| Previous changeset 10:480d9e9d156b (2023-10-27) Next changeset 12:29648e5e83a8 (2024-03-27) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ena_upload commit c7f54e6e3b1ffad5631ff7c150449cb79bd3686d |
|
modified:
ena_upload.xml samples_macros.xml |
|
added:
test-data/ENA_TEST1.R1.fastq.gz test-data/ENA_TEST2.R1.fastq.gz test-data/ENA_TEST2.R2.fastq.gz test-data/simple_test_case_v2.json |
| b |
| diff -r 480d9e9d156b -r f803a68fc9e5 ena_upload.xml --- a/ena_upload.xml Fri Oct 27 19:44:40 2023 +0000 +++ b/ena_upload.xml Sat Mar 23 22:06:45 2024 +0000 |
| [ |
| b'@@ -1,6 +1,7 @@\n-<tool id="ena_upload" name="ENA Upload tool" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05" license="MIT">\n+<tool id="ena_upload" name="ENA Upload tool" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.05" license="MIT">\n+ <description>Submission of (meta)data to the European Nucleotide Archive (ENA)</description>\n <macros>\n- <token name="@TOOL_VERSION@">0.6.3</token>\n+ <token name="@TOOL_VERSION@">0.7.1</token>\n <token name="@VERSION_SUFFIX@">0</token>\n <import>samples_macros.xml</import>\n </macros>\n@@ -48,7 +49,10 @@\n #if $action_options.input_format_conditional.input_format == "excel_tables":\n ln -s \'$action_options.input_format_conditional.xlsx_file\' ./xlsx_input.xlsx &&\n #end if\n-#if $action_options.test_submit_parameters.dry_run == "False" and $action_options.test_submit == "False":\n+#if $action_options.input_format_conditional.input_format == "isa_json":\n+ ln -s \'$action_options.input_format_conditional.isa_json_file\' ./isa_json_input.json &&\n+#end if\n+#if $action_options.test_submit_parameters.dry_run == "False":\n webin_id=`grep \'username\' $credentials`;\n if [ "\\$webin_id" = "" ]; then\n ## No credentials in user defined preferences \n@@ -171,95 +175,52 @@\n #end if\n #end if\n \n-#if $action_options.action == "add":\n ena-upload-cli\n --tool \'ena-upload-cli v@TOOL_VERSION@ @ Galaxy\'\n --action \'$action_options.action\'\n- --center \'$action_options.center\'\n+ --center \'$action_options.test_submit_parameters.center\'\n --secret \\${credentials_path}\n --data\n- #for $dataset in $files_to_upload:\n- \'$dataset\'\n- #end for\n+#for $dataset in $files_to_upload:\n+ \'$dataset\'\n+#end for\n #if $action_options.test_submit_parameters.dry_run == "True":\n --draft\n #end if\n-#if $action_options.input_format_conditional.input_format != "excel_tables":\n+#if $action_options.input_format_conditional.input_format == "excel_tables":\n+ --xlsx ./xlsx_input.xlsx \n+#elif $action_options.input_format_conditional.input_format == "user_generated_tables" or $action_options.input_format_conditional.input_format == "build_tables":\n --experiment \'$experiments_table_path\'\n --study \'$studies_table_path\'\n --run \'$runs_table_path\'\n --sample \'$samples_table_path\'\n-#else\n- --xlsx ./xlsx_input.xlsx \n+#elif $action_options.input_format_conditional.input_format == "isa_json":\n+ --isa_json ./isa_json_input.json\n+ --isa_assay_stream \'$isa_assay_stream\'\n #end if\n---action add\n-#if $action_options.input_format_conditional.input_format == "user_generated_tables":\n- --checklist $action_options.input_format_conditional.checklist_id\n+#if $action_options.input_format_conditional.input_format == "build_tables":\n+ #if $action_options.input_format_conditional.conditional_viral_metadata.viral_sample == "True":\n+ --checklist ERC000033\n+ #end if\n+#elif $action_options.input_format_conditional.input_format == "isa_json":\n+ --checklist ERC000011\n #else:\n- #if $action_options.input_format_conditional.input_format == "build_tables":\n- #if $action_options.input_format_conditional.conditional_viral_metadata.viral_sample == "True":\n- --checklist ERC000033\n- #end if\n- #else:\n- --checklist $action_options.input_format_conditional.checklist_id\n- #end if\n-#end if\n-#if $action_options.idempotent == "True":\n- --auto_action\n+ --checklist $action_options.input_format_conditional.checklist_id\n #end if\n #if $action_options.test_submit_parameters.submit_dev == "True":\n -d\n #end if\n- >> \'$output\';\n-#end if\n-\n+>> \'$output\';\n \n \n-#if $action_options.action == "modify":\n- ena-upload-cli\n- --tool \'ena-upload-cli v@TOOL_VERSION@ @ Galaxy\'\n- --action \'$action_options.action\'\n- --center \'$action_options.center\'\n- --secret \\${credentials_path}\n- --data\n- #for $dataset in $files_to_upload:\n- \'$dataset\'\n- #end for\n-#if $action_options.'..b' </assert_command>\n </test>\n+ <!--Test 9: isa JSON input of NON-VIRAL samples-->\n+ <test expect_num_outputs="5">\n+ <conditional name="action_options">\n+ <param name="action" value="add"/>\n+ <section name="test_submit_parameters">\n+ <param name="center" value="Some research center"/>\n+ <param name="submit_dev" value="True" />\n+ <param name="dry_run" value="True" />\n+ </section>\n+ <conditional name="input_format_conditional">\n+ <param name="input_format" value="isa_json"/>\n+ <param name="isa_json_file" value="simple_test_case_v2.json"/>\n+ <param name="isa_assay_stream" value="Ena stream 1"/>\n+ <conditional name="run_input_format_conditional">\n+ <param name="add_extension" value="False"/>\n+ <param name="run_input_format" value="multiple_selection_list"/>\n+ <param name="data" value="ENA_TEST1.R1.fastq.gz,ENA_TEST2.R1.fastq.gz,ENA_TEST2.R2.fastq.gz"/>\n+ </conditional>\n+ </conditional>\n+ </conditional>\n+ <output name="experiments_table_out">\n+ <assert_contents>\n+ <has_n_lines n="4"/>\n+ <has_n_columns n="17"/>\n+ <has_line_matching expression="alias\\tstudy_alias\\tsample_alias\\tlibrary_name\\ttitle\\taccession\\tsubmission date\\tstatus\\tdesign_description\\tlibrary_source\\tlibrary_strategy\\tlibrary_selection\\tlibrary_layout\\tinsert_size\\tplatform\\tinstrument_model\\tsubmission_date"/>\n+ </assert_contents>\n+ </output>\n+ <output name="studies_table_out">\n+ <assert_contents>\n+ <has_n_lines n="2"/>\n+ <has_n_columns n="9"/>\n+ <has_line_matching expression="alias\\ttitle\\tstudy_type\\tstudy_abstract\\tnew_study_type\\tpubmed_id\\taccession\\tsubmission_date\\tstatus"/>\n+ </assert_contents>\n+ </output>\n+ <output name="samples_table_out">\n+ <assert_contents>\n+ <has_n_lines n="3"/>\n+ <has_n_columns n="11"/>\n+ </assert_contents>\n+ </output>\n+ <output name="runs_table_out">\n+ <assert_contents>\n+ <has_n_lines n="4"/>\n+ <has_n_columns n="10"/>\n+ <has_line_matching expression="alias\\texperiment_alias\\tfile_name\\tfile_type\\tfile checksum\\taccession\\tsubmission date\\tstatus\\tsubmission_date\\tfile_checksum"/>\n+ </assert_contents>\n+ </output>\n+ </test>\n </tests>\n- <help><![CDATA[\n- This is a wrapper for the ENA upload tool in https://github.com/usegalaxy-eu/ena-upload-cli\n- The input metadata can be submitted following the tabular format of the templates or their excel spreadsheet equivalent in https://github.com/ELIXIR-Belgium/ENA-metadata-templates. This template repo provides ready to use sheets for every ENA sample checklist and is automatically updated.\n- ]]></help>\n+ <help><![CDATA[This is a wrapper for the ENA upload tool in https://github.com/usegalaxy-eu/ena-upload-cli. The input metadata can be submitted following the tabular format of the templates or their excel spreadsheet equivalent in https://github.com/ELIXIR-Belgium/ENA-metadata-templates. This template repo provides ready to use sheets for every ENA sample checklist and is automatically updated.\n+ \n+ .. class:: warningmark\n+ \n+ The ENA upload tool won\'t work unless you have provided an ENA Webin ID in User > Preferences > Manage Information > ENA Webin account details.]]></help>\n <citations>\n <citation type="doi">doi:10.1093/bioinformatics/btab421</citation>\n </citations>\n' |
| b |
| diff -r 480d9e9d156b -r f803a68fc9e5 samples_macros.xml --- a/samples_macros.xml Fri Oct 27 19:44:40 2023 +0000 +++ b/samples_macros.xml Sat Mar 23 22:06:45 2024 +0000 |
| b |
| b'@@ -1,6 +1,6 @@\n <macros>\n <xml name="checklist_input_macro">\n- <param type="select" name="checklist_id" label="Select the metadata checklist" help="You can find metadata templates for each checklist at: https://github.com/ELIXIR-Belgium/ENA-metadata-templates">\n+ <param type="select" name="checklist_id" label="Select the ENA sample checklist" help="You can find metadata templates for each checklist at: https://github.com/ELIXIR-Belgium/ENA-metadata-templates">\n <option value="ERC000011">ENA default sample checklist (ERC000011)</option>\n <option value="ERC000012">GSC MIxS air (ERC000012)</option>\n <option value="ERC000013">GSC MIxS host associated (ERC000013)</option>\n@@ -44,37 +44,39 @@\n </param>\n </xml>\n <xml name="test_submit_section">\n- <section name="test_submit_parameters" expanded="True" title="Testing options">\n- <param name="submit_dev" type="boolean" truevalue="True" falsevalue="False" label="Submit to test ENA server?" help="By selecting yes the reads will be submitted to the ENA test server. Uploads to test platform will not be public and will be removed in 24hrs. Performing a preliminary test upload is advised to check for errors with metadata structure. You can find the uploads to the test platform at https://wwwdev.ebi.ac.uk/ena/" />\n- <param name="dry_run" type="boolean" truevalue="True" falsevalue="False" label="Print the tables but do not submit the datasets" help="If yes is selected then NO submission will be performed."/>\n+ <section name="test_submit_parameters" expanded="True" title="Submissions options">\n+ <param name="center" type="text" optional="False" label="Affiliation center"/>\n+ <param name="submit_dev" type="boolean" truevalue="True" falsevalue="False" label="Submit to ENA test server" help="Uploads to the test server of ENA will not be made public and will be removed automatically in 24 hours. Performing a preliminary test upload is advised to check for errors with metadata structure. You can find these uploads at https://wwwdev.ebi.ac.uk/ena/." />\n+ <param name="dry_run" type="boolean" truevalue="True" falsevalue="False" label="Create test outputs without submitting (meta)data to ENA" help="If yes is selected then NO submission will be performed."/>\n </section>\n </xml>\n <xml name="run_inputs_macro">\n <conditional name="run_input_format_conditional">\n- <param name="run_input_format" type="select" label="Select runs input format">\n- <option value="multiple_selection_list" selected="True">Select individual datasets or datasets collection</option>\n- <option value="paired_list" selected="False">Input from a paired collection</option>\n+ <param name="run_input_format" type="select" label="Select input data">\n+ <option value="multiple_selection_list" selected="True">Dataset or dataset collection</option>\n+ <option value="paired_list" selected="False">Paired dataset collection</option>\n </param>\n <when value="multiple_selection_list">\n- <param name="add_extension" type="boolean" checked="False" label="Add .fastq.(gz,.bz2) extension to the Galaxy dataset names to match the ones described in the input tables?"/>\n- <param name="data" type="data" format="fastq,fastqsanger,fastqsanger.gz,fastqsanger.bz2,fastq.gz,fastq.bz2" multiple="True" label="Select individual datasets or a dataset collection" help="Names should match the compressed run\'s files names defined in the metadata"/>\n+ <param name="add_extension" type="boolean" checked="False" label="Add .fastq (.gz, .bz2) extension to the Galaxy dataset names to match the ones described in the input tables?"/>\n+ <param name="data" type="data" format="fastq,fastqsanger,fastqsanger.gz,fastqsanger.bz2,fastq.gz,fastq.bz2" multiple="True" labe'..b'hould match the compressed run\'s files names defined in the metadata" />\n </when>\n </conditional>\n </xml>\n <xml name="table_inputs_macro">\n <conditional name="input_format_conditional">\n- <param name="input_format" type="select" label="Would you like to submit pregenerated table files or interactively define the input structures?">\n- <option value="excel_tables" selected="True">User generated metadata tables based on Excel template</option>\n- <option value="build_tables" selected="False">Interactive generation of the study structure (only recommended for small studies)</option>\n- <option value="user_generated_tables" selected="False">User generated tabular files (studies - samples - experiments - runs) </option>\n+ <param name="input_format" type="select" label="Select the metadata input method">\n+ <option value="excel_tables" selected="True">Excel file</option>\n+ <option value="user_generated_tables" selected="False">Tabular files (studies - samples - experiments - runs)</option>\n+ <option value="isa_json" selected="False">ISA json file</option>\n+ <option value="build_tables" selected="False">Interactively (only recommended for small studies)</option>\n </param>\n <when value="excel_tables">\n <!--<param name="viral_submission" type="boolean" label="Does your submission data belong to a viral sample?" help="If you select yes then your data will be submitted using the ENA virus pathogen reporting standard checklist (see: https://ena-browser-docs.readthedocs.io/en/latest/help_and_guides/sars-cov-2-submissions.html)" />-->\n <expand macro="checklist_input_macro"/>\n- <param name="xlsx_file" type="data" format="xlsx" label="Select Excel (xlsx) file based on template" />\n+ <param name="xlsx_file" type="data" format="xlsx" label="Select Excel (.xlsx) file based on template" />\n <expand macro="run_inputs_macro" />\n </when>\n <when value="user_generated_tables">\n@@ -87,7 +89,7 @@\n <param name="runs_users_table" type="data" format="tabular" multiple="False" label="Runs table" help="Runs metadata file"/>\n </when>\n <when value="build_tables">\n- <param name="add_extension" type="boolean" checked="False" label="Add .fastq.(gz.bz2) extension to the Galaxy dataset names to match the ones described in the input tables?"/>\n+ <param name="add_extension" type="boolean" checked="False" label="Add .fastq (.gz, .bz2) extension to the Galaxy dataset names to match the ones described in the input tables?"/>\n <conditional name="conditional_viral_metadata">\n <param name="viral_sample" type="select" label="Select your sample type" help="Non-viral interactive submissions lack specific sample checklist attributes and are suboptimal. It\'s highly recommended to use Excel or TSV templates as input for a more comprehensive submission.">\n <option value="True" selected="True">Viral</option>\n@@ -101,8 +103,13 @@\n </when>\n </conditional>\n </when>\n+ <when value="isa_json">\n+ <param name="isa_json_file" type="data" format="json" label="Select ISA json file" />\n+ <param name="isa_assay_stream" type="text" optional="False" help="List the assay_stream values from the comment field in the assays list of the ISA-json you want to submit." label="Specify the ISA json assay stream(s)" />\n+ <expand macro="run_inputs_macro" />\n+ </when>\n </conditional>\n- <param name="center" type="text" optional="False" label="Affiliation center"/>\n+ \n </xml>\n <xml name="viral_samples">\n <repeat name="rep_study" title="Study" min="1">\n' |
| b |
| diff -r 480d9e9d156b -r f803a68fc9e5 test-data/ENA_TEST1.R1.fastq.gz |
| b |
| Binary file test-data/ENA_TEST1.R1.fastq.gz has changed |
| b |
| diff -r 480d9e9d156b -r f803a68fc9e5 test-data/ENA_TEST2.R1.fastq.gz |
| b |
| Binary file test-data/ENA_TEST2.R1.fastq.gz has changed |
| b |
| diff -r 480d9e9d156b -r f803a68fc9e5 test-data/ENA_TEST2.R2.fastq.gz |
| b |
| Binary file test-data/ENA_TEST2.R2.fastq.gz has changed |
| b |
| diff -r 480d9e9d156b -r f803a68fc9e5 test-data/simple_test_case_v2.json --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/simple_test_case_v2.json Sat Mar 23 22:06:45 2024 +0000 |
| [ |
| b'@@ -0,0 +1,1631 @@\n+{\n+ "identifier": "",\n+ "title": "Test Case ENA upload tool",\n+ "description": "This investigation matches the test case of the ENA upload tool",\n+ "submissionDate": "",\n+ "publicReleaseDate": "",\n+ "ontologySourceReferences": [],\n+ "filename": "Test Case ENA upload tool.txt",\n+ "comments": [\n+ {\n+ "name": "ISAjson export time",\n+ "value": "2023-11-08T16:27:49Z"\n+ },\n+ {\n+ "name": "SEEK Project name",\n+ "value": "Test Project ENA upload Tool"\n+ },\n+ {\n+ "name": "SEEK Project ID",\n+ "value": "http://localhost:3000/single_pages/16"\n+ },\n+ {\n+ "name": "SEEK Investigation ID",\n+ "value": "27"\n+ }\n+ ],\n+ "publications": [],\n+ "people": [\n+ {\n+ "@id": "#people/4",\n+ "lastName": "De Pelseneer",\n+ "firstName": "Kevin",\n+ "midInitials": "",\n+ "email": "kevin.depelseneer@psb.ugent.be",\n+ "phone": "",\n+ "fax": "",\n+ "address": "",\n+ "affiliation": "",\n+ "roles": [\n+ {\n+ "termAccession": "",\n+ "termSource": "",\n+ "annotationValue": ""\n+ }\n+ ],\n+ "comments": [\n+ {\n+ "@id": "",\n+ "value": "",\n+ "name": ""\n+ }\n+ ]\n+ }\n+ ],\n+ "studies": [\n+ {\n+ "identifier": "",\n+ "title": "Study - Test Case ENA",\n+ "description": "",\n+ "submissionDate": "",\n+ "publicReleaseDate": "",\n+ "filename": "Study - Test Case ENA.txt",\n+ "comments": [\n+ {\n+ "@id": "#study_comment/25_13_49",\n+ "name": "ena_sample_alias_prefix",\n+ "value": "sample_alias_"\n+ },\n+ {\n+ "@id": "#study_comment/25_ae7461a0-6081-013c-9ed3-7a163e608de1",\n+ "name": "SEEK Study ID",\n+ "value": "25"\n+ },\n+ {\n+ "@id": "#study_comment/25_ae7467e0-6081-013c-9ed4-7a163e608de1",\n+ "name": "SEEK creation date",\n+ "value": "2023-10-20T11:12:23Z"\n+ }\n+ ],\n+ "publications": [],\n+ "people": [\n+ {\n+ "@id": "#people/4",\n+ "lastName": "De Pelseneer",\n+ "firstName": "Kevin",\n+ "midInitials": "",\n+ "email": "kevin.depelseneer@psb.ugent.be",\n+ "phone": "",\n+ "fax": "",\n+ "address": "",\n+ "affiliation": "",\n+ "roles": [\n+ {\n+ "termAccession": "",\n+ "termSource": "",\n+ "annotationValue": ""\n+ }\n+ ],\n+ "comments": [\n+ {\n+ "@id": "",\n+ "value": "",\n+ "name": ""\n+ }\n+ ]\n+ }\n+ ],\n+ "studyDesignDescriptors": [],\n+ "characteristicCategories": [\n+ {\n+ "@id": "#characteristic_category/geographic_location_(country_and/or_sea)_657",\n+ "characteristicType": {\n+ "annotationValue": "geographic location (country and/or sea)",\n+ "termAccession": "",\n+ "termSource": ""\n+ }\n+ },\n+ {\n+ "@id": "#characteristic_category/taxon_id_658",\n+ "characteristicType": {\n+ "annotationValue": "taxon_id",\n+ "termAccession": "",\n+ "termSource": ""\n+ }\n+ },\n+ {\n+ "@id": "#characteristic_category/title_662",\n+ "characteristicType": {\n+ "annotationValue": "title",\n+ "termAccession": "",\n+ "termSource": ""\n+ }\n+ },\n+ {\n+ "@id": "#characteristic_category/sample_description_663",\n+ "characteristicType": {\n+ "annotationValue": "sample_description",\n+ "termAccession": "",\n+ "termSource": ""\n+ }\n+ },\n+ {\n+ "@id": "#characteristic_category/collection_date_664",\n+ "characteristicType": {\n+ "annotationValue": "collection date",\n+ "termAccessi'..b'ial/227"\n+ }\n+ ],\n+ "outputs": [\n+ {\n+ "@id": "#data_file/233"\n+ },\n+ {\n+ "@id": "#data_file/234"\n+ }\n+ ],\n+ "previousProcess": {\n+ "@id": "#process/library_construction/233"\n+ },\n+ "nextProcess": {}\n+ },\n+ {\n+ "@id": "#process/nucleic_acid_sequencing/235",\n+ "name": "",\n+ "executesProtocol": {\n+ "@id": "#protocol/_49"\n+ },\n+ "parameterValues": [],\n+ "performer": "",\n+ "date": "",\n+ "inputs": [\n+ {\n+ "@id": "#other_material/229"\n+ }\n+ ],\n+ "outputs": [\n+ {\n+ "@id": "#data_file/235"\n+ }\n+ ],\n+ "previousProcess": {\n+ "@id": "#process/library_construction/235"\n+ },\n+ "nextProcess": {}\n+ }\n+ ],\n+ "dataFiles": [\n+ {\n+ "@id": "#data_file/233",\n+ "name": "RD file 1a",\n+ "type": "Raw Data File",\n+ "comments": [\n+ {\n+ "name": "file_name",\n+ "value": "ENA_TEST2.R1.fastq.gz"\n+ },\n+ {\n+ "name": "file_type",\n+ "value": "fastq"\n+ },\n+ {\n+ "name": "file checksum",\n+ "value": ""\n+ },\n+ {\n+ "name": "accession",\n+ "value": ""\n+ },\n+ {\n+ "name": "submission date",\n+ "value": ""\n+ },\n+ {\n+ "name": "status",\n+ "value": "add"\n+ }\n+ ]\n+ },\n+ {\n+ "@id": "#data_file/234",\n+ "name": "RD file 1b",\n+ "type": "Raw Data File",\n+ "comments": [\n+ {\n+ "name": "file_name",\n+ "value": "ENA_TEST2.R2.fastq.gz"\n+ },\n+ {\n+ "name": "file_type",\n+ "value": "fastq"\n+ },\n+ {\n+ "name": "file checksum",\n+ "value": ""\n+ },\n+ {\n+ "name": "accession",\n+ "value": ""\n+ },\n+ {\n+ "name": "submission date",\n+ "value": ""\n+ },\n+ {\n+ "name": "status",\n+ "value": "add"\n+ }\n+ ]\n+ },\n+ {\n+ "@id": "#data_file/235",\n+ "name": "RD file 3",\n+ "type": "Raw Data File",\n+ "comments": [\n+ {\n+ "name": "file_name",\n+ "value": "ENA_TEST1.R1.fastq.gz"\n+ },\n+ {\n+ "name": "file_type",\n+ "value": "fastq"\n+ },\n+ {\n+ "name": "file checksum",\n+ "value": ""\n+ },\n+ {\n+ "name": "accession",\n+ "value": ""\n+ },\n+ {\n+ "name": "submission date",\n+ "value": ""\n+ },\n+ {\n+ "name": "status",\n+ "value": "add"\n+ }\n+ ]\n+ }\n+ ],\n+ "unitCategories": []\n+ }\n+ ],\n+ "factors": [],\n+ "unitCategories": []\n+ }\n+ ]\n+}\n\\ No newline at end of file\n' |