular\"], \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "5d71aaff-1050-406f-875a-e671bd530867", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.3+galaxy1", + "errors": null, + "id": 2, + "input_connections": { + "infile": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [], + "label": "get the first group value", + "name": "Text reformatting", + "outputs": [ + { + "name": "outfile", + "type": "input" + } + ], + "position": { + "left": 370, + "top": 334 + }, + "post_job_actions": { + "HideDatasetActionoutfile": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "outfile" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.3+galaxy1", + "tool_shed_repository": { + "changeset_revision": "86755160afbf", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"code\": \"NR==1{print $2}\", \"infile\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "9.3+galaxy1", + "type": "tool", + "uuid": "f2c7d369-5e51-4a06-8bbf-86fac09d3601", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "", + "content_id": "param_value_from_file", + "errors": null, + "id": 3, + "input_connections": { + "input1": { + "id": 2, + "output_name": "outfile" + } + }, + "inputs": [], + "label": "convert to parameter", + "name": "Parse parameter value", + "outputs": [ + { + "name": "text_param", + "type": "expression.json" + } + ], + "position": { + "left": 638.34, + "top": 347.5 + }, + "post_job_actions": { + "HideDatasetActiontext_param": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "text_param" + } + }, + "tool_id": "param_value_from_file", + "tool_state": "{\"input1\": {\"__class__\": \"ConnectedValue\"}, \"param_type\": \"text\", \"remove_newlines\": true, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.1.0", + "type": "tool", + "uuid": "2d67559f-0da3-4b52-97e1-e7c7bd1ba83f", + "when": null, + "workflow_outputs": [] + }, + "4": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/compose_text_param/compose_text_param/0.1.1", + "errors": null, + "id": 4, + "input_connections": { + "components_1|param_type|component_value": { + "id": 3, + "output_name": "text_param" + } + }, + "inputs": [], + "label": "make filter condition", + "name": "Compose text parameter value", + "outputs": [ + { + "name": "out1", + "type": "expression.json" + } + ], + "position": { + "left": 869.1832700991363, + "top": 358.015694923965 + }, + "post_job_actions": { + "HideDatasetActionout1": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "out1" + } + }, + "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\": \"c2 == \\\"\"}}, {\"__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\": \"\\\"\"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.1.1", + "type": "tool", + "uuid": "72928cef-e147-45c0-866e-d3bdc5d82937", + "when": null, + "workflow_outputs": [] + }, + "5": { + "annotation": "", + "content_id": "Filter1", + "errors": null, + "id": 5, + "input_connections": { + "cond": { + "id": 4, + "output_name": "out1" + }, + "input": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [], + "label": "filter tabular to get only lines with first group", + "name": "Filter", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 1094.6521773218315, + "top": 312.3648800009677 + }, + "post_job_actions": { + "HideDatasetActionout_file1": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Filter1", + "tool_state": "{\"cond\": {\"__class__\": \"ConnectedValue\"}, \"header_lines\": \"0\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.1.1", + "type": "tool", + "uuid": "f07fefb8-f736-4d02-8f7f-8467735c760c", + "when": null, + "workflow_outputs": [] + }, + "6": { + "annotation": "", + "content_id": "Cut1", + "errors": null, + "id": 6, + "input_connections": { + "input": { + "id": 5, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": "keep only identifiers", + "name": "Cut", + "outputs": [ + { + "name": "out_file1", + "type": "tabular" + } + ], + "position": { + "left": 1345.2875324397519, + "top": 323.498696348884 + }, + "post_job_actions": { + "HideDatasetActionout_file1": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Cut1", + "tool_state": "{\"__input_ext\": \"tabular\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"columnList\": \"c1\", \"delimiter\": \"T\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.2", + "type": "tool", + "uuid": "364f21f7-fc99-4ad3-aa03-5379abeaa91d", + "when": null, + "workflow_outputs": [] + }, + "7": { + "annotation": "", + "content_id": "__FILTER_FROM_FILE__", + "errors": null, + "id": 7, + "input_connections": { + "how|filter_source": { + "id": 6, + "output_name": "out_file1" + }, + "input": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter collection", + "name": "how" + } + ], + "label": "Split collection into 2", + "name": "Filter collection", + "outputs": [ + { + "name": "output_filtered", + "type": "input" + }, + { + "name": "output_discarded", + "type": "input" + } + ], + "position": { + "left": 1604.8936434420398, + "top": 252.46106251153242 + }, + "post_job_actions": { + "RenameDatasetActionoutput_discarded": { + "action_arguments": { + "newname": "not first group" + }, + "action_type": "RenameDatasetAction", + "output_name": "output_discarded" + }, + "RenameDatasetActionoutput_filtered": { + "action_arguments": { + "newname": "first group" + }, + "action_type": "RenameDatasetAction", + "output_name": "output_filtered" + } + }, + "tool_id": "__FILTER_FROM_FILE__", + "tool_state": "{\"how\": {\"how_filter\": \"remove_if_absent\", \"__current_case__\": 0, \"filter_source\": {\"__class__\": \"ConnectedValue\"}}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.0", + "type": "tool", + "uuid": "8ff72610-8349-4862-b66e-1416e40ff95a", + "when": null, + "workflow_outputs": [ + { + "label": "collection_first_group", + "output_name": "output_filtered", + "uuid": "32af9f5d-c3f1-437a-8b08-6032212dd277" + }, + { + "label": "collection_other", + "output_name": "output_discarded", + "uuid": "d8721c45-506c-4378-95fc-a951cd854fc5" + } + ] + } + }, + "tags": [], + "uuid": "11bb0822-24d7-4e26-adc8-2f389dddae88" + }, + "tool_id": null, + "type": "subworkflow", + "uuid": "6bb1b0b5-802d-4eed-b18e-2d3769f90c07", + "when": null, + "workflow_outputs": [] + } + }, + "tags": [], + "uuid": "fcaa95a1-9b92-474e-8807-a124b9fd54a7", + "version": 1 +} \ No newline at end of file diff --git a/workflows/data-manipulation/split-collection/Split_collection_using_tabular.ga b/workflows/data-manipulation/split-collection/Split_collection_using_tabular.ga new file mode 100644 index 000000000..ec13d964e --- /dev/null +++ b/workflows/data-manipulation/split-collection/Split_collection_using_tabular.ga @@ -0,0 +1,360 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "This workflow takes a collection and a tabular with 2 columns (one matches the identifiers of the collection, the second indicates the group) and returns 2 collections: One with the items which were in the tabular and whose second column value was the same as the first item and one with the others.", + "comments": [], + "creator": [ + { + "class": "Person", + "identifier": "https://orcid.org/0000-0002-1964-4960", + "name": "Lucille Delisle" + } + ], + "format-version": "0.1", + "license": "MIT", + "name": "Split collection using tabular", + "report": { + "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" + }, + "steps": { + "0": { + "annotation": "Collection you want to split into 2", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "Collection you want to split into 2", + "name": "Input Dataset Collection" + } + ], + "label": "Input Dataset Collection", + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 0, + "top": 0 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list\"}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "25938412-e737-4d0c-892f-497a548ce40b", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "tabular where first column matches identifers of input collection and second column indicates the group", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "tabular where first column matches identifers of input collection and second column indicates the group", + "name": "identifier mapping" + } + ], + "label": "identifier mapping", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 76, + "top": 114.5 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"format\": [\"tabular\"], \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "5d71aaff-1050-406f-875a-e671bd530867", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.3+galaxy1", + "errors": null, + "id": 2, + "input_connections": { + "infile": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [], + "label": "get the first group value", + "name": "Text reformatting", + "outputs": [ + { + "name": "outfile", + "type": "input" + } + ], + "position": { + "left": 370, + "top": 334 + }, + "post_job_actions": { + "HideDatasetActionoutfile": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "outfile" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.3+galaxy1", + "tool_shed_repository": { + "changeset_revision": "86755160afbf", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"code\": \"NR==1{print $2}\", \"infile\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "9.3+galaxy1", + "type": "tool", + "uuid": "f2c7d369-5e51-4a06-8bbf-86fac09d3601", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "", + "content_id": "param_value_from_file", + "errors": null, + "id": 3, + "input_connections": { + "input1": { + "id": 2, + "output_name": "outfile" + } + }, + "inputs": [], + "label": "convert to parameter", + "name": "Parse parameter value", + "outputs": [ + { + "name": "text_param", + "type": "expression.json" + } + ], + "position": { + "left": 638.34, + "top": 347.5 + }, + "post_job_actions": { + "HideDatasetActiontext_param": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "text_param" + } + }, + "tool_id": "param_value_from_file", + "tool_state": "{\"input1\": {\"__class__\": \"ConnectedValue\"}, \"param_type\": \"text\", \"remove_newlines\": true, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.1.0", + "type": "tool", + "uuid": "2d67559f-0da3-4b52-97e1-e7c7bd1ba83f", + "when": null, + "workflow_outputs": [] + }, + "4": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/compose_text_param/compose_text_param/0.1.1", + "errors": null, + "id": 4, + "input_connections": { + "components_1|param_type|component_value": { + "id": 3, + "output_name": "text_param" + } + }, + "inputs": [], + "label": "make filter condition", + "name": "Compose text parameter value", + "outputs": [ + { + "name": "out1", + "type": "expression.json" + } + ], + "position": { + "left": 869.1832700991363, + "top": 358.015694923965 + }, + "post_job_actions": { + "HideDatasetActionout1": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "out1" + } + }, + "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\": \"c2 == \\\"\"}}, {\"__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\": \"\\\"\"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.1.1", + "type": "tool", + "uuid": "72928cef-e147-45c0-866e-d3bdc5d82937", + "when": null, + "workflow_outputs": [] + }, + "5": { + "annotation": "", + "content_id": "Filter1", + "errors": null, + "id": 5, + "input_connections": { + "cond": { + "id": 4, + "output_name": "out1" + }, + "input": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [], + "label": "filter tabular to get only lines with first group", + "name": "Filter", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 1094.6521773218315, + "top": 312.3648800009677 + }, + "post_job_actions": { + "HideDatasetActionout_file1": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Filter1", + "tool_state": "{\"cond\": {\"__class__\": \"ConnectedValue\"}, \"header_lines\": \"0\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.1.1", + "type": "tool", + "uuid": "f07fefb8-f736-4d02-8f7f-8467735c760c", + "when": null, + "workflow_outputs": [] + }, + "6": { + "annotation": "", + "content_id": "Cut1", + "errors": null, + "id": 6, + "input_connections": { + "input": { + "id": 5, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": "keep only identifiers", + "name": "Cut", + "outputs": [ + { + "name": "out_file1", + "type": "tabular" + } + ], + "position": { + "left": 1345.2875324397519, + "top": 323.498696348884 + }, + "post_job_actions": { + "HideDatasetActionout_file1": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Cut1", + "tool_state": "{\"__input_ext\": \"tabular\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"columnList\": \"c1\", \"delimiter\": \"T\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.2", + "type": "tool", + "uuid": "364f21f7-fc99-4ad3-aa03-5379abeaa91d", + "when": null, + "workflow_outputs": [] + }, + "7": { + "annotation": "", + "content_id": "__FILTER_FROM_FILE__", + "errors": null, + "id": 7, + "input_connections": { + "how|filter_source": { + "id": 6, + "output_name": "out_file1" + }, + "input": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter collection", + "name": "how" + } + ], + "label": "Split collection into 2", + "name": "Filter collection", + "outputs": [ + { + "name": "output_filtered", + "type": "input" + }, + { + "name": "output_discarded", + "type": "input" + } + ], + "position": { + "left": 1604.8936434420398, + "top": 252.46106251153242 + }, + "post_job_actions": { + "RenameDatasetActionoutput_discarded": { + "action_arguments": { + "newname": "not first group" + }, + "action_type": "RenameDatasetAction", + "output_name": "output_discarded" + }, + "RenameDatasetActionoutput_filtered": { + "action_arguments": { + "newname": "first group" + }, + "action_type": "RenameDatasetAction", + "output_name": "output_filtered" + } + }, + "tool_id": "__FILTER_FROM_FILE__", + "tool_state": "{\"how\": {\"how_filter\": \"remove_if_absent\", \"__current_case__\": 0, \"filter_source\": {\"__class__\": \"ConnectedValue\"}}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.0", + "type": "tool", + "uuid": "8ff72610-8349-4862-b66e-1416e40ff95a", + "when": null, + "workflow_outputs": [ + { + "label": "collection_other", + "output_name": "output_discarded", + "uuid": "d8721c45-506c-4378-95fc-a951cd854fc5" + }, + { + "label": "collection_first_group", + "output_name": "output_filtered", + "uuid": "32af9f5d-c3f1-437a-8b08-6032212dd277" + } + ] + } + }, + "tags": [], + "uuid": "11bb0822-24d7-4e26-adc8-2f389dddae88", + "version": 3 +} \ No newline at end of file From e2903b52df27ca059c87fe93eff1a59839e471b7 Mon Sep 17 00:00:00 2001 From: Lucille Delisle Date: Tue, 12 Nov 2024 11:58:53 +0100 Subject: [PATCH 2/9] add tests --- ...ection_by_pattern_in_identifiers_tests.yml | 51 +++++++++++++++++ ...t_collection_using_comma_separated_list.ga | 23 ++++++-- ...ction_using_comma_separated_list_tests.yml | 52 +++++++++++++++++ .../Split_collection_using_tabular_tests.yml | 56 +++++++++++++++++++ .../split-collection/test-data/file.txt | 1 + .../test-data/group_asignment.txt | 5 ++ 6 files changed, 182 insertions(+), 6 deletions(-) create mode 100644 workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers_tests.yml create mode 100644 workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list_tests.yml create mode 100644 workflows/data-manipulation/split-collection/Split_collection_using_tabular_tests.yml create mode 100644 workflows/data-manipulation/split-collection/test-data/file.txt create mode 100644 workflows/data-manipulation/split-collection/test-data/group_asignment.txt diff --git a/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers_tests.yml b/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers_tests.yml new file mode 100644 index 000000000..93f1ea5c6 --- /dev/null +++ b/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers_tests.yml @@ -0,0 +1,51 @@ +- doc: Test outline for Split_collection_by_pattern_in_identifiers.ga + job: + Input Dataset Collection: + class: Collection + collection_type: list + elements: + - class: File + identifier: cat1_1 + path: test-data/file.txt + - class: File + identifier: cat1_2 + path: test-data/file.txt + - class: File + identifier: cat1_3 + path: test-data/file.txt + - class: File + identifier: cat2_1 + path: test-data/file.txt + - class: File + identifier: cat3_1 + path: test-data/file.txt + pattern: cat1 + outputs: + unselected_collection: + class: Collection + collection_type: list + element_tests: + cat2_1: + asserts: + has_text: + text: "whatever" + cat3_1: + asserts: + has_text: + text: "whatever" + selected_collection: + class: Collection + collection_type: list + element_tests: + cat1_1: + asserts: + has_text: + text: "whatever" + cat1_2: + asserts: + has_text: + text: "whatever" + cat1_3: + asserts: + has_text: + text: "whatever" diff --git a/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga b/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga index 43b145b29..46cf9ee19 100644 --- a/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga +++ b/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga @@ -32,8 +32,8 @@ "name": "Input dataset collection", "outputs": [], "position": { - "left": 0.0, - "top": 0.0 + "left": 0, + "top": 0 }, "tool_id": null, "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list\"}", @@ -108,7 +108,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"__input_ext\": \"tabular\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"input_collection\": null, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"__input_ext\": \"tabular\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"input_collection\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "0.0.2", "type": "tool", "uuid": "7e1054de-eff3-4ff4-86f4-780c051fc43b", @@ -641,10 +641,21 @@ "type": "subworkflow", "uuid": "6bb1b0b5-802d-4eed-b18e-2d3769f90c07", "when": null, - "workflow_outputs": [] + "workflow_outputs": [ + { + "label": "collection_other", + "output_name": "collection_other", + "uuid": "508ac256-3c68-4024-83d4-d2966f7b2fa6" + }, + { + "label": "collection_first_group", + "output_name": "collection_first_group", + "uuid": "99c02ccc-4c97-4d80-a112-513a260832fa" + } + ] } }, "tags": [], - "uuid": "fcaa95a1-9b92-474e-8807-a124b9fd54a7", - "version": 1 + "uuid": "cb0eeee3-59c5-48c7-b14a-c66826ec2f93", + "version": 2 } \ No newline at end of file diff --git a/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list_tests.yml b/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list_tests.yml new file mode 100644 index 000000000..bf2ddae8b --- /dev/null +++ b/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list_tests.yml @@ -0,0 +1,52 @@ +- doc: Test outline for Split_collection_using_comma_separated_list.ga + job: + Input Dataset Collection: + class: Collection + collection_type: list + elements: + - class: File + identifier: cat1_1 + path: test-data/file.txt + - class: File + identifier: cat1_2 + path: test-data/file.txt + - class: File + identifier: cat1_3 + path: test-data/file.txt + - class: File + identifier: cat2_1 + path: test-data/file.txt + - class: File + identifier: cat3_1 + path: test-data/file.txt + Groups: 1,1,1,2,3 + outputs: + collection_other: + class: Collection + collection_type: list + element_tests: + cat2_1: + asserts: + has_text: + text: "whatever" + cat3_1: + asserts: + has_text: + text: "whatever" + collection_first_group: + class: Collection + collection_type: list + element_tests: + cat1_1: + asserts: + has_text: + text: "whatever" + cat1_2: + asserts: + has_text: + text: "whatever" + cat1_3: + asserts: + has_text: + text: "whatever" + diff --git a/workflows/data-manipulation/split-collection/Split_collection_using_tabular_tests.yml b/workflows/data-manipulation/split-collection/Split_collection_using_tabular_tests.yml new file mode 100644 index 000000000..44948c1b2 --- /dev/null +++ b/workflows/data-manipulation/split-collection/Split_collection_using_tabular_tests.yml @@ -0,0 +1,56 @@ +- doc: Test outline for Split_collection_using_tabular.ga + job: + Input Dataset Collection: + class: Collection + collection_type: list + elements: + - class: File + identifier: cat1_1 + path: test-data/file.txt + - class: File + identifier: cat1_2 + path: test-data/file.txt + - class: File + identifier: cat1_3 + path: test-data/file.txt + - class: File + identifier: cat2_1 + path: test-data/file.txt + - class: File + identifier: cat3_1 + path: test-data/file.txt + identifier mapping: + class: File + path: group_asignment.txt + datatype: tabular + outputs: + collection_other: + class: Collection + collection_type: list + element_tests: + cat2_1: + asserts: + has_text: + text: "whatever" + cat3_1: + asserts: + has_text: + text: "whatever" + collection_first_group: + class: Collection + collection_type: list + element_tests: + cat1_1: + asserts: + has_text: + text: "whatever" + cat1_2: + asserts: + has_text: + text: "whatever" + cat1_3: + asserts: + has_text: + text: "whatever" + + diff --git a/workflows/data-manipulation/split-collection/test-data/file.txt b/workflows/data-manipulation/split-collection/test-data/file.txt new file mode 100644 index 000000000..982793c32 --- /dev/null +++ b/workflows/data-manipulation/split-collection/test-data/file.txt @@ -0,0 +1 @@ +whatever diff --git a/workflows/data-manipulation/split-collection/test-data/group_asignment.txt b/workflows/data-manipulation/split-collection/test-data/group_asignment.txt new file mode 100644 index 000000000..2676868b4 --- /dev/null +++ b/workflows/data-manipulation/split-collection/test-data/group_asignment.txt @@ -0,0 +1,5 @@ +cat1_1 1 +cat1_2 1 +cat1_3 1 +cat2_1 2 +cat3_1 3 From a863ef367f01ebc39912cc514fb26e99a1fc94c3 Mon Sep 17 00:00:00 2001 From: Lucille Delisle Date: Tue, 12 Nov 2024 11:59:05 +0100 Subject: [PATCH 3/9] add .dockstore --- .../split-collection/.dockstore.yml | 23 +++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 workflows/data-manipulation/split-collection/.dockstore.yml diff --git a/workflows/data-manipulation/split-collection/.dockstore.yml b/workflows/data-manipulation/split-collection/.dockstore.yml new file mode 100644 index 000000000..d501782c8 --- /dev/null +++ b/workflows/data-manipulation/split-collection/.dockstore.yml @@ -0,0 +1,23 @@ +version: 1.2 +workflows: +- name: Split_collection_using_tabular + subclass: Galaxy + publish: true + primaryDescriptorPath: /Split_collection_using_tabular.ga + authors: + - name: Lucille Delisle + orcid: 0000-0002-1964-4960 +- name: Split_collection_using_comma_separated_list + subclass: Galaxy + publish: true + primaryDescriptorPath: /Split_collection_using_comma_separated_list.ga + authors: + - name: Lucille Delisle + orcid: 0000-0002-1964-4960 +- name: Split_collection_by_pattern_in_identifiers + subclass: Galaxy + publish: true + primaryDescriptorPath: /Split_collection_by_pattern_in_identifiers.ga + authors: + - name: Lucille Delisle + orcid: 0000-0002-1964-4960 From 5733596117d5a6e785fdd67c4fb3688961513267 Mon Sep 17 00:00:00 2001 From: Lucille Delisle Date: Tue, 12 Nov 2024 12:54:07 +0100 Subject: [PATCH 4/9] add README CHANGELOG release --- .../split-collection/CHANGELOG.md | 5 +++++ .../data-manipulation/split-collection/README.md | 14 ++++++++++++++ .../Split_collection_by_pattern_in_identifiers.ga | 1 + .../Split_collection_using_comma_separated_list.ga | 1 + .../Split_collection_using_tabular.ga | 1 + 5 files changed, 22 insertions(+) create mode 100644 workflows/data-manipulation/split-collection/CHANGELOG.md create mode 100644 workflows/data-manipulation/split-collection/README.md diff --git a/workflows/data-manipulation/split-collection/CHANGELOG.md b/workflows/data-manipulation/split-collection/CHANGELOG.md new file mode 100644 index 000000000..2954c5f21 --- /dev/null +++ b/workflows/data-manipulation/split-collection/CHANGELOG.md @@ -0,0 +1,5 @@ +# Changelog + +## [0.1] 2024-11-12 + +First release diff --git a/workflows/data-manipulation/split-collection/README.md b/workflows/data-manipulation/split-collection/README.md new file mode 100644 index 000000000..04a1f113c --- /dev/null +++ b/workflows/data-manipulation/split-collection/README.md @@ -0,0 +1,14 @@ +# Split collection + +These workflows allow to split a collection into 2 using identifiers. + +The common input to all workflows is a collection of type 'list'. + +The way to split the collection differs with the workflow. + +- In the workflow "Split collection by pattern in identifiers", you need to specify a "pattern". This is a word that is present only in one part of your samples. This will split your collection into 2: one with the identifiers which have the 'pattern' and the other one with the identifiers which don't have. +- In the workflow "Split collection using tabular", you need to give a tabular where the first column is the identifier and the second column is the group (no header). All identifiers where the second column match the first item will be grouped into a collection. Others will be in another collection. +- In the workflow "Split collection using comma separated list", you need to give the group of each item of your collection separated by comma. For example, if you have 3 items in your collection, you can put "1,1,2" to put the first 2 together and the third one appart. + +Warnings: +- If you specify more than 2 groups in the second and third workflow, it will not create 3 collections. diff --git a/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers.ga b/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers.ga index 8e5f1a268..17efc9cf0 100644 --- a/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers.ga +++ b/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers.ga @@ -11,6 +11,7 @@ ], "format-version": "0.1", "license": "MIT", + "release": "0.1", "name": "Split collection by pattern in identifiers", "report": { "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" diff --git a/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga b/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga index 46cf9ee19..2257cb2a0 100644 --- a/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga +++ b/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga @@ -11,6 +11,7 @@ ], "format-version": "0.1", "license": "MIT", + "release": "0.1", "name": "Split collection using comma separated list", "report": { "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" diff --git a/workflows/data-manipulation/split-collection/Split_collection_using_tabular.ga b/workflows/data-manipulation/split-collection/Split_collection_using_tabular.ga index ec13d964e..54f00eef5 100644 --- a/workflows/data-manipulation/split-collection/Split_collection_using_tabular.ga +++ b/workflows/data-manipulation/split-collection/Split_collection_using_tabular.ga @@ -11,6 +11,7 @@ ], "format-version": "0.1", "license": "MIT", + "release": "0.1", "name": "Split collection using tabular", "report": { "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" From 86b19a69d77b62a3482a6e7aeaa42bb3ce116be3 Mon Sep 17 00:00:00 2001 From: Lucille Delisle Date: Tue, 12 Nov 2024 12:57:09 +0100 Subject: [PATCH 5/9] relabel tests files and update dockstore --- workflows/data-manipulation/split-collection/.dockstore.yml | 6 ++++++ ...=> Split_collection_by_pattern_in_identifiers-tests.yml} | 0 ...> Split_collection_using_comma_separated_list-tests.yml} | 0 ...r_tests.yml => Split_collection_using_tabular-tests.yml} | 0 4 files changed, 6 insertions(+) rename workflows/data-manipulation/split-collection/{Split_collection_by_pattern_in_identifiers_tests.yml => Split_collection_by_pattern_in_identifiers-tests.yml} (100%) rename workflows/data-manipulation/split-collection/{Split_collection_using_comma_separated_list_tests.yml => Split_collection_using_comma_separated_list-tests.yml} (100%) rename workflows/data-manipulation/split-collection/{Split_collection_using_tabular_tests.yml => Split_collection_using_tabular-tests.yml} (100%) diff --git a/workflows/data-manipulation/split-collection/.dockstore.yml b/workflows/data-manipulation/split-collection/.dockstore.yml index d501782c8..b6be96bf0 100644 --- a/workflows/data-manipulation/split-collection/.dockstore.yml +++ b/workflows/data-manipulation/split-collection/.dockstore.yml @@ -4,6 +4,8 @@ workflows: subclass: Galaxy publish: true primaryDescriptorPath: /Split_collection_using_tabular.ga + testParameterFiles: + - /Split_collection_using_tabular-tests.yml authors: - name: Lucille Delisle orcid: 0000-0002-1964-4960 @@ -11,6 +13,8 @@ workflows: subclass: Galaxy publish: true primaryDescriptorPath: /Split_collection_using_comma_separated_list.ga + testParameterFiles: + - /Split_collection_using_comma_separated_list-tests.yml authors: - name: Lucille Delisle orcid: 0000-0002-1964-4960 @@ -18,6 +22,8 @@ workflows: subclass: Galaxy publish: true primaryDescriptorPath: /Split_collection_by_pattern_in_identifiers.ga + testParameterFiles: + - /Split_collection_by_pattern_in_identifiers-tests.yml authors: - name: Lucille Delisle orcid: 0000-0002-1964-4960 diff --git a/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers_tests.yml b/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers-tests.yml similarity index 100% rename from workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers_tests.yml rename to workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers-tests.yml diff --git a/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list_tests.yml b/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list-tests.yml similarity index 100% rename from workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list_tests.yml rename to workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list-tests.yml diff --git a/workflows/data-manipulation/split-collection/Split_collection_using_tabular_tests.yml b/workflows/data-manipulation/split-collection/Split_collection_using_tabular-tests.yml similarity index 100% rename from workflows/data-manipulation/split-collection/Split_collection_using_tabular_tests.yml rename to workflows/data-manipulation/split-collection/Split_collection_using_tabular-tests.yml From f3dfa057926ad36c082d82fd24b31a0d8c06c128 Mon Sep 17 00:00:00 2001 From: Lucille Delisle Date: Tue, 12 Nov 2024 13:03:54 +0100 Subject: [PATCH 6/9] use - instead of _ --- .../split-collection/.dockstore.yml | 18 +++++++++--------- ...ection-by-pattern-in-identifiers-tests.yml} | 2 +- ...it-collection-by-pattern-in-identifiers.ga} | 0 ...ction-using-comma-separated-list-tests.yml} | 2 +- ...t-collection-using-comma-separated-list.ga} | 0 ...> Split-collection-using-tabular-tests.yml} | 2 +- ...ar.ga => Split-collection-using-tabular.ga} | 0 7 files changed, 12 insertions(+), 12 deletions(-) rename workflows/data-manipulation/split-collection/{Split_collection_by_pattern_in_identifiers-tests.yml => Split-collection-by-pattern-in-identifiers-tests.yml} (94%) rename workflows/data-manipulation/split-collection/{Split_collection_by_pattern_in_identifiers.ga => Split-collection-by-pattern-in-identifiers.ga} (100%) rename workflows/data-manipulation/split-collection/{Split_collection_using_comma_separated_list-tests.yml => Split-collection-using-comma-separated-list-tests.yml} (94%) rename workflows/data-manipulation/split-collection/{Split_collection_using_comma_separated_list.ga => Split-collection-using-comma-separated-list.ga} (100%) rename workflows/data-manipulation/split-collection/{Split_collection_using_tabular-tests.yml => Split-collection-using-tabular-tests.yml} (95%) rename workflows/data-manipulation/split-collection/{Split_collection_using_tabular.ga => Split-collection-using-tabular.ga} (100%) diff --git a/workflows/data-manipulation/split-collection/.dockstore.yml b/workflows/data-manipulation/split-collection/.dockstore.yml index b6be96bf0..3620212e9 100644 --- a/workflows/data-manipulation/split-collection/.dockstore.yml +++ b/workflows/data-manipulation/split-collection/.dockstore.yml @@ -1,29 +1,29 @@ version: 1.2 workflows: -- name: Split_collection_using_tabular +- name: Split collection by pattern in identifiers subclass: Galaxy publish: true - primaryDescriptorPath: /Split_collection_using_tabular.ga + primaryDescriptorPath: /Split-collection-by-pattern-in-identifiers.ga testParameterFiles: - - /Split_collection_using_tabular-tests.yml + - /Split-collection-by-pattern-in-identifiers-tests.yml authors: - name: Lucille Delisle orcid: 0000-0002-1964-4960 -- name: Split_collection_using_comma_separated_list +- name: Split collection using tabular subclass: Galaxy publish: true - primaryDescriptorPath: /Split_collection_using_comma_separated_list.ga + primaryDescriptorPath: /Split-collection-using-tabular.ga testParameterFiles: - - /Split_collection_using_comma_separated_list-tests.yml + - /Split-collection-using-tabular-tests.yml authors: - name: Lucille Delisle orcid: 0000-0002-1964-4960 -- name: Split_collection_by_pattern_in_identifiers +- name: Split collection using comma-separated list subclass: Galaxy publish: true - primaryDescriptorPath: /Split_collection_by_pattern_in_identifiers.ga + primaryDescriptorPath: /Split-collection-using-comma-separated-list.ga testParameterFiles: - - /Split_collection_by_pattern_in_identifiers-tests.yml + - /Split-collection-using-comma-separated-list-tests.yml authors: - name: Lucille Delisle orcid: 0000-0002-1964-4960 diff --git a/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers-tests.yml b/workflows/data-manipulation/split-collection/Split-collection-by-pattern-in-identifiers-tests.yml similarity index 94% rename from workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers-tests.yml rename to workflows/data-manipulation/split-collection/Split-collection-by-pattern-in-identifiers-tests.yml index 93f1ea5c6..aa4ec7cb9 100644 --- a/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers-tests.yml +++ b/workflows/data-manipulation/split-collection/Split-collection-by-pattern-in-identifiers-tests.yml @@ -1,4 +1,4 @@ -- doc: Test outline for Split_collection_by_pattern_in_identifiers.ga +- doc: Test outline for Split-collection-by-pattern-in-identifiers.ga job: Input Dataset Collection: class: Collection diff --git a/workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers.ga b/workflows/data-manipulation/split-collection/Split-collection-by-pattern-in-identifiers.ga similarity index 100% rename from workflows/data-manipulation/split-collection/Split_collection_by_pattern_in_identifiers.ga rename to workflows/data-manipulation/split-collection/Split-collection-by-pattern-in-identifiers.ga diff --git a/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list-tests.yml b/workflows/data-manipulation/split-collection/Split-collection-using-comma-separated-list-tests.yml similarity index 94% rename from workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list-tests.yml rename to workflows/data-manipulation/split-collection/Split-collection-using-comma-separated-list-tests.yml index bf2ddae8b..5ed826226 100644 --- a/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list-tests.yml +++ b/workflows/data-manipulation/split-collection/Split-collection-using-comma-separated-list-tests.yml @@ -1,4 +1,4 @@ -- doc: Test outline for Split_collection_using_comma_separated_list.ga +- doc: Test outline for Split-collection-using-comma-separated-list.ga job: Input Dataset Collection: class: Collection diff --git a/workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga b/workflows/data-manipulation/split-collection/Split-collection-using-comma-separated-list.ga similarity index 100% rename from workflows/data-manipulation/split-collection/Split_collection_using_comma_separated_list.ga rename to workflows/data-manipulation/split-collection/Split-collection-using-comma-separated-list.ga diff --git a/workflows/data-manipulation/split-collection/Split_collection_using_tabular-tests.yml b/workflows/data-manipulation/split-collection/Split-collection-using-tabular-tests.yml similarity index 95% rename from workflows/data-manipulation/split-collection/Split_collection_using_tabular-tests.yml rename to workflows/data-manipulation/split-collection/Split-collection-using-tabular-tests.yml index 44948c1b2..b6fa5b275 100644 --- a/workflows/data-manipulation/split-collection/Split_collection_using_tabular-tests.yml +++ b/workflows/data-manipulation/split-collection/Split-collection-using-tabular-tests.yml @@ -1,4 +1,4 @@ -- doc: Test outline for Split_collection_using_tabular.ga +- doc: Test outline for Split-collection-using-tabular.ga job: Input Dataset Collection: class: Collection diff --git a/workflows/data-manipulation/split-collection/Split_collection_using_tabular.ga b/workflows/data-manipulation/split-collection/Split-collection-using-tabular.ga similarity index 100% rename from workflows/data-manipulation/split-collection/Split_collection_using_tabular.ga rename to workflows/data-manipulation/split-collection/Split-collection-using-tabular.ga From 2208649607f19e3b227b7c26bb903864d7826112 Mon Sep 17 00:00:00 2001 From: Lucille Delisle Date: Tue, 12 Nov 2024 13:08:16 +0100 Subject: [PATCH 7/9] do not get space in workflow names --- workflows/data-manipulation/split-collection/.dockstore.yml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/workflows/data-manipulation/split-collection/.dockstore.yml b/workflows/data-manipulation/split-collection/.dockstore.yml index 3620212e9..c4eb4c60f 100644 --- a/workflows/data-manipulation/split-collection/.dockstore.yml +++ b/workflows/data-manipulation/split-collection/.dockstore.yml @@ -1,6 +1,6 @@ version: 1.2 workflows: -- name: Split collection by pattern in identifiers +- name: Split-collection-by-pattern-in-identifiers subclass: Galaxy publish: true primaryDescriptorPath: /Split-collection-by-pattern-in-identifiers.ga @@ -9,7 +9,7 @@ workflows: authors: - name: Lucille Delisle orcid: 0000-0002-1964-4960 -- name: Split collection using tabular +- name: Split-collection-using-tabular subclass: Galaxy publish: true primaryDescriptorPath: /Split-collection-using-tabular.ga @@ -18,7 +18,7 @@ workflows: authors: - name: Lucille Delisle orcid: 0000-0002-1964-4960 -- name: Split collection using comma-separated list +- name: Split-collection-using-comma-separated-list subclass: Galaxy publish: true primaryDescriptorPath: /Split-collection-using-comma-separated-list.ga From 0619a94b5f621c58d4649faafc2a192058d35404 Mon Sep 17 00:00:00 2001 From: Lucille Delisle Date: Tue, 12 Nov 2024 13:51:24 +0100 Subject: [PATCH 8/9] update workflows and tests --- ...t-collection-using-comma-separated-list.ga | 124 +++++++----------- .../Split-collection-using-tabular-tests.yml | 2 +- .../Split-collection-using-tabular.ga | 96 +++++--------- 3 files changed, 83 insertions(+), 139 deletions(-) diff --git a/workflows/data-manipulation/split-collection/Split-collection-using-comma-separated-list.ga b/workflows/data-manipulation/split-collection/Split-collection-using-comma-separated-list.ga index 2257cb2a0..f426f794b 100644 --- a/workflows/data-manipulation/split-collection/Split-collection-using-comma-separated-list.ga +++ b/workflows/data-manipulation/split-collection/Split-collection-using-comma-separated-list.ga @@ -276,8 +276,8 @@ "name": "Split collection using tabular", "outputs": [], "position": { - "left": 1056.0418201104033, - "top": 153.98743551496034 + "left": 1071, + "top": 151.5 }, "subworkflow": { "a_galaxy_workflow": "true", @@ -447,7 +447,7 @@ } }, "inputs": [], - "label": "make filter condition", + "label": "make awk program", "name": "Compose text parameter value", "outputs": [ { @@ -456,8 +456,8 @@ } ], "position": { - "left": 869.1832700991363, - "top": 358.015694923965 + "left": 905.183349609375, + "top": 343.01666259765625 }, "post_job_actions": { "HideDatasetActionout1": { @@ -473,7 +473,7 @@ "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\": \"c2 == \\\"\"}}, {\"__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\": \"\\\"\"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"components\": [{\"__index__\": 0, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \"$2==\\\"\"}}, {\"__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 $1}\"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "0.1.1", "type": "tool", "uuid": "72928cef-e147-45c0-866e-d3bdc5d82937", @@ -482,95 +482,67 @@ }, "5": { "annotation": "", - "content_id": "Filter1", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.3+galaxy1", "errors": null, "id": 5, "input_connections": { - "cond": { + "code": { "id": 4, "output_name": "out1" }, - "input": { + "infile": { "id": 1, "output_name": "output" } }, - "inputs": [], - "label": "filter tabular to get only lines with first group", - "name": "Filter", - "outputs": [ + "inputs": [ { - "name": "out_file1", - "type": "input" + "description": "runtime parameter for tool Text reformatting", + "name": "infile" } ], - "position": { - "left": 1094.6521773218315, - "top": 312.3648800009677 - }, - "post_job_actions": { - "HideDatasetActionout_file1": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "out_file1" - } - }, - "tool_id": "Filter1", - "tool_state": "{\"cond\": {\"__class__\": \"ConnectedValue\"}, \"header_lines\": \"0\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.1.1", - "type": "tool", - "uuid": "f07fefb8-f736-4d02-8f7f-8467735c760c", - "when": null, - "workflow_outputs": [] - }, - "6": { - "annotation": "", - "content_id": "Cut1", - "errors": null, - "id": 6, - "input_connections": { - "input": { - "id": 5, - "output_name": "out_file1" - } - }, - "inputs": [], - "label": "keep only identifiers", - "name": "Cut", + "label": "get only identifiers with first group", + "name": "Text reformatting", "outputs": [ { - "name": "out_file1", - "type": "tabular" + "name": "outfile", + "type": "input" } ], "position": { - "left": 1345.2875324397519, - "top": 323.498696348884 + "left": 1224, + "top": 298.5 }, "post_job_actions": { - "HideDatasetActionout_file1": { + "HideDatasetActionoutfile": { "action_arguments": {}, "action_type": "HideDatasetAction", - "output_name": "out_file1" + "output_name": "outfile" } }, - "tool_id": "Cut1", - "tool_state": "{\"__input_ext\": \"tabular\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"columnList\": \"c1\", \"delimiter\": \"T\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.0.2", + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.3+galaxy1", + "tool_shed_repository": { + "changeset_revision": "86755160afbf", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"code\": {\"__class__\": \"ConnectedValue\"}, \"infile\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "9.3+galaxy1", "type": "tool", - "uuid": "364f21f7-fc99-4ad3-aa03-5379abeaa91d", + "uuid": "904fd1c2-cbc6-45c2-b4d7-d8e72b07d5cf", "when": null, "workflow_outputs": [] }, - "7": { + "6": { "annotation": "", "content_id": "__FILTER_FROM_FILE__", "errors": null, - "id": 7, + "id": 6, "input_connections": { "how|filter_source": { - "id": 6, - "output_name": "out_file1" + "id": 5, + "output_name": "outfile" }, "input": { "id": 0, @@ -622,41 +594,41 @@ "uuid": "8ff72610-8349-4862-b66e-1416e40ff95a", "when": null, "workflow_outputs": [ - { - "label": "collection_first_group", - "output_name": "output_filtered", - "uuid": "32af9f5d-c3f1-437a-8b08-6032212dd277" - }, { "label": "collection_other", "output_name": "output_discarded", "uuid": "d8721c45-506c-4378-95fc-a951cd854fc5" + }, + { + "label": "collection_first_group", + "output_name": "output_filtered", + "uuid": "32af9f5d-c3f1-437a-8b08-6032212dd277" } ] } }, "tags": [], - "uuid": "11bb0822-24d7-4e26-adc8-2f389dddae88" + "uuid": "f3a5e3f5-f2ce-4dde-aa36-6d39c8d37855" }, "tool_id": null, "type": "subworkflow", - "uuid": "6bb1b0b5-802d-4eed-b18e-2d3769f90c07", + "uuid": "eadd9f06-55d3-49db-b1e2-02550196540a", "when": null, "workflow_outputs": [ - { - "label": "collection_other", - "output_name": "collection_other", - "uuid": "508ac256-3c68-4024-83d4-d2966f7b2fa6" - }, { "label": "collection_first_group", "output_name": "collection_first_group", - "uuid": "99c02ccc-4c97-4d80-a112-513a260832fa" + "uuid": "cc55d416-fed3-4a69-9ce3-a33ea9ca62bf" + }, + { + "label": "collection_other", + "output_name": "collection_other", + "uuid": "f432b663-fb45-426c-b890-84062087db44" } ] } }, "tags": [], - "uuid": "cb0eeee3-59c5-48c7-b14a-c66826ec2f93", + "uuid": "71ae6dd8-b4e7-419d-83d5-9cd25ca79d57", "version": 2 } \ No newline at end of file diff --git a/workflows/data-manipulation/split-collection/Split-collection-using-tabular-tests.yml b/workflows/data-manipulation/split-collection/Split-collection-using-tabular-tests.yml index b6fa5b275..40a462487 100644 --- a/workflows/data-manipulation/split-collection/Split-collection-using-tabular-tests.yml +++ b/workflows/data-manipulation/split-collection/Split-collection-using-tabular-tests.yml @@ -21,7 +21,7 @@ path: test-data/file.txt identifier mapping: class: File - path: group_asignment.txt + path: test-data/group_asignment.txt datatype: tabular outputs: collection_other: diff --git a/workflows/data-manipulation/split-collection/Split-collection-using-tabular.ga b/workflows/data-manipulation/split-collection/Split-collection-using-tabular.ga index 54f00eef5..20af85094 100644 --- a/workflows/data-manipulation/split-collection/Split-collection-using-tabular.ga +++ b/workflows/data-manipulation/split-collection/Split-collection-using-tabular.ga @@ -167,7 +167,7 @@ } }, "inputs": [], - "label": "make filter condition", + "label": "make awk program", "name": "Compose text parameter value", "outputs": [ { @@ -176,8 +176,8 @@ } ], "position": { - "left": 869.1832700991363, - "top": 358.015694923965 + "left": 905.183349609375, + "top": 343.01666259765625 }, "post_job_actions": { "HideDatasetActionout1": { @@ -193,7 +193,7 @@ "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\": \"c2 == \\\"\"}}, {\"__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\": \"\\\"\"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"components\": [{\"__index__\": 0, \"param_type\": {\"select_param_type\": \"text\", \"__current_case__\": 0, \"component_value\": \"$2==\\\"\"}}, {\"__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 $1}\"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "0.1.1", "type": "tool", "uuid": "72928cef-e147-45c0-866e-d3bdc5d82937", @@ -202,95 +202,67 @@ }, "5": { "annotation": "", - "content_id": "Filter1", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.3+galaxy1", "errors": null, "id": 5, "input_connections": { - "cond": { + "code": { "id": 4, "output_name": "out1" }, - "input": { + "infile": { "id": 1, "output_name": "output" } }, - "inputs": [], - "label": "filter tabular to get only lines with first group", - "name": "Filter", - "outputs": [ + "inputs": [ { - "name": "out_file1", - "type": "input" + "description": "runtime parameter for tool Text reformatting", + "name": "infile" } ], - "position": { - "left": 1094.6521773218315, - "top": 312.3648800009677 - }, - "post_job_actions": { - "HideDatasetActionout_file1": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "out_file1" - } - }, - "tool_id": "Filter1", - "tool_state": "{\"cond\": {\"__class__\": \"ConnectedValue\"}, \"header_lines\": \"0\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.1.1", - "type": "tool", - "uuid": "f07fefb8-f736-4d02-8f7f-8467735c760c", - "when": null, - "workflow_outputs": [] - }, - "6": { - "annotation": "", - "content_id": "Cut1", - "errors": null, - "id": 6, - "input_connections": { - "input": { - "id": 5, - "output_name": "out_file1" - } - }, - "inputs": [], - "label": "keep only identifiers", - "name": "Cut", + "label": "get only identifiers with first group", + "name": "Text reformatting", "outputs": [ { - "name": "out_file1", - "type": "tabular" + "name": "outfile", + "type": "input" } ], "position": { - "left": 1345.2875324397519, - "top": 323.498696348884 + "left": 1224, + "top": 298.5 }, "post_job_actions": { - "HideDatasetActionout_file1": { + "HideDatasetActionoutfile": { "action_arguments": {}, "action_type": "HideDatasetAction", - "output_name": "out_file1" + "output_name": "outfile" } }, - "tool_id": "Cut1", - "tool_state": "{\"__input_ext\": \"tabular\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"columnList\": \"c1\", \"delimiter\": \"T\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.0.2", + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.3+galaxy1", + "tool_shed_repository": { + "changeset_revision": "86755160afbf", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"code\": {\"__class__\": \"ConnectedValue\"}, \"infile\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "9.3+galaxy1", "type": "tool", - "uuid": "364f21f7-fc99-4ad3-aa03-5379abeaa91d", + "uuid": "904fd1c2-cbc6-45c2-b4d7-d8e72b07d5cf", "when": null, "workflow_outputs": [] }, - "7": { + "6": { "annotation": "", "content_id": "__FILTER_FROM_FILE__", "errors": null, - "id": 7, + "id": 6, "input_connections": { "how|filter_source": { - "id": 6, - "output_name": "out_file1" + "id": 5, + "output_name": "outfile" }, "input": { "id": 0, @@ -356,6 +328,6 @@ } }, "tags": [], - "uuid": "11bb0822-24d7-4e26-adc8-2f389dddae88", - "version": 3 + "uuid": "f3a5e3f5-f2ce-4dde-aa36-6d39c8d37855", + "version": 4 } \ No newline at end of file From ea558b3489a46a57fe85b8498103b9c59a2e8834 Mon Sep 17 00:00:00 2001 From: Lucille Delisle Date: Mon, 18 Nov 2024 09:12:57 +0100 Subject: [PATCH 9/9] Apply suggestions from @mvdbeek Co-authored-by: Marius van den Beek --- .../Split-collection-by-pattern-in-identifiers.ga | 2 +- .../Split-collection-using-comma-separated-list-tests.yml | 1 - .../split-collection/Split-collection-using-tabular-tests.yml | 2 -- 3 files changed, 1 insertion(+), 4 deletions(-) diff --git a/workflows/data-manipulation/split-collection/Split-collection-by-pattern-in-identifiers.ga b/workflows/data-manipulation/split-collection/Split-collection-by-pattern-in-identifiers.ga index 17efc9cf0..3cecd8922 100644 --- a/workflows/data-manipulation/split-collection/Split-collection-by-pattern-in-identifiers.ga +++ b/workflows/data-manipulation/split-collection/Split-collection-by-pattern-in-identifiers.ga @@ -12,7 +12,7 @@ "format-version": "0.1", "license": "MIT", "release": "0.1", - "name": "Split collection by pattern in identifiers", + "name": "Split collection by pattern in element identifiers", "report": { "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" }, diff --git a/workflows/data-manipulation/split-collection/Split-collection-using-comma-separated-list-tests.yml b/workflows/data-manipulation/split-collection/Split-collection-using-comma-separated-list-tests.yml index 5ed826226..74632b271 100644 --- a/workflows/data-manipulation/split-collection/Split-collection-using-comma-separated-list-tests.yml +++ b/workflows/data-manipulation/split-collection/Split-collection-using-comma-separated-list-tests.yml @@ -49,4 +49,3 @@ asserts: has_text: text: "whatever" - diff --git a/workflows/data-manipulation/split-collection/Split-collection-using-tabular-tests.yml b/workflows/data-manipulation/split-collection/Split-collection-using-tabular-tests.yml index 40a462487..a56f5a1e0 100644 --- a/workflows/data-manipulation/split-collection/Split-collection-using-tabular-tests.yml +++ b/workflows/data-manipulation/split-collection/Split-collection-using-tabular-tests.yml @@ -52,5 +52,3 @@ asserts: has_text: text: "whatever" - -