Annotate existing WFs with edam topics and operations

workflows/data-fetching/parallel-accession-download/parallel-accession-download.ga

@@ -18,6 +18,8 @@
     "license": "MIT",
     "release": "0.1.14",
     "name": "Parallel Accession Download",
+    "edam_topics": ["topic_3168"],  # Sequencing
+    "edam_operations": ["operation_2409", "operation_2422"],  # Data handling, Data retrieval
     "steps": {
         "0": {
             "annotation": "Text file containing run accessions (starting with SRR, ERR or DRR), one per line.",
@@ -271,4 +273,4 @@
     "tags": [],
     "uuid": "15c3229d-8786-457f-a020-7aa64c0cf6e8",
     "version": 10
-}
+}

workflows/data-fetching/sra-manifest-to-concatenated-fastqs/sra-manifest-to-concatenated-fastqs.ga

@@ -22,6 +22,8 @@
     "release": "0.7",
     "license": "MIT",
     "name": "sra_manifest_to_concatenated_fastqs_parallel",
+    "edam_topics": ["topic_3168"],  # Sequencing
+    "edam_operations": ["operation_2409", "operation_2422"],  # Data handling, Data retrieval
     "steps": {
         "0": {
             "annotation": "Input tabular from SRA Run Selector or home made (First row needs to be a header)",
@@ -739,4 +741,4 @@
     "tags": [],
     "uuid": "363898af-e598-4f0e-abd9-e6ded395ce66",
     "version": 3
-}
+}

workflows/genome-assembly/assembly-with-flye/Genome-assembly-with-Flye.ga

@@ -12,6 +12,8 @@
     "license": "MIT",
     "release": "0.2",
     "name": "Genome assembly with Flye",
+    "edam_topics": ["topic_0196"],  # Sequence assembly
+    "edam_operations": ["operation_0524", "operation_3180"],  # De-novo assembly, Sequence assembly validation
     "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\n"
     },
@@ -262,4 +264,4 @@
     "tags": [],
     "uuid": "83ef6fdc-b8a9-41af-a824-0225f0199e63",
     "version": 21
-}
+}

workflows/genome-assembly/bacterial-genome-assembly/bacterial_genome_assembly.ga

@@ -29,6 +29,8 @@
     "release": "1.1.5",
     "license": "GPL-3.0-or-later",
     "name": "Bacterial Genome Assembly using Shovill",
+    "edam_topics": ["topic_0196", "topic_3301"],  # Sequence assembly, Microbiology
+    "edam_operations": ["operation_0524", "operation_3180"],  # De-novo assembly, Sequence assembly validation
     "steps": {
         "0": {
             "annotation": "Should be the adapter trimmed forward strand of the paired end reads.",
@@ -715,4 +717,4 @@
     ],
     "uuid": "bfe7f341-07ef-4bfe-9b50-2bc7628d6c55",
     "version": 1
-}
+}

workflows/genome-assembly/polish-with-long-reads/Assembly-polishing-with-long-reads.ga

@@ -12,6 +12,8 @@
     "release": "0.1",
     "license": "MIT",
     "name": "Assembly polishing with long reads",
+    "edam_topics": ["topic_0196"],  # Sequence assembly
+    "edam_operations": ["operation_2425"],  # Optimisation and refinement
     "steps": {
         "0": {
             "annotation": "",

workflows/genome-assembly/quality-and-contamination-control/quality_and_contamination_control.ga

@@ -29,6 +29,8 @@
     "license": "GPL-3.0-or-later",
     "release": "1.1.6",
     "name": "Quality and Contamination Control For Genome Assembly",
+    "edam_topics": ["topic_0637", "topic_3168", "topic_3174"],  # Taxonomy, Sequencing, Metagenomics
+    "edam_operations": ["operation_3218", "operation_3460"],  # Sequencing quality control, Taxonomic classification
     "steps": {
         "0": {
             "annotation": "Should be the forward strand of the paired end reads.",
@@ -816,4 +818,4 @@
     ],
     "uuid": "eb1c667d-639d-4403-a2b4-1cb6683e0fa5",
     "version": 1
-}
+}

workflows/imaging/fluorescence-nuclei-segmentation-and-counting/segmentation-and-counting.ga

@@ -13,6 +13,8 @@
     "license": "MIT",
     "release": "0.2",
     "name": "Segmentation and counting of cell nuclei in fluorescence microscopy images",
+    "edam_topics": ["topic_3383"],  # Bioimaging
+    "edam_operations": ["operation_3443"],  # Image analysis
     "steps": {
         "0": {
             "annotation": "The fluorescence microscopy images to be segmented. Must be the single image channel, which contains the cell nuclei.",

workflows/metabomics/gcms-metams/Mass-spectrometry__GCMS-with-metaMS.ga

@@ -13,6 +13,8 @@
     "release": "0.1",
     "license": "MIT",
     "name": "Mass spectrometry: GCMS with metaMS",
+    "edam_topics": ["topic_3172"],  # Metabolomics
+    "edam_operations": ["operation_3628", "operation_3803"],  # Chromatographic alignment, Natural product identification
     "steps": {
         "0": {
             "annotation": "",
@@ -466,4 +468,4 @@
     ],
     "uuid": "a2b0d4f7-164c-40d3-ac34-f248db18bbef",
     "version": 2
-}
+}

workflows/metabomics/lcms-preprocessing/Mass_spectrometry__LC-MS_preprocessing_with_XCMS.ga

@@ -13,6 +13,8 @@
     "license": "MIT",
     "release": "1.0",
     "name": "Mass spectrometry: LC-MS preprocessing with XCMS",
+    "edam_topics": ["topic_3172"],  # Metabolomics
+    "edam_operations": ["operation_3628", "operation_3803"],  # Chromatographic alignment, Natural product identification
     "steps": {
         "0": {
             "annotation": "",

workflows/microbiome/allele-based-pathogen-identification/Allele-based-Pathogen-Identification.ga

@@ -102,6 +102,8 @@
     "license": "MIT",
     "release": "0.1.2",
     "name": "Allele-based Pathogen Identification",
+    "edam_topics": ["topic_3168", "topic_3301"],  # Sequencing, Microbiology
+    "edam_operations": ["operation_3198", "operation_3223"],  # Read mapping, Variant calling
     "report": {
         "markdown": "# Allele-based Pathogen Identification Workflow Report\nBelow are the results for the Allele based Pathogenic Identification Workflow\n\nThis workflow was run on:\n\n```galaxy\ngenerate_time()\n```\n\nWith Galaxy version:\n\n```galaxy\ngenerate_galaxy_version()\n```\n\n## Workflow Inputs\nThe Perprocessing workflow main output (Collection of all samples reads after quality retaining and hosts filtering), and a FASTA file of the reference genome of the main Pathogen identified in the Gene based Pathogen Identification workflow, or per-known to the user.\n\n## Workflow Output: \n\n### All variants found per sample against the reference genome\n\n```galaxy\nhistory_dataset_display(output=\"extracted_fields_from_the_vcf_output\")\n```\n\n### Number of variants per sample\n\n```galaxy\nhistory_dataset_display(output=\"number_of_variants_per_sample\")\n```\n\n### Mapping mean depth of coverage per sample\n\n```galaxy\nhistory_dataset_display(output=\"mapping_mean_depth_per_sample\")\n```\n\n### Mapping breadth of coverage percentage per sample\n\n```galaxy\nhistory_dataset_display(output=\"mapping_coverage_percentage_per_sample\")\n```\n\n"
     },
@@ -1324,4 +1326,4 @@
     ],
     "uuid": "435875a1-72c4-4fda-8943-3a78f25c6574",
     "version": 72
-}
+}

workflows/microbiome/gene-based-pathogen-identification/Gene-based-Pathogen-Identification.ga

@@ -113,6 +113,8 @@
     "license": "MIT",
     "release": "0.1",
     "name": "Gene-based Pathogen Identification",
+    "edam_topics": ["topic_3168", "topic_3301"],  # Sequencing, Microbiology
+    "edam_operations": ["operation_0524", "operation_2425", "operation_3461", "operation_3482"],  # De-novo assembly, Optimisation and refinement, Virulence prediction, Antimicrobial resistance prediction
     "report": {
         "markdown": "# Gene-based Pathogen Identification Workflow Report\n\nBelow are the results for the Gene based Pathogen Identification Workflow\n\nThis workflow was run on:\n\n```galaxy\ngenerate_time()\n```\n\nWith Galaxy version:\n\n```galaxy\ngenerate_galaxy_version()\n```\n\n## Workflow Inputs\nThe Perprocessing workflow main output (Collection of all samples reads after quality retaining and hosts filtering)\n\n## Workflow Output\n\n### Identified contigs per sample\n\n```galaxy\nhistory_dataset_display(output=\"contigs\")\n```\n\n### Identified pathogenic genes per sample\n\n```galaxy\nhistory_dataset_display(output=\"vfs\")\n```\n\n### Identified Antimicrobial Resistance genes per sample\n\n```galaxy\nhistory_dataset_display(output=\"amrs\")\n```\n"
     },

workflows/microbiome/nanopore-pre-processing/Nanopore-Pre-Processing.ga

@@ -194,6 +194,8 @@
     "license": "MIT",
     "release": "0.1",
     "name": "Nanopore Preprocessing",
+    "edam_topics": ["topic_3168", "topic_3301"],  # Sequencing, Microbiology
+    "edam_operations": ["operation_3218", "operation_3219"],  # Sequencing quality control, Read pre-processing
     "report": {
         "markdown": "# Nanopore - Preprocessing Workflow Report\nBelow are the results of the Preprocessing  Workflow\n\nThis workflow was run on:\n\n```galaxy\ngenerate_time()\n```\n\nWith Galaxy version:\n\n```galaxy\ngenerate_galaxy_version()\n```\n\n## Workflow Inputs\nA collection of all sample reads (all in the same sequence file format, e.g.: Fastq, Fastq.gz, Fastqsanger, etc.)\n\n## Workflow Outputs\n\n### Multi QC Report of all samples before reads quality retaining\n\n```galaxy\nhistory_dataset_as_image(output=\"multiQC_html_report_before_preprocessing\")\n```\n### Multi QC Report of all samples after reads quality retaining\n\n```galaxy\nhistory_dataset_as_image(output=\"multiQC_html_report_after_preprocessing\")\n```\n\n### Table of the total number of reads and the number of host reads\n\n```galaxy\nhistory_dataset_display(output=\"removed_hosts_percentage_tabular\")\n```\n\n"
     },

workflows/microbiome/pathogen-detection-pathogfair-samples-aggregation-and-visualisation/Pathogen-Detection-PathoGFAIR-Samples-Aggregation-and-Visualisation.ga

@@ -204,6 +204,8 @@
     "license": "MIT",
     "release": "0.1",
     "name": "Pathogen Detection PathoGFAIR Samples Aggregation and Visualisation",
+    "edam_topics": ["topic_3168", "topic_3301"],  # Sequencing, Microbiology
+    "edam_operations": ["operation_0566", "operation_3436", "operation_3731"],  # Sequence cluster visualisation, Aggregation, Sample comparison
     "report": {
         "markdown": "# Pathogen Detection - PathoGFAIR Samples Aggregation and Visualisation Workflow Report\nBelow are the results for the PathoGFAIR Samples Aggregation and Visualisation Workflow\n\nThis workflow was run on:\n\n```galaxy\ngenerate_time()\n```\n\nWith Galaxy version:\n\n```galaxy\ngenerate_galaxy_version()\n```\n\n## Workflow Inputs\nTabular files and a FASTA file from the Gene-based Pathogen Identification workflow, four other tabular files from Nanopore Preprocessing and Nanopore - Allele-based Pathogen Identification workflow, and an optional Metadata tabular file with more sample information:\n\nFrom Gene-based Pathogenic Identification workflow: \n- contigs, FASTA file\n- VFs, Tabular file\n- vfs_of_genes_identified_by_vfdb, Tabular file\n- AMRs, Tabular file\n- amr_identified_by_ncbi, Tabular file\n\nFrom Nanopore - Allele bases Pathogen Identification workflow: \n- number_of_variants_per_sample, Tabular file\n- mapping_mean_depth_per_sample, Tabular file\n- mapping_coverage_percentage_per_sample, Tabular file\n\nFrom Nanopore Preprocessing: \n- removed_hosts_percentage_tabular, Tabular file\n\n## Some of the Workflow Outputs\n\n1- All Samples VFs Heatmap\n\n```galaxy\nhistory_dataset_as_image(output=\"heatmap_png\")\n```\n\n2- All samples phylogenetic tree VFs based\n\n```galaxy\nhistory_dataset_as_image(output=\"all_samples_phylogenetic_tree_based_vfs\")\n```\n\n3- All samples Phylogenetic tree AMR based \n\n```galaxy\nhistory_dataset_as_image(output=\"all_samples_phylogenetic_tree_based_amrs\")\n```\n\n4- Bar-plot for the Number of reads before host sequences removal and Number of found host reads per sample, performed in the Nanopore - Preprocessing workflow\n\n\n5- Barplot for the total number of removed host sequences per sample\n\n \n6- Barplot for the Mapping mean depth of coverage per sample\n\n\n6- Barplot for the Mapping breadth of coverage percentage per sample\n\n\n7- Barplot for the total number of complex variants and SNPs identified per sample\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n"
     },

workflows/microbiome/taxonomy-profiling-and-visualization-with-krona/Taxonomy-Profiling-and-Visualization-with-Krona.ga

@@ -66,6 +66,8 @@
     "license": "MIT",
     "release": "0.1",
     "name": "Taxonomy Profiling and Visualization with Krona",
+    "edam_topics": ["topic_3168", "topic_3301"],  # Sequencing, Microbiology,
+    "edam_operations": ["operation_3460"],  # Taxonomic classification
     "report": {
         "markdown": "# Taxonomy Profiling and Visualisation with Krona Workflow Report\n\nIn this workflow you can identify your microbial community, but identifying all possible Taxon found in your samples, from the kingdom level down to the species level. In the application of the pathogen detection, this workflow gives an overview of the possible bacterial found in samples and what might be a possible suspect for pathogenicity.\n\nThe workflow uses Kraken2 tool and allow the user to choose any Kraken2 database or other added ones depending on the user application or the input samples. All Kraken2 tool databases are available in Galaxy. More description about these databases can be found [here](https://benlangmead.github.io/aws-indexes/k2). Other databases can be also added to the tool, just contact us anytime for that. We recommend using StandardPF database.\n\nVisualization is done using Krona Pie Chart, and you can replace it with any other tool. e.g. Phinch interactive tool, which is also available in Galaxy\n\n## Workflow Inputs:\n\nThe per-processing workflow main output (Collection of all samples reads after quality retaining and hosts filtering)\n\n## Workflow Outputs are:\n\n### Taxonomy Tabular Report\n\nThe report shows the abundance of every taxon from the kingdom level down to the species level\n\n```galaxy\nhistory_dataset_display(output=\"converted_kraken_report\")\n```\n\n### Taxonomy Profiling Visualization with Krona\nAn interactive Pie chart showing the different identified taxons along with their percentages, which is one of the ways to visualize the previous taxonomy tabular\n\n```galaxy\nhistory_dataset_as_image(output=\"krona_pie_chart\")\n```\n"
     },

workflows/proteomics/clinicalmp/clinicalmp-discovery/iwc-clinicalmp-discovery-workflow.ga

@@ -12,6 +12,8 @@
     "format-version": "0.1",
     "license": "CC-BY-4.0",
     "name": "Clinical Metaproteomics Discovery Workflow",
+    "edam_topics": ["topic_0121",],  # Proteomics
+    "edam_operations": ["operation_3649"],  # Target-Decoy
     "release": "0.1",
     "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"

workflows/proteomics/clinicalmp/clinicalmp-quantitation/iwc-clinicalmp-quantitation.ga

@@ -11,6 +11,8 @@
     "format-version": "0.1",
     "license": "CC-BY-4.0",
     "name": "Clinical Metaproteomics Quantitation",
+    "edam_topics": ["topic_0121",],  # Proteomics
+    "edam_operations": ["operation_3630"],  # Protein quantification
     "release": "0.1",
     "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"

workflows/repeatmasking/RepeatMasking-Workflow.ga

@@ -5,6 +5,8 @@
     "license": "MIT",
     "release": "0.1",
     "name": "Repeat masking with RepeatModeler and RepeatMasker",
+    "edam_topics": ["topic_0157"],  # Sequence composition, complexity and repeats
+    "edam_operations": ["operation_0368", "operation_0379"],  # Sequence masking, Repeat sequence detection
     "creator": [
         {
             "class": "Person",
@@ -172,4 +174,4 @@
     "tags": [],
     "uuid": "f25be8fa-7823-456f-9707-a497703f48d7",
     "version": 0
-}
+}

workflows/sars-cov-2-variant-calling/sars-cov-2-consensus-from-variation/consensus-from-variation.ga

@@ -11,6 +11,8 @@
     "format-version": "0.1",
     "license": "MIT",
     "name": "COVID-19: consensus construction",
+    "edam_topics": ["topic_0781", "topic_3324"],  # Virology, Infectious disease
+    "edam_operations": ["operation_0448"],  # Sequence alignment analysis (conservation)
     "release": "0.4.2",
     "steps": {
         "0": {
@@ -1228,4 +1230,4 @@
         "covid19.galaxyproject.org"
     ],
     "uuid": "06dc40a7-99f2-4b3c-ae21-b3dcb239306f"
-}
+}

workflows/sars-cov-2-variant-calling/sars-cov-2-variation-reporting/variation-reporting.ga

@@ -11,6 +11,8 @@
     "format-version": "0.1",
     "license": "MIT",
     "name": "COVID-19: variation analysis reporting",
+    "edam_topics": ["topic_0781", "topic_3324"],  # Virology, Infectious disease
+    "edam_operations": ["operation_0566", "operation_3436", "operation_3731"],  # Sequence cluster visualisation, Aggregation, Sample comparison
     "release": "0.3.4",
     "steps": {
         "0": {
@@ -1713,4 +1715,4 @@
         "covid19.galaxyproject.org"
     ],
     "uuid": "b08c744d-7c61-4b58-ac5f-4b5886c3c643"
-}
+}

workflows/transcriptomics/brew3r/BREW3R.ga

@@ -12,6 +12,8 @@
     "format-version": "0.1",
     "license": "GPL-3.0-or-later",
     "name": "BREW3R",
+    "edam_topics": ["topic_3308"],  # Transcriptomics
+    "edam_operations": ["operation_0362"],  # Genome annotation
     "release": "0.2",
     "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"
@@ -452,4 +454,4 @@
     "tags": [],
     "uuid": "ac8ef6cb-1621-4b73-9362-8a460ef3c3a2",
     "version": 1
-}
+}

workflows/transcriptomics/rnaseq-de/rnaseq-de-filtering-plotting.ga

@@ -13,6 +13,8 @@
     "license": "MIT",
     "release": "0.2",
     "name": "RNAseq_DE_filtering_plotting",
+    "edam_topics": ["topic_3308"],  # Transcriptomics
+    "edam_operations": ["operation_3223"],  # Differential gene expression profiling
     "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"
     },
@@ -1131,4 +1133,4 @@
     ],
     "uuid": "15d188a7-b028-4cf7-bb5d-13858e1f6e78",
     "version": 15
-}
+}

workflows/transcriptomics/rnaseq-pe/rnaseq-pe.ga

@@ -81,6 +81,8 @@
     "license": "MIT",
     "release": "1.1",
     "name": "RNA-seq for Paired-end fastqs",
+    "edam_topics": ["topic_3170", "topic_3308"],  # RNA-Seq, Transcriptomics
+    "edam_operations": ["operation_3198", "operation_3219"],  # Read mapping, Read pre-processing
     "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"
     },
@@ -3411,4 +3413,4 @@
     ],
     "uuid": "5ab1d724-01d4-4673-a3c3-ae2bc944458f",
     "version": 1
-}
+}

workflows/virology/pox-virus-amplicon/pox-virus-half-genome.ga

@@ -18,6 +18,8 @@
     "license": "MIT",
     "release": "0.2",
     "name": "Pox Virus Illumina Amplicon Workflow from half-genomes",
+    "edam_topics": ["topic_0781", "topic_3168", "topic_3324"],  # Virology, Sequencing, Infectious disease
+    "edam_operations": ["operation_0448", "operation_3198", "operation_3218", "operation_3923"],  # Sequence alignment analysis (conservation), Read mapping, Sequencing quality control, Genome resequencing
     "steps": {
         "0": {
             "annotation": "The viral reference sequence to map sequenced reads against",