diff --git a/workflows/microbiome/mags-building/.dockstore.yml b/workflows/microbiome/mags-building/.dockstore.yml index 7a97a9b44e..011bb81d9f 100755 --- a/workflows/microbiome/mags-building/.dockstore.yml +++ b/workflows/microbiome/mags-building/.dockstore.yml @@ -16,4 +16,4 @@ workflows: - name: "Patrick Bühler" orcid: 0000-0003-2982-388X - name: Santino Faack - orcid: 0000-0003-2982-388X + orcid: 0009-0004-0382-2023 diff --git a/workflows/microbiome/mags-building/CHANGELOG.md b/workflows/microbiome/mags-building/CHANGELOG.md index a20c5270d5..b5eb485261 100644 --- a/workflows/microbiome/mags-building/CHANGELOG.md +++ b/workflows/microbiome/mags-building/CHANGELOG.md @@ -1,5 +1,13 @@ # Changelog +## [0.5] - 2026-26-04 + +- **metaSPAdes** now can use optional long reads as input +- remove non-main MAGs steps from the workflow (genome annotation, taxonomy annotation) they are now in seperate workflows, that can be used optionally downstream of the main workflow +- Change COMEBin to be a optional binner + +### Changed + ## [0.4] - 2025-10-07 ### Changed diff --git a/workflows/microbiome/mags-building/MAGs-generation-tests.yml b/workflows/microbiome/mags-building/MAGs-generation-tests.yml index 84531578f4..afde743d3f 100644 --- a/workflows/microbiome/mags-building/MAGs-generation-tests.yml +++ b/workflows/microbiome/mags-building/MAGs-generation-tests.yml @@ -1,4 +1,4 @@ -- doc: Test for Metagenome-Assembled-Genomes-(MAGs)-generation +- doc: Test for Metagenome-Assembled-Genomes-(MAGs)-generation short read only job: Trimmed reads: class: Collection @@ -6,61 +6,202 @@ elements: - class: Collection type: paired - identifier: 50contig_reads + identifier: test_minigut elements: - class: File identifier: forward - location: https://zenodo.org/records/15089018/files/MAG_reads_forward.fastqsanger.gz + location: https://zenodo.org/records/19235149/files/test_minigut_R1.fastq.gz - class: File identifier: reverse - location: https://zenodo.org/records/15089018/files/MAG_reads_reverse.fastqsanger.gz - Trimmed reads from grouped samples: + location: https://zenodo.org/records/19235149/files/test_minigut_R2.fastq.gz + Trimmed paired reads from grouped samples: class: Collection collection_type: list:paired elements: - class: Collection type: paired - identifier: 50contig_reads + identifier: test_minigut elements: - - class: File - identifier: forward - location: https://zenodo.org/records/15089018/files/MAG_reads_forward.fastqsanger.gz - - class: File - identifier: reverse - location: https://zenodo.org/records/15089018/files/MAG_reads_reverse.fastqsanger.gz + - class: File + identifier: forward + location: https://zenodo.org/records/19235149/files/test_minigut_R1.fastq.gz + - class: File + identifier: reverse + location: https://zenodo.org/records/19235149/files/test_minigut_R2.fastq.gz + Trimmed nanopore reads from grouped samples: null + Trimmed PacBio reads from grouped samples: null Choose Assembler: MEGAHIT Custom Assemblies: null - Minimum length of contigs to output: '200' + Minimum length of contigs to output: '100' Read length (CONCOCT): '100' Environment for the built-in model (SemiBin): global - Contamination weight (Binette): '2' + Contamination weight (Binette): '100' CheckM2 Database: 1.0.2 Minimum MAG completeness percentage: '1' - Maximum MAG contamination percentage: '25' + Maximum MAG contamination percentage: '1' Minimum MAG length: '100' - ANI threshold for dereplication: '0.95' - GTDB-tk Database: full_database_release_220_downloaded_2024-10-19 - Bakta Database: V5.1_2024-01-19 - AMRFinderPlus Database for Bakta: amrfinderplus_V3.12_2024-05-02.2 - Run Bakta on MAGs: true - Run GTDB-Tk on MAGs: false + ANI threshold for dereplication: '0.99' + Run COMEBin: false outputs: Full MultiQC Report: asserts: - that: has_text - text: "50contig_reads_bin" + text: "minigut_reads_binette_bin10_fasta" - that: has_text text: "QUAST" - that: has_text text: "CheckM" Assembly Report: element_tests: - 50contig_reads: + minigut_reads: asserts: - that: has_text text: "All statistics are based on contigs of size" - that: has_size - value: 372000 + value: 373800 delta: 50000 - - + Primary clustering dendrogram: + asserts: + - that: has_size + value: 169000 + delta: 20000 + Cluster Assignment: + asserts: + - that: has_text + text: "genome" + - that: has_text + text: "primary_cluster" + - that: has_text + text: "minigut_reads_binette_bin49.fasta" + Dereplicated Bins: + element_tests: + minigut_reads_binette_bin1.fasta: + asserts: + - that: has_size + value: 715700 + delta: 10000 + Merged CoverM Output: + asserts: + - that: has_text + text: "Genome" + - that: has_text + text: "minigut_reads_binette_bin10" + Merged Quast Output: + asserts: + - that: has_text + text: "Assembly" + - that: has_text + text: "118" + - that: has_text + text: "minigut_reads_binette_bin10.fasta" +- doc: Test for Metagenome-Assembled-Genomes-(MAGs)-generation long read test + job: + Trimmed reads: + class: Collection + collection_type: list:paired + elements: + - class: Collection + type: paired + identifier: test_minigut + elements: + - class: File + identifier: forward + location: https://zenodo.org/records/19235149/files/test_minigut_R1.fastq.gz + - class: File + identifier: reverse + location: https://zenodo.org/records/19235149/files/test_minigut_R2.fastq.gz + Trimmed paired reads from grouped samples: + class: Collection + collection_type: list:paired + elements: + - class: Collection + type: paired + identifier: test_minigut + elements: + - class: File + identifier: forward + location: https://zenodo.org/records/19235149/files/test_minigut_R1.fastq.gz + - class: File + identifier: reverse + location: https://zenodo.org/records/19235149/files/test_minigut_R2.fastq.gz + Trimmed nanopore reads from grouped samples: + class: Collection + collection_type: list + elements: + - class: File + identifier: minigut_reads + location: https://zenodo.org/records/19235149/files/minigut_reads.fastq.gz + Trimmed PacBio reads from grouped samples: null + Choose Assembler: metaSPAdes + Custom Assemblies: null + Minimum length of contigs to output: '100' + Read length (CONCOCT): '100' + Environment for the built-in model (SemiBin): global + Contamination weight (Binette): '100' + CheckM2 Database: 1.0.2 + Minimum MAG completeness percentage: '1' + Maximum MAG contamination percentage: '1' + Minimum MAG length: '100' + ANI threshold for dereplication: '0.99' + Run COMEBin: false + outputs: + Full MultiQC Report: + asserts: + - that: has_text + text: "minigut_reads_binette_bin1_fasta" + - that: has_text + text: "QUAST" + - that: has_text + text: "CheckM" + Assembly Report: + element_tests: + minigut_reads: + asserts: + - that: has_text + text: "All statistics are based on contigs of size" + - that: has_size + value: 361400 + delta: 50000 + out cn: + element_tests: + minigut_reads: + asserts: + - that: has_size + value: 1736000 + delta: 200000 + Primary clustering dendrogram: + asserts: + - that: has_size + value: 131000 + delta: 20000 + Cluster Assignment: + asserts: + - that: has_text + text: "genome" + - that: has_text + text: "primary_cluster" + - that: has_text + text: "minigut_reads_binette_bin2.fasta" + Dereplicated Bins: + element_tests: + minigut_reads_binette_bin1.fasta: + asserts: + - that: has_size + value: 848000 + delta: 10000 + Merged CoverM Output: + asserts: + - that: has_text + text: "Genome" + - that: has_text + text: "unmapped" + - that: has_text + text: "minigut_reads_binette_bin2" + Merged Quast Output: + asserts: + - that: has_text + text: "Assembly" + - that: has_text + text: "4" + - that: has_text + text: "minigut_reads_binette_bin2.fasta" \ No newline at end of file diff --git a/workflows/microbiome/mags-building/MAGs-generation.ga b/workflows/microbiome/mags-building/MAGs-generation.ga index 874f2e3b36..65c4600de8 100644 --- a/workflows/microbiome/mags-building/MAGs-generation.ga +++ b/workflows/microbiome/mags-building/MAGs-generation.ga @@ -1,16 +1,25 @@ { "a_galaxy_workflow": "true", - "annotation": "This workflow produces Metagenome-Assembled Genomes (MAGs) from paired-end metagenomic reads. It includes assembly, binning, refinement, dereplication, annotation, taxonomic classification, quality assessment, and abundance estimation. All results are summarised in a single integrated report and aggregated tables.", + "annotation": "", "comments": [ { + "child_steps": [ + 63, + 65, + 66, + 67, + 68, + 62, + 64 + ], "color": "blue", "data": { "title": "Quality" }, - "id": 9, + "id": 11, "position": [ 9931, - 1274.2311960629306 + 1850.7311960629306 ], "size": [ 1663, @@ -19,94 +28,174 @@ "type": "frame" }, { - "color": "turquoise", + "child_steps": [ + 58, + 61, + 59, + 60, + 16, + 15, + 14 + ], + "color": "green", "data": { - "title": "Annotation" + "title": "Depreplication" }, - "id": 8, + "id": 10, "position": [ - 9646.2, - 155.9311960629306 + 6702.1, + 850.6311960629305 ], "size": [ - 1873, - 801 + 2384, + 1005 ], "type": "frame" }, { - "color": "green", + "child_steps": [ + 54, + 38, + 43, + 48, + 12, + 52 + ], + "color": "yellow", "data": { - "title": "Depreplication" + "title": "Binner (CONOCT)" }, - "id": 7, + "id": 9, "position": [ - 6702.1, - 274.13119606293054 + 4544.4, + 4084.8 ], "size": [ - 2384, - 1005 + 1108.7, + 471 + ], + "type": "frame" + }, + { + "child_steps": [ + 42, + 47, + 9 + ], + "color": "yellow", + "data": { + "title": "COMEBin" + }, + "id": 8, + "position": [ + 4465.9, + 3625.2 + ], + "size": [ + 725, + 307 ], "type": "frame" }, { + "child_steps": [ + 57, + 44, + 49, + 50, + 53, + 55, + 56, + 11, + 10 + ], "color": "lime", "data": { "title": "Bin refinement" }, - "id": 5, + "id": 7, "position": [ 5697.9, - 205.23119606293056 + 781.7311960629306 ], "size": [ - 918, - 1402 + 978, + 1670 ], "type": "frame" }, { - "color": "orange", + "child_steps": [ + 46 + ], + "color": "yellow", "data": { - "title": "Assembly" + "title": "Binner (MetaBAT2)" }, - "id": 1, + "id": 6, "position": [ - 1182.7000000000003, - 1003.5455697009531 + 4739.7, + 3131.8 ], "size": [ - 1323, - 1439 + 240, + 438.5 ], "type": "frame" }, { - "color": "pink", + "child_steps": [ + 45 + ], + "color": "yellow", "data": { - "title": "Input" + "title": "Binner (MaxBin2)" }, - "id": 0, + "id": 5, "position": [ - 0, - 991.3455697009531 + 4913.9, + 2538.4 ], "size": [ - 436, - 638 + 240, + 417.7 + ], + "type": "frame" + }, + { + "child_steps": [ + 40, + 8 + ], + "color": "orange", + "data": { + "title": "SemiBin" + }, + "id": 4, + "position": [ + 4114.4, + 1030.1 + ], + "size": [ + 860, + 1120 ], "type": "frame" }, { + "child_steps": [ + 37, + 39, + 41 + ], "color": "yellow", "data": { - "title": "Binning (each binner)" + "title": "Abundance utils for Binning" }, - "id": 2, + "id": 3, "position": [ 2071.1000000000004, - 2852.2455697009527 + 3428.7455697009527 ], "size": [ 1673, @@ -115,50 +204,84 @@ "type": "frame" }, { - "color": "yellow", + "child_steps": [ + 36, + 20, + 24, + 6, + 21, + 4, + 22, + 35, + 7 + ], + "color": "orange", "data": { - "title": "Binner (MaxBin2)" + "title": "Assembly" }, - "id": 3, + "id": 2, "position": [ - 4751.1, - 1923.645569700953 + 1182.7000000000003, + 1580.0455697009531 ], "size": [ - 540.4, - 562.4 + 1323, + 1439 ], "type": "frame" }, { - "color": "yellow", + "child_steps": [ + 3, + 1, + 2, + 5 + ], + "color": "pink", "data": { - "title": "Binner (MetaBAT2)" + "title": "Input" }, - "id": 4, + "id": 1, "position": [ - 4532.700000000001, - 2498.845569700953 + 0, + 1567.845569700953 ], "size": [ - 635.7, - 468.8 + 436, + 638 ], "type": "frame" }, { - "color": "yellow", + "child_steps": [ + 17, + 34, + 0, + 26, + 25, + 23, + 18, + 19, + 27, + 28, + 29, + 30, + 31, + 32, + 33 + ], + "color": "pink", "data": { - "title": "Binner (CONOCT)" + "title": "metaSPADES with optional long reads" }, - "id": 6, + "id": 0, "position": [ - 4535.9, - 3496.545569700953 + 361.6, + 0 ], "size": [ - 1547, - 986 + 2579, + 1494 ], "type": "frame" } @@ -196,74 +319,135 @@ } ], "format-version": "0.1", - "help": "The current workflow default parameters are rather conservative, aiming for high-quality MAGs.\nTo report lower quality MAGs as well, change the parameters of completeness and contamination.\nThis workflow is maintained by the microGalaxy community. Feel free to reach out for support: [microGalaxy](https://galaxyproject.org/community/sig/microbial)", "license": "MIT", - "release": "0.4", + "release": "0.5", "name": "Metagenome-Assembled Genomes (MAGs) generation", - "readme": "# Metagenome-Assembled Genomes (MAGs) Generation \n\nThis workflow generates Metagenome-Assembled Genomes (MAGs) from paired short reads. \nDereplicated MAGs for the complete input sample set are reported.\n\n## Workflow Logic \n\nThe workflow supports assembly using **metaSPADES** and **MEGAHIT**. \nFor binning, it utilizes four different tools: **MetaBAT2, MaxBin2, SemiBin, and CONCOCT**. The resulting bins are then refined using **Binette**, the successor of metaWRAP. \n\n## MAGs Annotation and Quality Control \n\nAfter binning, the resulting MAGs are **dereplicated** across all input samples based on **CheckM2 quality metrics** using **dRep**. The following processing steps are then performed: \n\n- **Annotation** with Bakta \n- **Taxonomic Assignment** using GTDB-Tk \n- **Quality Control** via QUAST and CheckM/CheckM2 \n- **Abundance Estimation** per sample with CoverM \n\nAll results are consolidated into a single **MultiQC report** for easy analysis. \n\n## Input Requirements \n\nInput reads must be quality-filtered, with host reads removed. \nSee other MAGs workflows in IWC for quality filtering and host removal.\n\n- **Trimmed reads**: Quality-trimmed reads from individual samples.\n- **Trimmed reads from grouped samples**: These reads need to be grouped based on the desired MAGs generation approach. The tool [fastq_groupmerge](toolshed.g2.bx.psu.edu/repos/iuc/fastq_groupmerge/fastq_groupmerge/1.0.1+galaxy0) can be used to perform the grouping. \n - **Individual MAGs Generation**: Use the same input as `Trimmed Reads` to generate MAGs per sample. \n - **Pooled MAGs Generation (Co-assembly/Binning)**: Merge all reads input one file for a fully pooled MAGs approach. \n - **Grouped MAGs Generation (Co-assembly/Binning)**: Merge samples based on predefined groups. \n - **Hybrid MAGs Generation**: Combine individual and grouped reads for a mixed approach. \n\n> **Note**: Merging reads can result in large input files, significantly increasing computational demands\u2014especially during assembly and binning, which may require substantial RAM. Our tests with synthetic samples up to **50 GB** showed feasible performance. For larger datasets, we recommend limiting the approach to **individual or pooled MAGs generation**. \n\n## Optional modifications\n\nSome modifications that can be done via the workflow editor for specific use cases:\n- Compare binners / bin refinement: add checkM/M2 to each binner / refiner and compare completeness, contamination, n. of bins.\n- Optionally use DAS tool instead of Binette (our benchmark showed that Binette produce better MAGs on average).\n- Add annotation for Bakta (currently Bakta only reports rRNAs to save resources), other annotations can be selected in the Bakta options.\n- Downstream: compare differential abundance of MAGs in your samples based on metadata using maaslin2.\n- Downstream: compare your MAGs to a catalogue of MAGs for similar samples. Download desired MAGs e.g. from [MGnify genomes](https://www.ebi.ac.uk/metagenomics/browse/genomes) you can query your MAGs via the [MGnify API](https://www.ebi.ac.uk/metagenomics/browse/genomes?browse-by=mag-search); download the Genomes and compare in Galaxy e.g. using dREP.", + "readme": "# Metagenome-Assembled Genomes (MAGs) Generation\n\nThis workflow generates Metagenome-Assembled Genomes (MAGs) from paired short reads and optional long reads.\nThe use of long reads is only supported for assembly with **metaSPADES**.\nDereplicated MAGs for the complete input sample set are reported.\n\n## Workflow Logic\n\nThe workflow supports assembly using **metaSPADES** and **MEGAHIT**.\nFor binning, it utilizes five different tools: **MetaBAT2, MaxBin2, SemiBin, COMEBin, and CONCOCT**. The resulting bins are then refined using **Binette**, the successor of metaWRAP.\n\n## MAGs Annotation and Quality Control\n\nAfter binning, the resulting MAGs are **dereplicated** across all input samples based on **CheckM2 quality metrics** using **dRep**. The following processing steps are then performed:\n\n* **Quality Control** via QUAST and CheckM/CheckM2\n* **Abundance Estimation** per sample with CoverM\n\nIn previous versions, genome annotation and taxonomic annotation were also performed. This can now be done with dedicated and more comprehensive IWC workflows if needed:\n\n* [MAG Genome Annotation](https://iwc.galaxyproject.org/workflow/mag-genome-annotation-parallel-main)\n* [MAGs Taxonomy Annotation](https://iwc.galaxyproject.org/workflow/mags-taxonomy-annotation-main)\n* [Functional Annotation of Sequences](https://iwc.galaxyproject.org/workflow/functional-annotation-of-sequences-main)\n* [AMR Gene Detection](https://iwc.galaxyproject.org/workflow/amr_gene_detection-main)\n\nAll results are consolidated into a single **MultiQC report**.\n\n## Input Requirements\n\nInput reads must be quality-filtered, with host reads removed.\nSee other MAG workflows in IWC for quality filtering and host removal.\n\n**Short reads:**\n\n* QC: [Short Read QC & Trimming](https://iwc.galaxyproject.org/workflow/short-read-qc-trimming-main)\n* Host removal: [Host Contamination Removal (Short Reads)](https://iwc.galaxyproject.org/workflow/host-contamination-removal-short-reads-main)\n\n**Long reads:**\n\n* QC: [Nanopore Pre-processing](https://iwc.galaxyproject.org/workflow/nanopore-pre-processing-main)\n* Host removal: [Host Contamination Removal (Long Reads)](https://iwc.galaxyproject.org/workflow/host-contamination-removal-long-reads-main)\n\n**Workflow input:**\n\n* **Trimmed reads**: Quality-trimmed reads from individual samples.\n* **Trimmed reads from grouped samples**: These reads need to be grouped based on the desired MAGs generation approach. The tool [fastq_groupmerge](toolshed.g2.bx.psu.edu/repos/iuc/fastq_groupmerge/fastq_groupmerge/1.0.1+galaxy0) can be used to perform the grouping. Long reads and short reads must be grouped using the same logic.\n\n * **Individual MAGs Generation**: Use the same input as `Trimmed Reads` to generate MAGs per sample.\n * **Pooled MAGs Generation (Co-assembly/Binning)**: Merge all reads into one file for a fully pooled MAGs approach.\n * **Grouped MAGs Generation (Co-assembly/Binning)**: Merge samples based on predefined groups.\n * **Hybrid MAGs Generation**: Combine individual and grouped reads for a mixed approach.\n\n> **Note**: Merging reads can result in large input files, significantly increasing computational demands\u2014especially during assembly and binning, which may require substantial RAM. Our tests with synthetic samples up to **50 GB** showed feasible performance. For larger datasets, we recommend limiting the approach to **individual or pooled MAGs generation**.\n\n## Optional Modifications\n\nSome modifications can be made via the workflow editor for specific use cases:\n\n* Compare binners/bin refinement: add CheckM/CheckM2 to each binner/refiner and compare completeness, contamination, and number of bins.\n* Optionally use DAS Tool instead of Binette (our benchmark showed that Binette produces better MAGs on average).\n* Downstream: compare differential abundance of MAGs in your samples based on metadata using Maaslin2.\n* Downstream: compare your MAGs to a catalogue of MAGs for similar samples. Download desired MAGs from [MGnify genomes](https://www.ebi.ac.uk/metagenomics/browse/genomes) and query your MAGs via the [MGnify API](https://www.ebi.ac.uk/metagenomics/browse/genomes?browse-by=mag-search); download the genomes and compare in Galaxy, e.g., using dRep.", "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": "These should be the reads from the samples to estimate MAGs abundance in the original samples.", - "content_id": null, + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_text_file_with_recurring_lines/9.5+galaxy3", "errors": null, "id": 0, "input_connections": {}, + "inputs": [], + "label": null, + "name": "Create text file", + "outputs": [ + { + "name": "outfile", + "type": "txt" + } + ], + "position": { + "left": 749.9543333862634, + "top": 725.266848738474 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_text_file_with_recurring_lines/9.5+galaxy3", + "tool_shed_repository": { + "changeset_revision": "ab83aa685821", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"token_set\": [{\"__index__\": 0, \"line\": null, \"repeat_select\": {\"repeat_select_opts\": \"user\", \"__current_case__\": 0, \"times\": \"1\"}}], \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "9.5+galaxy3", + "type": "tool", + "uuid": "4bd09898-aa56-4f77-a49a-7607e2f7daa6", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, "inputs": [ { - "description": "These should be the reads from the samples to estimate MAGs abundance in the original samples.", - "name": "Trimmed reads" + "description": "", + "name": "Trimmed nanopore reads from grouped samples" } ], - "label": "Trimmed reads", + "label": "Trimmed nanopore reads from grouped samples", "name": "Input dataset collection", "outputs": [], "position": { - "left": 91.82161527691096, - "top": 1248.722231575075 + "left": 90.89495849609375, + "top": 1611.7471313476562 }, "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null}", + "tool_state": "{\"optional\": true, \"tag\": null, \"collection_type\": \"list\", \"fields\": null, \"column_definitions\": null}", "tool_version": null, "type": "data_collection_input", - "uuid": "2e5f8ecc-d8a8-4591-b311-4b87fc0c8e7e", + "uuid": "9d728ee0-09d3-4bfd-9bdf-5d5a2924c87a", "when": null, "workflow_outputs": [] }, - "1": { + "2": { + "annotation": "", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "Trimmed PacBio reads from grouped samples" + } + ], + "label": "Trimmed PacBio reads from grouped samples", + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 86.81805419921875, + "top": 1740.0283813476562 + }, + "tool_id": null, + "tool_state": "{\"optional\": true, \"tag\": null, \"collection_type\": \"list\", \"fields\": null, \"column_definitions\": null}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "ab984f1f-205f-447d-9b9c-0f42a11711c6", + "when": null, + "workflow_outputs": [] + }, + "3": { "annotation": "Samples grouped for co-assembly. For individual assembly use same reads as `Trimmed reads input`. The tool fastq_groupmerge can be used to perform the grouping.", "content_id": null, "errors": null, - "id": 1, + "id": 3, "input_connections": {}, "inputs": [ { "description": "Samples grouped for co-assembly. For individual assembly use same reads as `Trimmed reads input`. The tool fastq_groupmerge can be used to perform the grouping.", - "name": "Trimmed reads from grouped samples" + "name": "Trimmed paired reads from grouped samples" } ], - "label": "Trimmed reads from grouped samples", + "label": "Trimmed paired reads from grouped samples", "name": "Input dataset collection", "outputs": [], "position": { - "left": 84.80300485208974, - "top": 1417.1656812076462 + "left": 80.90911865234375, + "top": 1908.849365234375 }, "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null}", + "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", "tool_version": null, "type": "data_collection_input", - "uuid": "dd8faa6e-3f29-4fa2-befb-38ef4a7832b5", + "uuid": "0b547a63-e3e4-4026-8b77-3da10ec86c34", "when": null, "workflow_outputs": [] }, - "2": { + "4": { "annotation": "The workflow can use MEGAHIT and metaSPAdes as assembler", "content_id": null, "errors": null, - "id": 2, + "id": 4, "input_connections": {}, "inputs": [ { @@ -276,21 +460,48 @@ "outputs": [], "position": { "left": 1218.6987516456284, - "top": 1072.7991986932018 + "top": 1649.2991986932018 }, "tool_id": null, "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictions\": [\"MEGAHIT\", \"metaSPAdes\", \"Custom Assembly\"], \"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "c583f4f7-8857-42d4-b1bb-05f32364526f", + "uuid": "d6354c3c-a712-48aa-86a9-4e638978340d", "when": null, "workflow_outputs": [] }, - "3": { + "5": { + "annotation": "These should be the reads from the samples to estimate MAGs abundance in the original samples.\n", + "content_id": null, + "errors": null, + "id": 5, + "input_connections": {}, + "inputs": [ + { + "description": "These should be the reads from the samples to estimate MAGs abundance in the original samples.\n", + "name": "Trimmed reads" + } + ], + "label": "Trimmed reads", + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 82.96881103515625, + "top": 2068.678955078125 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "2a9df494-9cb4-4fd3-97f5-82a7f340d65f", + "when": null, + "workflow_outputs": [] + }, + "6": { "annotation": "Minimum length of contigs to output (only for MEGAHIT).", "content_id": null, "errors": null, - "id": 3, + "id": 6, "input_connections": {}, "inputs": [ { @@ -303,21 +514,21 @@ "outputs": [], "position": { "left": 1690.6877659215845, - "top": 1685.252615443602 + "top": 2261.752615443602 }, "tool_id": null, "tool_state": "{\"default\": 200, \"validators\": [{\"min\": null, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "dff03e41-04a4-4c60-84f1-5f3ec1591e7d", + "uuid": "eee86c51-632e-4b05-b9f8-4cb0da0d849e", "when": null, "workflow_outputs": [] }, - "4": { + "7": { "annotation": "This workflow allows using a custom assembly as input. If provided, select `custom assembly` as Assembler.\nProvide one assembly for each group of trimmed input reads.", "content_id": null, "errors": null, - "id": 4, + "id": 7, "input_connections": {}, "inputs": [ { @@ -330,21 +541,21 @@ "outputs": [], "position": { "left": 1963.0885585694696, - "top": 1701.8131539167669 + "top": 2278.313153916767 }, "tool_id": null, - "tool_state": "{\"optional\": true, \"tag\": null, \"collection_type\": \"list\", \"fields\": null}", + "tool_state": "{\"optional\": true, \"tag\": null, \"collection_type\": \"list\", \"fields\": null, \"column_definitions\": null}", "tool_version": null, "type": "data_collection_input", - "uuid": "e2f5ad16-674f-4687-94a4-a5e55680440a", + "uuid": "3fb488b6-6daf-41a1-bbd0-fc6af0d7e940", "when": null, "workflow_outputs": [] }, - "5": { + "8": { "annotation": "Environment for the built-in model (SemiBin), options are: human_gut, dog_gut, ocean, soil, cat_gut, human_oral, mouse_gut, pig_gut, built_environment, wastewater, chicken_caecum, global", "content_id": null, "errors": null, - "id": 5, + "id": 8, "input_connections": {}, "inputs": [ { @@ -356,22 +567,49 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 2919.26939260254, - "top": 2926.7343639392298 + "left": 4173.914484674159, + "top": 1481.6938976695028 }, "tool_id": null, "tool_state": "{\"default\": \"global\", \"multiple\": false, \"validators\": [], \"restrictions\": [\"global\", \"human_gut\", \"dog_gut\", \"ocean\", \"soil\", \"cat_gut\", \"human_oral\", \"mouse_gut\", \"pig_gut\", \"built_environment\", \"wastewater\", \"chicken_caecum\"], \"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "86fc3246-f756-49ce-b196-ffa358e5ac41", + "uuid": "5f4853c1-8792-4910-9f2f-b27b5418bee7", "when": null, "workflow_outputs": [] }, - "6": { + "9": { + "annotation": "", + "content_id": null, + "errors": null, + "id": 9, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "Run COMEBin" + } + ], + "label": "Run COMEBin", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 4502.499854329428, + "top": 3667.453172607423 + }, + "tool_id": null, + "tool_state": "{\"validators\": [], \"parameter_type\": \"boolean\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "6b89cbbe-31c1-4ace-8f06-1ac239f4540d", + "when": null, + "workflow_outputs": [] + }, + "10": { "annotation": "Minimum MAG completeness percentage for bin refinement (binette) and dereplication (drep)", "content_id": null, "errors": null, - "id": 6, + "id": 10, "input_connections": {}, "inputs": [ { @@ -384,21 +622,21 @@ "outputs": [], "position": { "left": 5730.37010398056, - "top": 614.5939624823972 + "top": 1191.0939624823973 }, "tool_id": null, "tool_state": "{\"default\": 75, \"validators\": [{\"min\": null, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "a4523acb-d004-4637-b3f6-e5f0e01b5cb0", + "uuid": "f694e159-2c86-4c88-9ed9-c2205bb515a5", "when": null, "workflow_outputs": [] }, - "7": { + "11": { "annotation": "This weight is used for the scoring the bins. A low weight favor complete bins over low contaminated bins (--contamination_weight)", "content_id": null, "errors": null, - "id": 7, + "id": 11, "input_connections": {}, "inputs": [ { @@ -411,21 +649,21 @@ "outputs": [], "position": { "left": 5721.867017043314, - "top": 771.4338055273925 + "top": 1347.9338055273925 }, "tool_id": null, "tool_state": "{\"default\": 2, \"validators\": [{\"min\": null, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "144508a3-dea3-41fe-8e50-306e23dc9db7", + "uuid": "1c620487-ecee-46d3-b849-4bf8977047f9", "when": null, "workflow_outputs": [] }, - "8": { + "12": { "annotation": "CONCOCT requires the read length for coverage. Best use fastQC to estimate the mean value.", "content_id": null, "errors": null, - "id": 8, + "id": 12, "input_connections": {}, "inputs": [ { @@ -438,21 +676,21 @@ "outputs": [], "position": { "left": 4878.02632018713, - "top": 3877.424079253945 + "top": 4453.924079253945 }, "tool_id": null, "tool_state": "{\"default\": 100, \"validators\": [{\"min\": null, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "30109f1d-816b-4f85-a0b3-e54506ae32ae", + "uuid": "5236e9c1-cb54-48a1-9891-c9211fb42ff8", "when": null, "workflow_outputs": [] }, - "9": { + "13": { "annotation": "CheckM2 Reference Database used for quality assessment for Binette, dRep, and quality assessment of the final bins", "content_id": null, "errors": null, - "id": 9, + "id": 13, "input_connections": {}, "inputs": [ { @@ -465,21 +703,21 @@ "outputs": [], "position": { "left": 6622.788246571617, - "top": 0 + "top": 576.5 }, "tool_id": null, "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "8f5f3b1a-5b4c-4286-8a7e-bec0669b49e8", + "uuid": "194b88aa-7001-4598-ae8c-7840c38517e0", "when": null, "workflow_outputs": [] }, - "10": { + "14": { "annotation": "Minimum MAG length for dereplication", "content_id": null, "errors": null, - "id": 10, + "id": 14, "input_connections": {}, "inputs": [ { @@ -492,186 +730,194 @@ "outputs": [], "position": { "left": 8292.163070422486, - "top": 448.9933530121662 + "top": 1025.4933530121662 }, "tool_id": null, "tool_state": "{\"default\": 50000, \"validators\": [{\"min\": null, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "60120647-1bb9-4eb9-879a-ab9796ee94c4", + "uuid": "d730cd68-dabf-4625-8f30-7c08400434b1", "when": null, "workflow_outputs": [] }, - "11": { - "annotation": "ANI threshold to form secondary clusters of dereplication. An ANI value of \u226595-96% indicates genomes belong to the same species, an ANI of \u226598-99% suggests they are the same strain, and an ANI of \u226490-95% typically points to genomes from different genera.", + "15": { + "annotation": "Maximum MAG contamination percentage for dereplication ", "content_id": null, "errors": null, - "id": 11, + "id": 15, "input_connections": {}, "inputs": [ { - "description": "ANI threshold to form secondary clusters of dereplication. An ANI value of \u226595-96% indicates genomes belong to the same species, an ANI of \u226598-99% suggests they are the same strain, and an ANI of \u226490-95% typically points to genomes from different genera.", - "name": "ANI threshold for dereplication" + "description": "Maximum MAG contamination percentage for dereplication ", + "name": "Maximum MAG contamination percentage" } ], - "label": "ANI threshold for dereplication", + "label": "Maximum MAG contamination percentage", "name": "Input parameter", "outputs": [], "position": { - "left": 8303.820103167396, - "top": 980.0792387496865 + "left": 8363.90878646624, + "top": 1173.4463214274667 }, "tool_id": null, - "tool_state": "{\"default\": 0.95, \"validators\": [{\"min\": 0.9, \"max\": 1.0, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"float\", \"optional\": false}", + "tool_state": "{\"default\": 25, \"validators\": [{\"min\": null, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "a05feebf-3744-434f-8865-50788e52ab15", + "uuid": "63130ee7-0d4c-48fa-b5e5-d0f315659749", "when": null, "workflow_outputs": [] }, - "12": { - "annotation": "Maximum MAG contamination percentage for dereplication ", + "16": { + "annotation": "ANI threshold to form secondary clusters of dereplication. An ANI value of \u226595-96% indicates genomes belong to the same species, an ANI of \u226598-99% suggests they are the same strain, and an ANI of \u226490-95% typically points to genomes from different genera.", "content_id": null, "errors": null, - "id": 12, + "id": 16, "input_connections": {}, "inputs": [ { - "description": "Maximum MAG contamination percentage for dereplication ", - "name": "Maximum MAG contamination percentage" + "description": "ANI threshold to form secondary clusters of dereplication. An ANI value of \u226595-96% indicates genomes belong to the same species, an ANI of \u226598-99% suggests they are the same strain, and an ANI of \u226490-95% typically points to genomes from different genera.", + "name": "ANI threshold for dereplication" } ], - "label": "Maximum MAG contamination percentage", + "label": "ANI threshold for dereplication", "name": "Input parameter", "outputs": [], "position": { - "left": 8363.90878646624, - "top": 596.9463214274667 + "left": 8303.820103167396, + "top": 1556.5792387496865 }, "tool_id": null, - "tool_state": "{\"default\": 25, \"validators\": [{\"min\": null, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", + "tool_state": "{\"default\": 0.95, \"validators\": [{\"min\": 0.9, \"max\": 1.0, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"float\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "57370a7c-aa90-4fbf-8761-25fbe2c3d947", + "uuid": "98263780-89bb-40e1-8a36-3cfe139c7181", "when": null, "workflow_outputs": [] }, - "13": { - "annotation": "GTDB-Tk can take a long time and requires a lot of memory, run only if taxonomic placement is required.", - "content_id": null, + "17": { + "annotation": "", + "content_id": "Grep1", "errors": null, - "id": 13, - "input_connections": {}, - "inputs": [ - { - "description": "GTDB-Tk can take a long time and requires a lot of memory, run only if taxonomic placement is required.", - "name": "Run GTDB-Tk on MAGs" + "id": 17, + "input_connections": { + "input": { + "id": 0, + "output_name": "outfile" } - ], - "label": "Run GTDB-Tk on MAGs", - "name": "Input parameter", - "outputs": [], - "position": { - "left": 9740.137180438269, - "top": 236.23599481705372 }, - "tool_id": null, - "tool_state": "{\"default\": true, \"validators\": [], \"parameter_type\": \"boolean\", \"optional\": false}", - "tool_version": null, - "type": "parameter_input", - "uuid": "60115dff-f28d-4c18-acbc-725ffed7ac33", - "when": null, - "workflow_outputs": [] - }, - "14": { - "annotation": "GTDB-tk Database used for Bin Taxonomy Classification", - "content_id": null, - "errors": null, - "id": 14, - "input_connections": {}, - "inputs": [ + "inputs": [], + "label": null, + "name": "Select", + "outputs": [ { - "description": "GTDB-tk Database used for Bin Taxonomy Classification", - "name": "GTDB-tk Database" + "name": "out_file1", + "type": "input" } ], - "label": "GTDB-tk Database", - "name": "Input parameter", - "outputs": [], "position": { - "left": 9825.45285836357, - "top": 405.36663227433286 + "left": 996.0325672519823, + "top": 844.0712867377113 }, - "tool_id": null, - "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", - "tool_version": null, - "type": "parameter_input", - "uuid": "38438918-1248-4256-bf36-c59be3db506f", + "post_job_actions": { + "ChangeDatatypeActionout_file1": { + "action_arguments": { + "newtype": "fasta" + }, + "action_type": "ChangeDatatypeAction", + "output_name": "out_file1" + } + }, + "tool_id": "Grep1", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"invert\": \"\", \"keep_header\": false, \"pattern\": \"^chr([0-9A-Za-z])+\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.4", + "type": "tool", + "uuid": "b43503bf-f391-4d3b-b355-61eea41b03af", "when": null, "workflow_outputs": [] }, - "15": { - "annotation": "Bakta Database - ideally use the newest installed on the server", - "content_id": null, + "18": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.2", "errors": null, - "id": 15, - "input_connections": {}, - "inputs": [ + "id": 18, + "input_connections": { + "input_collection": { + "id": 3, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Extract element identifiers", + "outputs": [ { - "description": "Bakta Database - ideally use the newest installed on the server", - "name": "Bakta Database" + "name": "output", + "type": "txt" } ], - "label": "Bakta Database", - "name": "Input parameter", - "outputs": [], "position": { - "left": 10293.210108019277, - "top": 657.0083585736907 + "left": 710.8843263011966, + "top": 450.83742320735155 }, - "tool_id": null, - "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", - "tool_version": null, - "type": "parameter_input", - "uuid": "7a4f3e3f-be72-404c-aa3f-1eeca2963467", + "post_job_actions": {}, + "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_collection\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "0.0.2", + "type": "tool", + "uuid": "add7df81-4165-4ce7-88a5-6891b287decd", "when": null, "workflow_outputs": [] }, - "16": { - "annotation": "AMRFinderPlus Database for Bakta - ideally use the newest installed in the server", - "content_id": null, + "19": { + "annotation": "", + "content_id": "__APPLY_RULES__", "errors": null, - "id": 16, - "input_connections": {}, - "inputs": [ + "id": 19, + "input_connections": { + "input": { + "id": 3, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Apply rules", + "outputs": [ { - "description": "AMRFinderPlus Database for Bakta - ideally use the newest installed in the server", - "name": "AMRFinderPlus Database for Bakta" + "name": "output", + "type": "input" } ], - "label": "AMRFinderPlus Database for Bakta", - "name": "Input parameter", - "outputs": [], "position": { - "left": 10310.396550976655, - "top": 805.5241497596726 + "left": 1488.6067826520364, + "top": 270.41802882442556 }, - "tool_id": null, - "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", - "tool_version": null, - "type": "parameter_input", - "uuid": "ac4febf2-2c33-480e-9906-4e5bd3ad38ff", + "post_job_actions": {}, + "tool_id": "__APPLY_RULES__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"rules\": {\"mapping\": [{\"columns\": [0, 2], \"editing\": false, \"type\": \"list_identifiers\"}, {\"columns\": [1], \"type\": \"paired_identifier\"}], \"rules\": [{\"error\": null, \"type\": \"add_column_metadata\", \"value\": \"identifier0\", \"warn\": null}, {\"error\": null, \"type\": \"add_column_metadata\", \"value\": \"identifier1\", \"warn\": null}, {\"error\": null, \"type\": \"add_column_metadata\", \"value\": \"identifier0\", \"warn\": null}]}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "fe5661cc-ddab-40e6-be50-2daf546202eb", "when": null, "workflow_outputs": [] }, - "17": { + "20": { "annotation": "", "content_id": "__UNZIP_COLLECTION__", "errors": null, - "id": 17, + "id": 20, "input_connections": { "input": { - "id": 0, + "id": 3, "output_name": "output" } }, @@ -690,25 +936,26 @@ ], "position": { "left": 1764.9952946263793, - "top": 2052.3691306510445 + "top": 2628.8691306510445 }, "post_job_actions": {}, "tool_id": "__UNZIP_COLLECTION__", "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.0.0", "type": "tool", - "uuid": "5211717b-c58b-4456-b7d7-6c27b26f4e65", + "uuid": "f2577db4-191e-4b24-bf94-96b2cde4c49f", "when": null, "workflow_outputs": [] }, - "18": { + "21": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/map_param_value/map_param_value/0.2.0", "errors": null, - "id": 18, + "id": 21, "input_connections": { "input_param_type|input_param": { - "id": 2, + "id": 4, "output_name": "output" } }, @@ -728,7 +975,7 @@ ], "position": { "left": 1420.1101876476544, - "top": 1236.3653835002958 + "top": 1812.8653835002958 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/map_param_value/map_param_value/0.2.0", @@ -739,20 +986,21 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"input_param_type\": {\"type\": \"text\", \"__current_case__\": 0, \"input_param\": {\"__class__\": \"ConnectedValue\"}, \"mappings\": [{\"__index__\": 0, \"from\": \"MEGAHIT\", \"to\": \"True\"}]}, \"output_param_type\": \"boolean\", \"unmapped\": {\"on_unmapped\": \"default\", \"__current_case__\": 2, \"default_value\": \"False\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "0.2.0", "type": "tool", - "uuid": "7757e8dc-0b81-46a6-9ac0-08097b99ea2d", + "uuid": "f9490006-a893-4c40-beb1-618b9da2b48c", "when": null, "workflow_outputs": [] }, - "19": { + "22": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/map_param_value/map_param_value/0.2.0", "errors": null, - "id": 19, + "id": 22, "input_connections": { "input_param_type|input_param": { - "id": 2, + "id": 4, "output_name": "output" } }, @@ -772,7 +1020,7 @@ ], "position": { "left": 1644.1681192380715, - "top": 1054.2515184985184 + "top": 1630.7515184985184 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/map_param_value/map_param_value/0.2.0", @@ -783,28 +1031,63 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"input_param_type\": {\"type\": \"text\", \"__current_case__\": 0, \"input_param\": {\"__class__\": \"ConnectedValue\"}, \"mappings\": [{\"__index__\": 0, \"from\": \"metaSPAdes\", \"to\": \"True\"}]}, \"output_param_type\": \"boolean\", \"unmapped\": {\"on_unmapped\": \"default\", \"__current_case__\": 2, \"default_value\": \"False\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "0.2.0", "type": "tool", - "uuid": "6c8d8774-7692-4fec-8761-beba4e77902f", + "uuid": "50a64deb-c659-4afe-a0ce-5386ef7e768c", "when": null, "workflow_outputs": [] }, - "20": { + "23": { + "annotation": "", + "content_id": "wc_gnu", + "errors": null, + "id": 23, + "input_connections": { + "input1": { + "id": 18, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Line/Word/Character count", + "outputs": [ + { + "name": "out_file1", + "type": "tabular" + } + ], + "position": { + "left": 942.5923958844637, + "top": 485.1759311542751 + }, + "post_job_actions": {}, + "tool_id": "wc_gnu", + "tool_state": "{\"include_header\": false, \"input1\": {\"__class__\": \"ConnectedValue\"}, \"options\": [\"lines\"], \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.0", + "type": "tool", + "uuid": "d4071c23-5da3-44b2-a4ca-0b4e8f37bc2f", + "when": null, + "workflow_outputs": [] + }, + "24": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/megahit/megahit/1.2.9+galaxy2", "errors": null, - "id": 20, + "id": 24, "input_connections": { "input_option|batchmode|pair_input": { - "id": 0, + "id": 3, "output_name": "output" }, "output_section|min_contig_len": { - "id": 3, + "id": 6, "output_name": "output" }, "when": { - "id": 18, + "id": 21, "output_name": "output_param_boolean" } }, @@ -824,7 +1107,7 @@ ], "position": { "left": 1925.774111534121, - "top": 1414.8823511387398 + "top": 1991.3823511387398 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/megahit/megahit/1.2.9+galaxy2", @@ -835,192 +1118,461 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"advanced_section\": {\"nomercy\": false, \"bubble_level\": \"2\", \"merge_level\": \"20,0.95\", \"prune_level\": \"2\", \"prune_depth\": \"2\", \"disconnect_ratio\": \"0.1\", \"low_local_ratio\": \"0.2\", \"cleaning_rounds\": \"5\", \"nolocal\": false, \"kmin1pass\": false}, \"basic_section\": {\"min_count\": \"2\", \"k_mer\": {\"k_mer_method\": \"klist_method\", \"__current_case__\": 0, \"k_list\": \"21,29,39,59,79,99,119,141\"}}, \"input_option\": {\"choice\": \"paired_collection\", \"__current_case__\": 3, \"batchmode\": {\"processmode\": \"individual\", \"__current_case__\": 0, \"pair_input\": {\"__class__\": \"ConnectedValue\"}}}, \"output_section\": {\"min_contig_len\": {\"__class__\": \"ConnectedValue\"}, \"show_intermediate_contigs\": false, \"log_file\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.2.9+galaxy2", "type": "tool", - "uuid": "44d90a40-131b-43a5-b579-d6495825f7c3", + "uuid": "5d701b6a-aa66-4765-acae-f45e4d1a37de", "when": "$(inputs.when)", "workflow_outputs": [] }, - "21": { - "annotation": "metaSPAdes performs co-assembly on default if multiple samples are supplied. This sub-WF allows running it individually.", - "id": 21, + "25": { + "annotation": "", + "content_id": "param_value_from_file", + "errors": null, + "id": 25, "input_connections": { - "0:Input dataset collection": { - "id": 0, - "input_subworkflow_step_id": 0, + "input1": { + "id": 23, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": null, + "name": "Parse parameter value", + "outputs": [ + { + "name": "integer_param", + "type": "expression.json" + } + ], + "position": { + "left": 1178.228727342863, + "top": 560.5040898740183 + }, + "post_job_actions": {}, + "tool_id": "param_value_from_file", + "tool_state": "{\"input1\": {\"__class__\": \"ConnectedValue\"}, \"param_type\": \"integer\", \"remove_newlines\": true, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "0.1.0", + "type": "tool", + "uuid": "9d44fb56-c36a-436e-9d9a-b23f4f4b9201", + "when": null, + "workflow_outputs": [] + }, + "26": { + "annotation": "", + "content_id": "__DUPLICATE_FILE_TO_COLLECTION__", + "errors": null, + "id": 26, + "input_connections": { + "input": { + "id": 17, + "output_name": "out_file1" + }, + "number": { + "id": 25, + "output_name": "integer_param" + } + }, + "inputs": [], + "label": null, + "name": "Duplicate file to collection", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 1331.0056168132862, + "top": 789.2607485830649 + }, + "post_job_actions": {}, + "tool_id": "__DUPLICATE_FILE_TO_COLLECTION__", + "tool_state": "{\"element_identifier\": null, \"input\": {\"__class__\": \"ConnectedValue\"}, \"number\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.0", + "type": "tool", + "uuid": "a046475d-fd0d-4e07-b3c0-b227500d60fd", + "when": null, + "workflow_outputs": [] + }, + "27": { + "annotation": "", + "content_id": "__RELABEL_FROM_FILE__", + "errors": null, + "id": 27, + "input_connections": { + "how|labels": { + "id": 18, "output_name": "output" }, - "when": { + "input": { + "id": 26, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Relabel identifiers", + "name": "how" + } + ], + "label": null, + "name": "Relabel identifiers", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 1551.1625127487957, + "top": 960.6540486623608 + }, + "post_job_actions": {}, + "tool_id": "__RELABEL_FROM_FILE__", + "tool_state": "{\"how\": {\"how_select\": \"txt\", \"__current_case__\": 0, \"labels\": {\"__class__\": \"ConnectedValue\"}, \"strict\": false}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "3eb4cae2-7ba2-43a4-bcdb-4bf8251c3322", + "when": null, + "workflow_outputs": [] + }, + "28": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/pick_value/pick_value/0.2.0", + "errors": null, + "id": 28, + "input_connections": { + "style_cond|type_cond|pick_from_0|value": { + "id": 1, + "output_name": "output" + }, + "style_cond|type_cond|pick_from_1|value": { + "id": 27, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Pick parameter value", + "outputs": [ + { + "name": "data_param", + "type": "input" + } + ], + "position": { + "left": 1801.884652276902, + "top": 1064.8709731427205 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/pick_value/pick_value/0.2.0", + "tool_shed_repository": { + "changeset_revision": "b19e21af9c52", + "name": "pick_value", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"style_cond\": {\"pick_style\": \"first\", \"__current_case__\": 0, \"type_cond\": {\"param_type\": \"data\", \"__current_case__\": 4, \"pick_from\": [{\"__index__\": 0, \"value\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 1, \"value\": {\"__class__\": \"ConnectedValue\"}}]}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "0.2.0", + "type": "tool", + "uuid": "73112e61-bf9d-4982-a5a1-1d418b0cb0bc", + "when": null, + "workflow_outputs": [] + }, + "29": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/pick_value/pick_value/0.2.0", + "errors": null, + "id": 29, + "input_connections": { + "style_cond|type_cond|pick_from_0|value": { + "id": 2, + "output_name": "output" + }, + "style_cond|type_cond|pick_from_1|value": { + "id": 27, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Pick parameter value", + "outputs": [ + { + "name": "data_param", + "type": "input" + } + ], + "position": { + "left": 1810.9837913771769, + "top": 1293.786856484931 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/pick_value/pick_value/0.2.0", + "tool_shed_repository": { + "changeset_revision": "b19e21af9c52", + "name": "pick_value", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"style_cond\": {\"pick_style\": \"first\", \"__current_case__\": 0, \"type_cond\": {\"param_type\": \"data\", \"__current_case__\": 4, \"pick_from\": [{\"__index__\": 0, \"value\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 1, \"value\": {\"__class__\": \"ConnectedValue\"}}]}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "0.2.0", + "type": "tool", + "uuid": "09221b89-442c-48d7-b0f5-31d7a1cdc09f", + "when": null, + "workflow_outputs": [] + }, + "30": { + "annotation": "", + "content_id": "__APPLY_RULES__", + "errors": null, + "id": 30, + "input_connections": { + "input": { + "id": 28, + "output_name": "data_param" + } + }, + "inputs": [], + "label": null, + "name": "Apply rules", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 1820.1044060343454, + "top": 739.1220032064418 + }, + "post_job_actions": {}, + "tool_id": "__APPLY_RULES__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"rules\": {\"mapping\": [{\"columns\": [0, 1], \"editing\": false, \"type\": \"list_identifiers\"}], \"rules\": [{\"error\": null, \"type\": \"add_column_metadata\", \"value\": \"identifier0\", \"warn\": null}, {\"error\": null, \"type\": \"add_column_metadata\", \"value\": \"identifier0\", \"warn\": null}]}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "218a12db-5899-4b27-99d5-6df9c1fcf269", + "when": null, + "workflow_outputs": [] + }, + "31": { + "annotation": "", + "content_id": "__APPLY_RULES__", + "errors": null, + "id": 31, + "input_connections": { + "input": { + "id": 29, + "output_name": "data_param" + } + }, + "inputs": [], + "label": null, + "name": "Apply rules", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2134.060421098393, + "top": 1147.8051656181005 + }, + "post_job_actions": {}, + "tool_id": "__APPLY_RULES__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"rules\": {\"mapping\": [{\"columns\": [0, 1], \"editing\": false, \"type\": \"list_identifiers\"}], \"rules\": [{\"error\": null, \"type\": \"add_column_metadata\", \"value\": \"identifier0\", \"warn\": null}, {\"error\": null, \"type\": \"add_column_metadata\", \"value\": \"identifier0\", \"warn\": null}]}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "bf026b3d-0759-4299-b14a-f0257ec724ac", + "when": null, + "workflow_outputs": [] + }, + "32": { + "annotation": "", + "content_id": "__FILTER_EMPTY_DATASETS__", + "errors": null, + "id": 32, + "input_connections": { + "input": { + "id": 30, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter empty datasets", + "name": "replacement" + } + ], + "label": null, + "name": "Filter empty datasets", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2054.5621147830534, + "top": 510.9059064040648 + }, + "post_job_actions": {}, + "tool_id": "__FILTER_EMPTY_DATASETS__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "58d0e8fd-3fa9-4b5e-a6d1-105feef13410", + "when": null, + "workflow_outputs": [] + }, + "33": { + "annotation": "", + "content_id": "__FILTER_EMPTY_DATASETS__", + "errors": null, + "id": 33, + "input_connections": { + "input": { + "id": 31, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter empty datasets", + "name": "replacement" + } + ], + "label": null, + "name": "Filter empty datasets", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2282.421935904985, + "top": 887.9521652881248 + }, + "post_job_actions": {}, + "tool_id": "__FILTER_EMPTY_DATASETS__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "c12f0dce-4d8a-4338-a6cf-26c8107e2ac1", + "when": null, + "workflow_outputs": [] + }, + "34": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/nml/metaspades/metaspades/4.2.0+galaxy0", + "errors": null, + "id": 34, + "input_connections": { + "arf|nanopore": { + "id": 32, + "output_name": "output" + }, + "arf|pacbio": { + "id": 33, + "output_name": "output" + }, + "singlePaired|input": { "id": 19, + "output_name": "output" + }, + "when": { + "id": 22, "output_name": "output_param_boolean" } }, "inputs": [ { - "description": "metaSPAdes performs co-assembly on default if multiple samples are supplied. This sub-WF allows running it individually.", - "name": "Run metaSPAdes in individual assembly mode" + "description": "runtime parameter for tool metaSPAdes", + "name": "arf" + }, + { + "description": "runtime parameter for tool metaSPAdes", + "name": "arf" + }, + { + "description": "runtime parameter for tool metaSPAdes", + "name": "singlePaired" + } + ], + "label": null, + "name": "metaSPAdes", + "outputs": [ + { + "name": "out_ag", + "type": "fastg" + }, + { + "name": "out_ags", + "type": "txt" + }, + { + "name": "out_cn", + "type": "fasta" + }, + { + "name": "out_sc", + "type": "fasta" } ], - "label": "Run metaSPAdes in individual assembly mode", - "name": "Maping over metaSPAdes", - "outputs": [], "position": { - "left": 1934.4807239580614, - "top": 1197.348664810898 - }, - "subworkflow": { - "a_galaxy_workflow": "true", - "annotation": "", - "comments": [], - "format-version": "0.1", - "name": "Maping over metaSPAdes", - "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": "", - "content_id": null, - "errors": null, - "id": 0, - "input_connections": {}, - "inputs": [], - "label": null, - "name": "Input dataset collection", - "outputs": [], - "position": { - "left": 0, - "top": 23.536895751953125 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null}", - "tool_version": null, - "type": "data_collection_input", - "uuid": "a5f4b07b-c477-425d-93ec-80d286536552", - "when": null, - "workflow_outputs": [] - }, - "1": { - "annotation": "", - "content_id": "__APPLY_RULES__", - "errors": null, - "id": 1, - "input_connections": { - "input": { - "id": 0, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "Apply rules", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 304.36083984375, - "top": 14.54541015625 - }, - "post_job_actions": {}, - "tool_id": "__APPLY_RULES__", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"rules\": {\"mapping\": [{\"columns\": [0, 1], \"editing\": false, \"type\": \"list_identifiers\"}, {\"columns\": [2], \"type\": \"paired_identifier\"}], \"rules\": [{\"error\": null, \"type\": \"add_column_metadata\", \"value\": \"identifier0\", \"warn\": null}, {\"error\": null, \"type\": \"add_column_metadata\", \"value\": \"identifier1\", \"warn\": null}, {\"error\": null, \"target_column\": 0, \"type\": \"add_column_basename\", \"warn\": null}, {\"error\": null, \"target_column_0\": 1, \"target_column_1\": 2, \"type\": \"swap_columns\", \"warn\": null}]}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.1.0", - "type": "tool", - "uuid": "a77ca292-7af9-48dc-80d8-2a1adb177509", - "when": null, - "workflow_outputs": [] - }, - "2": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/nml/metaspades/metaspades/4.2.0+galaxy0", - "errors": null, - "id": 2, - "input_connections": { - "singlePaired|input": { - "id": 1, - "output_name": "output" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool metaSPAdes", - "name": "singlePaired" - } - ], - "label": null, - "name": "metaSPAdes", - "outputs": [ - { - "name": "out_ag", - "type": "fastg" - }, - { - "name": "out_ags", - "type": "txt" - }, - { - "name": "out_cn", - "type": "fasta" - }, - { - "name": "out_sc", - "type": "fasta" - } - ], - "position": { - "left": 606.178955078125, - "top": 0 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/metaspades/metaspades/4.2.0+galaxy0", - "tool_shed_repository": { - "changeset_revision": "f192c2fbe13f", - "name": "metaspades", - "owner": "nml", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"__input_ext\": \"input\", \"additional_reads\": {\"selector\": \"false\", \"__current_case__\": 1}, \"arf\": {\"nanopore\": null, \"pacbio\": null}, \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"kmer_cond\": {\"kmer_sel\": \"auto\", \"__current_case__\": 0}, \"library_number\": \"true\", \"mode_sel\": null, \"optional_output\": [\"ag\", \"ags\", \"cn\", \"sc\"], \"phred_offset\": \"auto\", \"singlePaired\": {\"sPaired\": \"paired_collection\", \"__current_case__\": 1, \"input\": {\"__class__\": \"ConnectedValue\"}, \"type_paired\": \"pe\", \"orientation\": \"fr\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_version": "4.2.0+galaxy0", - "type": "tool", - "uuid": "a0046a69-6ed4-4287-aabb-c36d5f47fe0b", - "when": null, - "workflow_outputs": [ - { - "label": "out_cn", - "output_name": "out_cn", - "uuid": "33e551dd-e82a-4b24-8b40-5d3a099a6422" - } - ] - } - }, - "tags": [], - "uuid": "0a6e1897-2dec-470f-86ba-7d83f96fec91" + "left": 2432.606026763842, + "top": 360.6699474951481 }, - "tool_id": null, - "type": "subworkflow", - "uuid": "11245b16-9627-4acc-831a-6147c3f222b4", + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/metaspades/metaspades/4.2.0+galaxy0", + "tool_shed_repository": { + "changeset_revision": "f192c2fbe13f", + "name": "metaspades", + "owner": "nml", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"additional_reads\": {\"selector\": \"false\", \"__current_case__\": 1}, \"arf\": {\"nanopore\": {\"__class__\": \"ConnectedValue\"}, \"pacbio\": {\"__class__\": \"ConnectedValue\"}}, \"kmer_cond\": {\"kmer_sel\": \"auto\", \"__current_case__\": 0}, \"library_number\": \"true\", \"mode_sel\": null, \"optional_output\": [\"ag\", \"ags\", \"cn\", \"sc\"], \"phred_offset\": \"auto\", \"singlePaired\": {\"sPaired\": \"paired_collection\", \"__current_case__\": 1, \"input\": {\"__class__\": \"ConnectedValue\"}, \"type_paired\": \"pe\", \"orientation\": \"fr\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "4.2.0+galaxy0", + "type": "tool", + "uuid": "d33fa5fb-26ef-431a-b9fe-9b6f0b76d707", "when": "$(inputs.when)", - "workflow_outputs": [] + "workflow_outputs": [ + { + "label": "out cn", + "output_name": "out_cn", + "uuid": "acb7a366-6a00-4ef0-a17f-6b556eadb555" + } + ] }, - "22": { + "35": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/pick_value/pick_value/0.2.0", "errors": null, - "id": 22, + "id": 35, "input_connections": { "style_cond|type_cond|pick_from_0|value": { - "id": 21, + "id": 34, "output_name": "out_cn" }, "style_cond|type_cond|pick_from_1|value": { - "id": 20, + "id": 24, "output_name": "output" }, "style_cond|type_cond|pick_from_2|value": { - "id": 4, + "id": 7, "output_name": "output" } }, @@ -1035,7 +1587,7 @@ ], "position": { "left": 2250.260442799615, - "top": 1327.794863797815 + "top": 1904.294863797815 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/pick_value/pick_value/0.2.0", @@ -1046,28 +1598,29 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"style_cond\": {\"pick_style\": \"first\", \"__current_case__\": 0, \"type_cond\": {\"param_type\": \"data\", \"__current_case__\": 4, \"pick_from\": [{\"__index__\": 0, \"value\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 1, \"value\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 2, \"value\": {\"__class__\": \"ConnectedValue\"}}]}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "0.2.0", "type": "tool", - "uuid": "936829be-fbe0-4045-92f5-d63c8d3bd146", + "uuid": "9ac1add7-a273-4110-a90a-424139348358", "when": null, "workflow_outputs": [] }, - "23": { + "36": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/quast/quast/5.3.0+galaxy1", "errors": null, - "id": 23, + "id": 36, "input_connections": { "mode|in|inputs": { - "id": 22, + "id": 35, "output_name": "data_param" }, "mode|reads|input_1": { - "id": 17, + "id": 20, "output_name": "forward" }, "mode|reads|input_2": { - "id": 17, + "id": 20, "output_name": "reverse" } }, @@ -1102,7 +1655,7 @@ ], "position": { "left": 2194.0226523206475, - "top": 1955.4029316870985 + "top": 2531.9029316870983 }, "post_job_actions": { "TagDatasetActionmetrics_tabular": { @@ -1121,30 +1674,31 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"advanced\": {\"contig_thresholds\": \"0,1000\", \"strict_NA\": false, \"extensive_mis_size\": \"1000\", \"scaffold_gap_max_size\": \"1000\", \"unaligned_part_size\": \"500\", \"skip_unaligned_mis_contigs\": true, \"fragmented_max_indent\": null, \"report_all_metrics\": false, \"x_for_Nx\": \"90\"}, \"alignments\": {\"use_all_alignments\": false, \"min_alignment\": \"65\", \"ambiguity_usage\": \"one\", \"ambiguity_score\": \"0.99\", \"fragmented\": false, \"upper_bound_assembly\": false, \"upper_bound_min_con\": null, \"local_mis_size\": \"200\"}, \"assembly\": {\"type\": \"metagenome\", \"__current_case__\": 1, \"ref\": {\"origin\": \"silva\", \"__current_case__\": 0, \"max_ref_num\": \"0\"}, \"reuse_combined_alignments\": false, \"min_identity\": \"90.0\"}, \"genes\": {\"gene_finding\": {\"tool\": \"none\", \"__current_case__\": 0}, \"rna_finding\": false, \"conserved_genes_finding\": false}, \"large\": false, \"min_contig\": \"500\", \"mode\": {\"mode\": \"individual\", \"__current_case__\": 0, \"in\": {\"custom\": \"false\", \"__current_case__\": 1, \"inputs\": {\"__class__\": \"ConnectedValue\"}}, \"reads\": {\"reads_option\": \"paired\", \"__current_case__\": 2, \"input_1\": {\"__class__\": \"ConnectedValue\"}, \"input_2\": {\"__class__\": \"ConnectedValue\"}}}, \"output_files\": [\"html\", \"pdf\", \"tabular\", \"log\", \"summary\", \"krona\"], \"split_scaffolds\": false, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "5.3.0+galaxy1", "type": "tool", - "uuid": "d35aecec-533b-4f32-b3d0-689b4efee819", + "uuid": "c6d31f00-61d4-4bbd-a6aa-28c5a207909d", "when": null, "workflow_outputs": [ { "label": "Assembly Report", "output_name": "report_html_meta", - "uuid": "07e55845-7f25-471b-b26c-b8241967ae01" + "uuid": "45350d2f-df38-4f83-b60d-c9689dd9e04e" } ] }, - "24": { + "37": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/devteam/bowtie2/bowtie2/2.5.4+galaxy0", "errors": null, - "id": 24, + "id": 37, "input_connections": { "library|input_1": { - "id": 0, + "id": 3, "output_name": "output" }, "reference_genome|own_file": { - "id": 22, + "id": 35, "output_name": "data_param" } }, @@ -1172,7 +1726,7 @@ ], "position": { "left": 2176.40220510254, - "top": 2939.8820690173548 + "top": 3516.3820690173548 }, "post_job_actions": { "HideDatasetActionoutput": { @@ -1189,20 +1743,21 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"__input_ext\": \"input\", \"analysis_type\": {\"analysis_type_selector\": \"simple\", \"__current_case__\": 0, \"presets\": \"no_presets\"}, \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"library\": {\"type\": \"paired_collection\", \"__current_case__\": 1, \"input_1\": {\"__class__\": \"ConnectedValue\"}, \"unaligned_file\": false, \"aligned_file\": false, \"paired_options\": {\"paired_options_selector\": \"no\", \"__current_case__\": 1}}, \"own_file|__identifier__\": \"ERR2231567.fastqsanger\", \"reference_genome\": {\"source\": \"history\", \"__current_case__\": 1, \"own_file\": {\"__class__\": \"ConnectedValue\"}}, \"rg\": {\"rg_selector\": \"do_not_set\", \"__current_case__\": 3}, \"sam_options\": {\"sam_options_selector\": \"no\", \"__current_case__\": 1}, \"save_mapping_stats\": true, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "2.5.4+galaxy0", "type": "tool", - "uuid": "e41a21d2-91c7-42e3-8072-e254280733ab", + "uuid": "2edf8b99-5852-45fb-918f-c57d66b7797a", "when": null, "workflow_outputs": [] }, - "25": { + "38": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/concoct_cut_up_fasta/concoct_cut_up_fasta/1.1.0+galaxy2", "errors": null, - "id": 25, + "id": 38, "input_connections": { "input_fasta": { - "id": 22, + "id": 35, "output_name": "data_param" } }, @@ -1221,7 +1776,7 @@ ], "position": { "left": 4564.40317293072, - "top": 3558.6111663214438 + "top": 4135.111166321443 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/concoct_cut_up_fasta/concoct_cut_up_fasta/1.1.0+galaxy2", @@ -1232,20 +1787,21 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"__input_ext\": \"input\", \"bedfile\": true, \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"chunk_size\": \"10000\", \"input_fasta\": {\"__class__\": \"ConnectedValue\"}, \"input_fasta|__identifier__\": \"ERR2231567.fastqsanger\", \"merge_last\": true, \"overlap_size\": \"0\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.1.0+galaxy2", "type": "tool", - "uuid": "3d11cf76-8a00-4aab-8cee-14647ad02165", + "uuid": "85e585b4-edbd-4222-93f6-de3c7f41e757", "when": null, "workflow_outputs": [] }, - "26": { + "39": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/devteam/samtools_sort/samtools_sort/2.0.7", "errors": null, - "id": 26, + "id": 39, "input_connections": { "input1": { - "id": 24, + "id": 37, "output_name": "output" } }, @@ -1260,7 +1816,7 @@ ], "position": { "left": 2199.953718774415, - "top": 3254.1147350329798 + "top": 3830.6147350329798 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/samtools_sort/samtools_sort/2.0.7", @@ -1271,28 +1827,29 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"input1\": {\"__class__\": \"ConnectedValue\"}, \"input1|__identifier__\": \"ERR2231567.fastqsanger\", \"minhash\": false, \"prim_key_cond\": {\"prim_key_select\": \"\", \"__current_case__\": 0}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "2.0.7", "type": "tool", - "uuid": "863d5ee6-9eb0-4ac7-a634-9e258807f8cb", + "uuid": "18477e83-a7e3-45ce-829a-711506c83273", "when": null, "workflow_outputs": [] }, - "27": { + "40": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/semibin/semibin/2.1.0+galaxy1", "errors": null, - "id": 27, + "id": 40, "input_connections": { "mode|environment": { - "id": 5, + "id": 8, "output_name": "output" }, "mode|input_bam": { - "id": 26, + "id": 39, "output_name": "output1" }, "mode|input_fasta": { - "id": 22, + "id": 35, "output_name": "data_param" } }, @@ -1310,7 +1867,7 @@ "name": "mode" } ], - "label": null, + "label": "SemiBin latest", "name": "SemiBin", "outputs": [ { @@ -1335,8 +1892,8 @@ } ], "position": { - "left": 3418.96128713379, - "top": 2998.3409313220423 + "left": 4701.336558095688, + "top": 1067.8572682717747 }, "post_job_actions": { "TagDatasetActionoutput_bins": { @@ -1355,20 +1912,21 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"annot\": {\"ml_threshold\": null}, \"bin\": {\"max_node\": \"1.0\", \"max_edges\": \"200\", \"minfasta_kbs\": \"200\"}, \"extra_output\": [\"data\", \"coverage\"], \"min_len\": {\"method\": \"automatic\", \"__current_case__\": 0}, \"mode\": {\"select\": \"single\", \"__current_case__\": 0, \"input_fasta\": {\"__class__\": \"ConnectedValue\"}, \"input_bam\": {\"__class__\": \"ConnectedValue\"}, \"ref\": {\"select\": \"ml\", \"__current_case__\": 2}, \"environment\": {\"__class__\": \"ConnectedValue\"}}, \"orf_finder\": \"fast-naive\", \"random_seed\": \"0\", \"training\": {\"epoches\": \"20\", \"batch_size\": \"2048\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "2.1.0+galaxy1", "type": "tool", - "uuid": "6fd5ada8-8884-4988-a895-a6c41172022d", + "uuid": "da649137-0c3b-4545-ba6a-13de26f1a156", "when": null, "workflow_outputs": [] }, - "28": { + "41": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/metabat2_jgi_summarize_bam_contig_depths/metabat2_jgi_summarize_bam_contig_depths/2.17+galaxy0", "errors": null, - "id": 28, + "id": 41, "input_connections": { "mode|bam_indiv_input": { - "id": 26, + "id": 39, "output_name": "output1" } }, @@ -1388,7 +1946,7 @@ ], "position": { "left": 3472.136335961915, - "top": 3418.2558483142298 + "top": 3994.7558483142298 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/metabat2_jgi_summarize_bam_contig_depths/metabat2_jgi_summarize_bam_contig_depths/2.17+galaxy0", @@ -1399,24 +1957,59 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"__input_ext\": \"input\", \"advanced\": {\"percentIdentity\": \"97\", \"output_paired_contigs\": false, \"noIntraDepthVariance\": false, \"showDepth\": false, \"minMapQual\": \"0\", \"weightMapQual\": \"0.0\", \"includeEdgeBases\": false, \"maxEdgeBases\": \"75\"}, \"bam_indiv_input|__identifier__\": \"ERR2231567.fastqsanger\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"mode\": {\"type\": \"individual\", \"__current_case__\": 0, \"bam_indiv_input\": {\"__class__\": \"ConnectedValue\"}, \"use_reference_cond\": {\"use_reference\": \"no\", \"__current_case__\": 0}}, \"shredding\": {\"shredLength\": \"16000\", \"shredDepth\": \"5\", \"minContigLength\": \"1\", \"minContigDepth\": \"0.0\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "2.17+galaxy0", "type": "tool", - "uuid": "99aabfaa-9e98-45e2-83f7-3009b959603d", + "uuid": "cf567963-cd6b-453e-86af-756d4ecafe9b", "when": null, "workflow_outputs": [] }, - "29": { + "42": { + "annotation": "", + "content_id": "__APPLY_RULES__", + "errors": null, + "id": 42, + "input_connections": { + "input": { + "id": 39, + "output_name": "output1" + } + }, + "inputs": [], + "label": null, + "name": "Apply rules", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 4616.55818883981, + "top": 3800.5427445388827 + }, + "post_job_actions": {}, + "tool_id": "__APPLY_RULES__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"rules\": {\"mapping\": [{\"columns\": [0, 1], \"editing\": false, \"type\": \"list_identifiers\"}], \"rules\": [{\"error\": null, \"type\": \"add_column_metadata\", \"value\": \"identifier0\", \"warn\": null}, {\"error\": null, \"type\": \"add_column_metadata\", \"value\": \"identifier0\", \"warn\": null}]}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "7b811cdd-63ad-4a6f-9f01-5430f167e69b", + "when": null, + "workflow_outputs": [] + }, + "43": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/concoct_coverage_table/concoct_coverage_table/1.1.0+galaxy2", "errors": null, - "id": 29, + "id": 43, "input_connections": { "bedfile": { - "id": 25, + "id": 38, "output_name": "output_bed" }, "mode|bamfile": { - "id": 26, + "id": 39, "output_name": "output1" } }, @@ -1436,7 +2029,7 @@ ], "position": { "left": 4728.636419405139, - "top": 3740.9829733730426 + "top": 4317.482973373042 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/concoct_coverage_table/concoct_coverage_table/1.1.0+galaxy2", @@ -1447,20 +2040,21 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"__input_ext\": \"input\", \"bedfile\": {\"__class__\": \"ConnectedValue\"}, \"bedfile|__identifier__\": \"ERR2231567.fastqsanger\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"mode\": {\"type\": \"individual\", \"__current_case__\": 0, \"bamfile\": {\"__class__\": \"ConnectedValue\"}}, \"mode|bamfile|__identifier__\": \"ERR2231567.fastqsanger\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.1.0+galaxy2", "type": "tool", - "uuid": "11dcb0bb-7626-4c97-a15c-0366194f1cea", + "uuid": "30bbc498-8cf1-45e5-982b-120fb94771b3", "when": null, "workflow_outputs": [] }, - "30": { + "44": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/fasta_to_contig2bin/Fasta_to_Contig2Bin/1.1.7+galaxy1", "errors": null, - "id": 30, + "id": 44, "input_connections": { "inputs": { - "id": 27, + "id": 40, "output_name": "output_bins" } }, @@ -1474,8 +2068,8 @@ } ], "position": { - "left": 5837.466317415978, - "top": 1321.6059602585415 + "left": 5834.275585758556, + "top": 2214.374454682633 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/fasta_to_contig2bin/Fasta_to_Contig2Bin/1.1.7+galaxy1", @@ -1486,24 +2080,25 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"inputs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.1.7+galaxy1", "type": "tool", - "uuid": "9a7aa4f6-b60b-4415-a1a4-73cf829ec2c3", + "uuid": "e43e1fee-f2a8-403c-8668-d52a47ec0da2", "when": null, "workflow_outputs": [] }, - "31": { + "45": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/mbernt/maxbin2/maxbin2/2.2.7+galaxy6", "errors": null, - "id": 31, + "id": 45, "input_connections": { "assembly|inputs|abund": { - "id": 28, + "id": 41, "output_name": "outputDepth" }, "contig": { - "id": 22, + "id": 35, "output_name": "data_param" } }, @@ -1546,7 +2141,7 @@ ], "position": { "left": 4933.920371630858, - "top": 2001.9496882015278 + "top": 2578.449688201528 }, "post_job_actions": { "TagDatasetActionbins": { @@ -1565,24 +2160,25 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"adv\": {\"min_contig_length\": \"1000\", \"max_iteration\": \"50\", \"prob_threshold\": \"0.5\"}, \"assembly\": {\"type\": \"individual\", \"__current_case__\": 0, \"inputs\": {\"type\": \"abund\", \"__current_case__\": 1, \"abund\": {\"__class__\": \"ConnectedValue\"}}}, \"contig\": {\"__class__\": \"ConnectedValue\"}, \"output\": {\"plotmarker\": true, \"marker\": true, \"markers\": true, \"log\": true, \"markerset\": \"107\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "2.2.7+galaxy6", "type": "tool", - "uuid": "c3282b9b-30ec-4e23-9859-5931275f7fdf", + "uuid": "066b1c8e-c08b-4ab4-9aba-e207b497b3d4", "when": null, "workflow_outputs": [] }, - "32": { + "46": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/metabat2/metabat2/2.17+galaxy0", "errors": null, - "id": 32, + "id": 46, "input_connections": { "advanced|base_coverage_depth_cond|abdFile": { - "id": 28, + "id": 41, "output_name": "outputDepth" }, "inFile": { - "id": 22, + "id": 35, "output_name": "data_param" } }, @@ -1612,8 +2208,8 @@ } ], "position": { - "left": 4724.08263043162, - "top": 2555.3686420340914 + "left": 4759.686399665575, + "top": 3171.756882662073 }, "post_job_actions": { "TagDatasetActionbins": { @@ -1632,28 +2228,77 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"__input_ext\": \"input\", \"advanced\": {\"base_coverage_depth_cond\": {\"base_coverage_depth\": \"yes\", \"__current_case__\": 1, \"abdFile\": {\"__class__\": \"ConnectedValue\"}, \"cvExt\": null}, \"minContig\": \"1500\", \"maxP\": \"95\", \"minS\": \"60\", \"maxEdges\": \"200\", \"pTNF\": \"0\", \"noAdd\": false, \"minCV\": \"1.0\", \"minCVSum\": \"1.0\", \"seed\": \"0\"}, \"advanced|abdFile|__identifier__\": \"ERR2231567.fastqsanger\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"inFile\": {\"__class__\": \"ConnectedValue\"}, \"inFile|__identifier__\": \"ERR2231567.fastqsanger\", \"out\": {\"minClsSize\": \"200000\", \"onlyLabel\": false, \"saveCls\": false, \"extra_outputs\": [\"lowDepth\", \"tooShort\", \"unbinned\", \"log\"]}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "2.17+galaxy0", "type": "tool", - "uuid": "12715693-dcaa-4097-bd1e-61bfaa0fbe42", + "uuid": "935f5fc5-0eac-457b-803d-c376952b92b4", "when": null, "workflow_outputs": [] }, - "33": { + "47": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/comebin/comebin/1.0.4+galaxy1", + "errors": null, + "id": 47, + "input_connections": { + "assembly_file": { + "id": 35, + "output_name": "data_param" + }, + "bam_files": { + "id": 42, + "output_name": "output" + }, + "when": { + "id": 9, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "COMEBin", + "outputs": [ + { + "name": "bins", + "type": "input" + } + ], + "position": { + "left": 4959.9062874348965, + "top": 3724.828172607423 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/comebin/comebin/1.0.4+galaxy1", + "tool_shed_repository": { + "changeset_revision": "ddfb9c10740a", + "name": "comebin", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"assembly_file\": {\"__class__\": \"ConnectedValue\"}, \"bam_files\": {\"__class__\": \"ConnectedValue\"}, \"batch\": \"1024\", \"emb_comebin\": \"2048\", \"emb_cov\": \"2048\", \"learning\": \"6\", \"loss\": \"0.15\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.4+galaxy1", + "type": "tool", + "uuid": "60d8125c-7fd1-4a17-9bd0-364a2b8ddaa0", + "when": "$(inputs.when)", + "workflow_outputs": [] + }, + "48": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/concoct/concoct/1.1.0+galaxy2", "errors": null, - "id": 33, + "id": 48, "input_connections": { "advanced|read_length": { - "id": 8, + "id": 12, "output_name": "output" }, "composition_file": { - "id": 25, + "id": 38, "output_name": "output_fasta" }, "coverage_file": { - "id": 29, + "id": 43, "output_name": "output" } }, @@ -1681,7 +2326,7 @@ ], "position": { "left": 4984.910613418179, - "top": 3548.303730624489 + "top": 4124.80373062449 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/concoct/concoct/1.1.0+galaxy2", @@ -1692,20 +2337,21 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"advanced\": {\"clusters\": \"400\", \"kmer_length\": \"4\", \"length_threshold\": \"1000\", \"read_length\": {\"__class__\": \"ConnectedValue\"}, \"total_percentage_pca\": \"90\", \"seed\": \"1\", \"iterations\": \"500\", \"no_cov_normalization\": false}, \"composition_file\": {\"__class__\": \"ConnectedValue\"}, \"coverage_file\": {\"__class__\": \"ConnectedValue\"}, \"output\": {\"no_total_coverage\": false, \"converge_out\": false, \"log\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.1.0+galaxy2", "type": "tool", - "uuid": "f4094547-c644-4657-a908-25e789703384", + "uuid": "5c79063a-e04a-435c-9e32-432f5021b8b3", "when": null, "workflow_outputs": [] }, - "34": { + "49": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/fasta_to_contig2bin/Fasta_to_Contig2Bin/1.1.7+galaxy1", "errors": null, - "id": 34, + "id": 49, "input_connections": { "inputs": { - "id": 31, + "id": 45, "output_name": "bins" } }, @@ -1720,7 +2366,7 @@ ], "position": { "left": 5834.225343463908, - "top": 1189.573619164476 + "top": 1766.073619164476 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/fasta_to_contig2bin/Fasta_to_Contig2Bin/1.1.7+galaxy1", @@ -1731,20 +2377,21 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"inputs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.1.7+galaxy1", "type": "tool", - "uuid": "e7e5c640-78f8-4af4-b589-75cea9f5a7fa", + "uuid": "427310ac-9915-4d62-8ce3-5f89dc81bf30", "when": null, "workflow_outputs": [] }, - "35": { + "50": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/fasta_to_contig2bin/Fasta_to_Contig2Bin/1.1.7+galaxy1", "errors": null, - "id": 35, + "id": 50, "input_connections": { "inputs": { - "id": 32, + "id": 46, "output_name": "bins" } }, @@ -1759,7 +2406,7 @@ ], "position": { "left": 5829.352606657643, - "top": 1058.8504947413653 + "top": 1635.3504947413653 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/fasta_to_contig2bin/Fasta_to_Contig2Bin/1.1.7+galaxy1", @@ -1770,20 +2417,61 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"inputs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.1.7+galaxy1", "type": "tool", - "uuid": "aca0d099-2011-42db-9cac-d0eed8750ec8", + "uuid": "c37a1b20-a541-46ff-8299-84d75655585f", "when": null, "workflow_outputs": [] }, - "36": { + "51": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/pick_value/pick_value/0.2.0", + "errors": null, + "id": 51, + "input_connections": { + "style_cond|type_cond|pick_from_0|value": { + "id": 47, + "output_name": "bins" + } + }, + "inputs": [], + "label": null, + "name": "Pick parameter value", + "outputs": [ + { + "name": "data_param", + "type": "input" + } + ], + "position": { + "left": 5330.015535913235, + "top": 3552.828064163577 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/pick_value/pick_value/0.2.0", + "tool_shed_repository": { + "changeset_revision": "b19e21af9c52", + "name": "pick_value", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"style_cond\": {\"pick_style\": \"first\", \"__current_case__\": 0, \"type_cond\": {\"param_type\": \"data\", \"__current_case__\": 4, \"pick_from\": [{\"__index__\": 0, \"value\": {\"__class__\": \"ConnectedValue\"}}]}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "0.2.0", + "type": "tool", + "uuid": "6236000c-e045-4ba3-a298-cba73bf45eea", + "when": null, + "workflow_outputs": [] + }, + "52": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/concoct_merge_cut_up_clustering/concoct_merge_cut_up_clustering/1.1.0+galaxy2", "errors": null, - "id": 36, + "id": 52, "input_connections": { "cutup_clustering_result": { - "id": 33, + "id": 48, "output_name": "output_clustering" } }, @@ -1798,7 +2486,7 @@ ], "position": { "left": 5220.397610444607, - "top": 3549.4145052206 + "top": 4125.9145052206 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/concoct_merge_cut_up_clustering/concoct_merge_cut_up_clustering/1.1.0+galaxy2", @@ -1809,24 +2497,65 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"cutup_clustering_result\": {\"__class__\": \"ConnectedValue\"}, \"cutup_clustering_result|__identifier__\": \"ERR2231567.fastqsanger\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.1.0+galaxy2", "type": "tool", - "uuid": "d7c52e93-16f4-4071-b47a-e6a0c3feaf6e", + "uuid": "73f67ae0-4882-43de-9bb3-5fa0b0bbd7c9", "when": null, "workflow_outputs": [] }, - "37": { + "53": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/fasta_to_contig2bin/Fasta_to_Contig2Bin/1.1.7+galaxy1", + "errors": null, + "id": 53, + "input_connections": { + "inputs": { + "id": 51, + "output_name": "data_param" + } + }, + "inputs": [], + "label": null, + "name": "Converts genome bins in fasta format", + "outputs": [ + { + "name": "contigs2bin", + "type": "tabular" + } + ], + "position": { + "left": 5832.96570483263, + "top": 1939.6849623437997 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/fasta_to_contig2bin/Fasta_to_Contig2Bin/1.1.7+galaxy1", + "tool_shed_repository": { + "changeset_revision": "fb2bed0eb02f", + "name": "fasta_to_contig2bin", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"inputs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.7+galaxy1", + "type": "tool", + "uuid": "0106a0b9-71a3-40e5-a030-e51814de9556", + "when": null, + "workflow_outputs": [] + }, + "54": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/concoct_extract_fasta_bins/concoct_extract_fasta_bins/1.1.0+galaxy2", "errors": null, - "id": 37, + "id": 54, "input_connections": { "cluster_file": { - "id": 36, + "id": 52, "output_name": "output" }, "fasta_file": { - "id": 22, + "id": 35, "output_name": "data_param" } }, @@ -1841,7 +2570,7 @@ ], "position": { "left": 5433.12731000314, - "top": 3758.4889279710737 + "top": 4334.988927971073 }, "post_job_actions": { "TagDatasetActionbins": { @@ -1860,20 +2589,21 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"cluster_file\": {\"__class__\": \"ConnectedValue\"}, \"cluster_file|__identifier__\": \"ERR2231567.fastqsanger\", \"fasta_file\": {\"__class__\": \"ConnectedValue\"}, \"fasta_file|__identifier__\": \"ERR2231567.fastqsanger\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.1.0+galaxy2", "type": "tool", - "uuid": "5e80f512-bda6-49a4-9294-d80a12c4209b", + "uuid": "3c22433c-3d11-4284-8ed9-ea384b161031", "when": null, "workflow_outputs": [] }, - "38": { + "55": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/fasta_to_contig2bin/Fasta_to_Contig2Bin/1.1.7+galaxy1", "errors": null, - "id": 38, + "id": 55, "input_connections": { "inputs": { - "id": 37, + "id": 54, "output_name": "bins" } }, @@ -1888,7 +2618,7 @@ ], "position": { "left": 5823.878136662792, - "top": 916.555360188202 + "top": 1493.055360188202 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/fasta_to_contig2bin/Fasta_to_Contig2Bin/1.1.7+galaxy1", @@ -1899,32 +2629,37 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"inputs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.1.7+galaxy1", "type": "tool", - "uuid": "024263f9-774c-46f0-9ed1-7dbc733a3e45", + "uuid": "138b4b07-8e35-49c9-a2ce-e39d435d5506", "when": null, "workflow_outputs": [] }, - "39": { + "56": { "annotation": "", "content_id": "__BUILD_LIST__", "errors": null, - "id": 39, + "id": 56, "input_connections": { "datasets_0|input": { - "id": 38, + "id": 55, "output_name": "contigs2bin" }, "datasets_1|input": { - "id": 35, + "id": 50, "output_name": "contigs2bin" }, "datasets_2|input": { - "id": 34, + "id": 49, "output_name": "contigs2bin" }, "datasets_3|input": { - "id": 30, + "id": 44, + "output_name": "contigs2bin" + }, + "datasets_4|input": { + "id": 53, "output_name": "contigs2bin" } }, @@ -1939,41 +2674,42 @@ ], "position": { "left": 6188.08389277774, - "top": 1082.6817441970434 + "top": 1659.1817441970434 }, "post_job_actions": {}, "tool_id": "__BUILD_LIST__", - "tool_state": "{\"datasets\": [{\"__index__\": 0, \"input\": {\"__class__\": \"ConnectedValue\"}, \"id_cond\": {\"id_select\": \"idx\", \"__current_case__\": 0}}, {\"__index__\": 1, \"input\": {\"__class__\": \"ConnectedValue\"}, \"id_cond\": {\"id_select\": \"idx\", \"__current_case__\": 0}}, {\"__index__\": 2, \"input\": {\"__class__\": \"ConnectedValue\"}, \"id_cond\": {\"id_select\": \"idx\", \"__current_case__\": 0}}, {\"__index__\": 3, \"input\": {\"__class__\": \"ConnectedValue\"}, \"id_cond\": {\"id_select\": \"idx\", \"__current_case__\": 0}}], \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"datasets\": [{\"__index__\": 0, \"input\": {\"__class__\": \"ConnectedValue\"}, \"id_cond\": {\"id_select\": \"idx\", \"__current_case__\": 0}}, {\"__index__\": 1, \"input\": {\"__class__\": \"ConnectedValue\"}, \"id_cond\": {\"id_select\": \"idx\", \"__current_case__\": 0}}, {\"__index__\": 2, \"input\": {\"__class__\": \"ConnectedValue\"}, \"id_cond\": {\"id_select\": \"idx\", \"__current_case__\": 0}}, {\"__index__\": 3, \"input\": {\"__class__\": \"ConnectedValue\"}, \"id_cond\": {\"id_select\": \"idx\", \"__current_case__\": 0}}, {\"__index__\": 4, \"input\": {\"__class__\": \"ConnectedValue\"}, \"id_cond\": {\"id_select\": \"idx\", \"__current_case__\": 0}}], \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.2.0", "type": "tool", - "uuid": "111a0da7-0ea8-488c-bcc1-cd40bffdd03f", + "uuid": "e13a4212-eab3-4382-aacb-b9f22d4c2113", "when": null, "workflow_outputs": [] }, - "40": { + "57": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/binette/binette/1.2.0+galaxy0", "errors": null, - "id": 40, + "id": 57, "input_connections": { "contamination_weight": { - "id": 7, + "id": 11, "output_name": "output" }, "contig2bin_tables": { - "id": 39, + "id": 56, "output_name": "output" }, "contigs": { - "id": 22, + "id": 35, "output_name": "data_param" }, "database_type|datamanager": { - "id": 9, + "id": 13, "output_name": "output" }, "min_completeness": { - "id": 6, + "id": 10, "output_name": "output" } }, @@ -2005,7 +2741,7 @@ ], "position": { "left": 6169.057072865007, - "top": 274.1599431447222 + "top": 850.6599431447222 }, "post_job_actions": { "TagDatasetActionbins": { @@ -2024,20 +2760,21 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"contamination_weight\": {\"__class__\": \"ConnectedValue\"}, \"contig2bin_tables\": {\"__class__\": \"ConnectedValue\"}, \"contigs\": {\"__class__\": \"ConnectedValue\"}, \"database_type\": {\"is_select\": \"cached\", \"__current_case__\": 1, \"datamanager\": {\"__class__\": \"ConnectedValue\"}}, \"min_completeness\": {\"__class__\": \"ConnectedValue\"}, \"proteins\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.2.0+galaxy0", "type": "tool", - "uuid": "c2645ba2-7568-43ab-8eb0-4095fb6a4f45", + "uuid": "e3501c6e-077b-4543-8d7e-761ab596c163", "when": null, "workflow_outputs": [] }, - "41": { + "58": { "annotation": "", "content_id": "__FLATTEN__", "errors": null, - "id": 41, + "id": 58, "input_connections": { "input": { - "id": 40, + "id": 57, "output_name": "bins" } }, @@ -2052,7 +2789,7 @@ ], "position": { "left": 7407.551665528626, - "top": 321.23733971002554 + "top": 897.7373397100255 }, "post_job_actions": { "RenameDatasetActionoutput": { @@ -2065,24 +2802,25 @@ }, "tool_id": "__FLATTEN__", "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"join_identifier\": \"_\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.0.0", "type": "tool", - "uuid": "b26f89a5-9946-45cb-876d-1aa7664f9ead", + "uuid": "4c107280-84cb-4743-a5ae-abf3953e5814", "when": null, "workflow_outputs": [] }, - "42": { + "59": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/checkm2/checkm2/1.1.0+galaxy0", "errors": null, - "id": 42, + "id": 59, "input_connections": { "database": { - "id": 9, + "id": 13, "output_name": "output" }, "input": { - "id": 41, + "id": 58, "output_name": "output" } }, @@ -2105,31 +2843,32 @@ ], "position": { "left": 7712.895947265625, - "top": 614.1737863949618 + "top": 1190.6737863949618 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/checkm2/checkm2/1.1.0+galaxy0", "tool_shed_repository": { - "changeset_revision": "304ac5b49dea", + "changeset_revision": "24313e0ff049", "name": "checkm2", "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"genes\": false, \"input\": {\"__class__\": \"ConnectedValue\"}, \"model\": \"\", \"ttable\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.1.0+galaxy0", "type": "tool", - "uuid": "a39fe38e-97d3-4ef7-abbf-48f335693013", + "uuid": "256fd8ed-fc4a-42f3-b2ad-32c41fc46ded", "when": null, "workflow_outputs": [] }, - "43": { + "60": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.5+galaxy2", "errors": null, - "id": 43, + "id": 60, "input_connections": { "infile": { - "id": 42, + "id": 59, "output_name": "quality" } }, @@ -2144,7 +2883,7 @@ ], "position": { "left": 8274.890808971664, - "top": 783.7851054571695 + "top": 1360.2851054571695 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.5+galaxy2", @@ -2155,40 +2894,41 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"code\": \"BEGIN {OFS=\\\"\\\\t\\\"; print \\\"genome\\\\tcompleteness\\\\tcontamination\\\"} \\nNR > 1 {\\n if ($1 !~ /\\\\.fasta$/) \\n $1 = $1 \\\".fasta\\\"\\n print $1, $2, $3\\n}\", \"infile\": {\"__class__\": \"ConnectedValue\"}, \"variables\": [], \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "9.5+galaxy2", "type": "tool", - "uuid": "8195014e-1e2c-41d1-8621-5797585a6682", + "uuid": "0265cc4f-a101-446a-8ecf-4210de781ab3", "when": null, "workflow_outputs": [] }, - "44": { + "61": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/drep_dereplicate/drep_dereplicate/3.6.2+galaxy1", "errors": null, - "id": 44, + "id": 61, "input_connections": { "comp_clust|steps|S_ani": { - "id": 11, + "id": 16, "output_name": "output" }, "filter|completeness": { - "id": 6, + "id": 10, "output_name": "output" }, "filter|contamination": { - "id": 12, + "id": 15, "output_name": "output" }, "filter|length": { - "id": 10, + "id": 14, "output_name": "output" }, "genomes": { - "id": 41, + "id": 58, "output_name": "output" }, "quality|genomeInfo": { - "id": 43, + "id": 60, "output_name": "outfile" } }, @@ -2244,7 +2984,7 @@ ], "position": { "left": 8767.015205061576, - "top": 367.2814206558115 + "top": 943.7814206558114 }, "post_job_actions": { "TagDatasetActionCdb": { @@ -2277,107 +3017,41 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"comp_clust\": {\"steps\": {\"select\": \"default\", \"__current_case__\": 0, \"MASH_sketch\": \"1000\", \"P_ani\": \"0.9\", \"multiround_primary_clustering\": false, \"primary_chunksize\": \"5000\", \"clustering\": {\"S_algorithm\": \"ANImf\", \"__current_case__\": 1, \"n_PRESET\": \"normal\", \"coverage_method\": \"larger\"}, \"S_ani\": {\"__class__\": \"ConnectedValue\"}, \"cov_thresh\": \"0.1\"}, \"clusterAlg\": \"average\", \"run_tertiary_clustering\": false}, \"filter\": {\"length\": {\"__class__\": \"ConnectedValue\"}, \"completeness\": {\"__class__\": \"ConnectedValue\"}, \"contamination\": {\"__class__\": \"ConnectedValue\"}}, \"genomes\": {\"__class__\": \"ConnectedValue\"}, \"quality\": {\"source\": \"genomeInfo\", \"__current_case__\": 1, \"genomeInfo\": {\"__class__\": \"ConnectedValue\"}}, \"scoring\": {\"completeness_weight\": \"1.0\", \"contamination_weight\": \"5.0\", \"strain_heterogeneity_weight\": \"1.0\", \"N50_weight\": \"0.5\", \"size_weight\": \"0.0\", \"centrality_weight\": \"1.0\", \"extra_weight_table\": {\"__class__\": \"RuntimeValue\"}}, \"select_outputs\": [\"log\", \"warnings\", \"Primary_clustering_dendrogram\", \"Clustering_scatterplots\", \"Cdb\"], \"warning\": {\"warn_dist\": \"0.25\", \"warn_sim\": \"0.98\", \"warn_aln\": \"0.25\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "3.6.2+galaxy1", "type": "tool", - "uuid": "9e2450b4-5fc6-4e5d-b396-d1394c9569f4", + "uuid": "6a5edc78-0bf4-44fa-85d6-9ba339cc6360", "when": null, "workflow_outputs": [ { - "label": "Primary_clustering_dendrogram", - "output_name": "Primary_clustering_dendrogram", - "uuid": "eca5d380-b9a8-468c-b85a-cd34be091b6d" + "label": "Dereplicated Bins", + "output_name": "dereplicated_genomes", + "uuid": "38fb1a12-8e3e-43ad-8c83-60f0c546ce9d" }, { "label": "Cluster Assignment", "output_name": "Cdb", - "uuid": "cd507b42-7627-4b43-a309-784de7c6abb7" + "uuid": "c68527b5-a126-44f6-a795-6a2830083086" }, { - "label": "Dereplicated Bins", - "output_name": "dereplicated_genomes", - "uuid": "334947a2-0415-4feb-9803-090a628430c5" + "label": "Primary clustering dendrogram", + "output_name": "Primary_clustering_dendrogram", + "uuid": "02e861c1-b2cf-48f0-8c03-f32eed8e35e2" } ] }, - "45": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/gtdbtk_classify_wf/gtdbtk_classify_wf/2.5.2+galaxy1", - "errors": null, - "id": 45, - "input_connections": { - "gtdbtk_db": { - "id": 14, - "output_name": "output" - }, - "input": { - "id": 44, - "output_name": "dereplicated_genomes" - }, - "when": { - "id": 13, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "GTDB-Tk Classify genomes", - "outputs": [ - { - "name": "output_align", - "type": "input" - }, - { - "name": "output_identfy", - "type": "input" - }, - { - "name": "output_classify", - "type": "input" - }, - { - "name": "output_summary", - "type": "input" - } - ], - "position": { - "left": 10074.700262666254, - "top": 207.640356523766 - }, - "post_job_actions": { - "TagDatasetActionoutput_summary": { - "action_arguments": { - "tags": "bin-taxonomy" - }, - "action_type": "TagDatasetAction", - "output_name": "output_summary" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/gtdbtk_classify_wf/gtdbtk_classify_wf/2.5.2+galaxy1", - "tool_shed_repository": { - "changeset_revision": "53a019316350", - "name": "gtdbtk_classify_wf", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"advanced\": {\"min_perc_aa\": \"10\", \"force\": false, \"min_af\": \"0.65\", \"full_tree\": false, \"output_process_log\": false}, \"gtdbtk_db\": {\"__class__\": \"ConnectedValue\"}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_version": "2.5.2+galaxy1", - "type": "tool", - "uuid": "1c8e155f-d52d-401a-91cd-763dc092888b", - "when": "$(inputs.when)", - "workflow_outputs": [] - }, - "46": { + "62": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/coverm_genome/coverm_genome/0.7.0+galaxy0", "errors": null, - "id": 46, + "id": 62, "input_connections": { "mapped|mode|genome|genomic|genome_fasta_files": { - "id": 44, + "id": 61, "output_name": "dereplicated_genomes" }, "mapped|mode|read_type|paired_reads": { - "id": 1, + "id": 5, "output_name": "output" } }, @@ -2401,7 +3075,7 @@ ], "position": { "left": 10002.480760441063, - "top": 1898.6658904129258 + "top": 2475.165890412926 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/coverm_genome/coverm_genome/0.7.0+galaxy0", @@ -2412,20 +3086,21 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"alignment\": {\"min_read_aligned_length\": \"0\", \"min_read_percent_identity\": \"0.0\", \"min_read_aligned_percent\": \"0.0\", \"proper_pairs_only\": {\"proper_pairs_only\": \"\", \"__current_case__\": 1}, \"exclude_supplementary\": false}, \"cov\": {\"methods\": [\"relative_abundance\"], \"trim_min\": \"5\", \"trim_max\": \"95\", \"min_covered_fraction\": \"10\", \"contig_end_exclusion\": \"75\"}, \"derep\": {\"dereplicate\": {\"dereplicate\": \"\", \"__current_case__\": 1}, \"checkm_tab_table\": {\"__class__\": \"RuntimeValue\"}, \"genome_info\": {\"__class__\": \"RuntimeValue\"}, \"min_completeness\": null, \"max_contamination\": null}, \"exclude_genomes_from_deshard\": false, \"mapped\": {\"mapped\": \"not-mapped\", \"__current_case__\": 1, \"mode\": {\"mode\": \"individual\", \"__current_case__\": 0, \"read_type\": {\"type\": \"paired_collection\", \"__current_case__\": 2, \"paired_reads\": {\"__class__\": \"ConnectedValue\"}}, \"genome\": {\"ref_or_genome\": \"genomic\", \"__current_case__\": 1, \"genomic\": {\"source\": \"history\", \"__current_case__\": 0, \"genome_fasta_files\": {\"__class__\": \"ConnectedValue\"}}}}, \"mapper\": \"minimap2-sr\"}, \"out\": {\"output_format\": \"dense\", \"no_zeros\": false, \"dereplication_output_cluster_definition\": false, \"dereplication_output_representative_fasta_directory_copy\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "0.7.0+galaxy0", "type": "tool", - "uuid": "97faaf0a-47f2-41c1-8a8a-0b5f3117125c", + "uuid": "5c60a7bb-34c3-40e8-95bf-12fe264e9e63", "when": null, "workflow_outputs": [] }, - "47": { + "63": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/checkm_lineage_wf/checkm_lineage_wf/1.2.4+galaxy2", "errors": null, - "id": 47, + "id": 63, "input_connections": { "bins|bins_coll": { - "id": 44, + "id": 61, "output_name": "dereplicated_genomes" } }, @@ -2445,7 +3120,7 @@ ], "position": { "left": 10112.203882673739, - "top": 1695.393868562631 + "top": 2271.893868562631 }, "post_job_actions": { "TagDatasetActionresults": { @@ -2464,112 +3139,21 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"bins\": {\"select\": \"collection\", \"__current_case__\": 0, \"bins_coll\": {\"__class__\": \"ConnectedValue\"}}, \"extra_outputs\": null, \"lineage_set\": {\"unique\": \"10\", \"multi\": \"10\", \"force_domain\": false, \"no_refinement\": false}, \"qa\": {\"individual_markers\": false, \"skip_adj_correction\": false, \"skip_pseudogene_correction\": false, \"aai_strain\": \"0.9\", \"ignore_thresholds\": false, \"e_value\": \"1e-10\", \"length\": \"0.7\"}, \"tree_analyze\": {\"reduced_tree\": false, \"ali\": false, \"nt\": false, \"genes\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.2.4+galaxy2", "type": "tool", - "uuid": "71d425b9-303f-4826-8223-8e4e03ac49aa", - "when": null, - "workflow_outputs": [] - }, - "48": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/bakta/bakta/1.9.4+galaxy1", - "errors": null, - "id": 48, - "input_connections": { - "input_option|amrfinder_db_select": { - "id": 16, - "output_name": "output" - }, - "input_option|bakta_db_select": { - "id": 15, - "output_name": "output" - }, - "input_option|input_file": { - "id": 44, - "output_name": "dereplicated_genomes" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Bakta", - "name": "annotation" - }, - { - "description": "runtime parameter for tool Bakta", - "name": "annotation" - }, - { - "description": "runtime parameter for tool Bakta", - "name": "annotation" - }, - { - "description": "runtime parameter for tool Bakta", - "name": "annotation" - }, - { - "description": "runtime parameter for tool Bakta", - "name": "input_option" - }, - { - "description": "runtime parameter for tool Bakta", - "name": "input_option" - }, - { - "description": "runtime parameter for tool Bakta", - "name": "input_option" - } - ], - "label": null, - "name": "Bakta", - "outputs": [ - { - "name": "annotation_tsv", - "type": "tabular" - }, - { - "name": "annotation_gff3", - "type": "gff3" - }, - { - "name": "annotation_ffn", - "type": "fasta" - }, - { - "name": "summary_txt", - "type": "txt" - }, - { - "name": "annotation_plot", - "type": "svg" - } - ], - "position": { - "left": 10716.293786303548, - "top": 324.59184123639255 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/bakta/bakta/1.9.4+galaxy1", - "tool_shed_repository": { - "changeset_revision": "1942e86e2ee1", - "name": "bakta", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"annotation\": {\"complete\": false, \"prodigal\": {\"__class__\": \"RuntimeValue\"}, \"translation_table\": \"11\", \"keep_contig_headers\": false, \"replicons\": {\"__class__\": \"RuntimeValue\"}, \"compliant\": false, \"proteins\": {\"__class__\": \"RuntimeValue\"}, \"meta\": false, \"regions\": {\"__class__\": \"RuntimeValue\"}}, \"input_option\": {\"input_file\": {\"__class__\": \"ConnectedValue\"}, \"min_contig_length\": null, \"bakta_db_select\": {\"__class__\": \"ConnectedValue\"}, \"amrfinder_db_select\": {\"__class__\": \"ConnectedValue\"}}, \"organism\": {\"genus\": null, \"species\": null, \"strain\": null, \"plasmid\": null}, \"output_files\": {\"output_selection\": [\"file_tsv\", \"file_gff3\", \"file_ffn\", \"file_plot\", \"sum_txt\"]}, \"workflow\": {\"skip_analysis\": [\"--skip-ncrna\", \"--skip-ncrna-region\", \"--skip-crispr\", \"--skip-cds\", \"--skip-pseudo\", \"--skip-sorf\", \"--skip-gap\", \"--skip-ori\", \"--skip-plot\", \"--skip-tmrna\", \"--skip-trna\"]}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.9.4+galaxy1", - "type": "tool", - "uuid": "0b526101-9ed2-4653-9b4d-28298929938d", + "uuid": "78f3fe34-4457-4122-b51f-6fd3caf5ff5b", "when": null, "workflow_outputs": [] }, - "49": { + "64": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/quast/quast/5.3.0+galaxy1", "errors": null, - "id": 49, + "id": 64, "input_connections": { "mode|in|inputs": { - "id": 44, + "id": 61, "output_name": "dereplicated_genomes" } }, @@ -2600,7 +3184,7 @@ ], "position": { "left": 10664.83124800533, - "top": 1336.0538133844973 + "top": 1912.5538133844973 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/quast/quast/5.3.0+galaxy1", @@ -2611,24 +3195,25 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"advanced\": {\"contig_thresholds\": \"0,1000\", \"strict_NA\": false, \"extensive_mis_size\": \"1000\", \"scaffold_gap_max_size\": \"1000\", \"unaligned_part_size\": \"500\", \"skip_unaligned_mis_contigs\": true, \"fragmented_max_indent\": null, \"report_all_metrics\": false, \"x_for_Nx\": \"90\"}, \"alignments\": {\"use_all_alignments\": false, \"min_alignment\": \"65\", \"ambiguity_usage\": \"one\", \"ambiguity_score\": \"0.99\", \"fragmented\": false, \"upper_bound_assembly\": false, \"upper_bound_min_con\": null, \"local_mis_size\": \"200\"}, \"assembly\": {\"type\": \"metagenome\", \"__current_case__\": 1, \"ref\": {\"origin\": \"silva\", \"__current_case__\": 0, \"max_ref_num\": \"0\"}, \"reuse_combined_alignments\": false, \"min_identity\": \"90.0\"}, \"genes\": {\"gene_finding\": {\"tool\": \"none\", \"__current_case__\": 0}, \"rna_finding\": false, \"conserved_genes_finding\": false}, \"large\": false, \"min_contig\": \"500\", \"mode\": {\"mode\": \"individual\", \"__current_case__\": 0, \"in\": {\"custom\": \"false\", \"__current_case__\": 1, \"inputs\": {\"__class__\": \"ConnectedValue\"}}, \"reads\": {\"reads_option\": \"disabled\", \"__current_case__\": 0}}, \"output_files\": [\"html\", \"tabular\", \"summary\", \"krona\"], \"split_scaffolds\": false, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "5.3.0+galaxy1", "type": "tool", - "uuid": "7f0d34c7-da74-4f20-9b14-dd083145bcf0", + "uuid": "dbf66382-11a6-4eb7-8063-5eb5e5af68c7", "when": null, "workflow_outputs": [] }, - "50": { + "65": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/checkm2/checkm2/1.1.0+galaxy0", "errors": null, - "id": 50, + "id": 65, "input_connections": { "database": { - "id": 9, + "id": 13, "output_name": "output" }, "input": { - "id": 44, + "id": 61, "output_name": "dereplicated_genomes" } }, @@ -2651,7 +3236,7 @@ ], "position": { "left": 10707.895018664514, - "top": 1711.1462551162301 + "top": 2287.6462551162303 }, "post_job_actions": { "TagDatasetActionquality": { @@ -2664,26 +3249,27 @@ }, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/checkm2/checkm2/1.1.0+galaxy0", "tool_shed_repository": { - "changeset_revision": "304ac5b49dea", + "changeset_revision": "24313e0ff049", "name": "checkm2", "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"genes\": false, \"input\": {\"__class__\": \"ConnectedValue\"}, \"model\": \"\", \"ttable\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.1.0+galaxy0", "type": "tool", - "uuid": "13ea1e0d-2676-4775-aacc-7b7291a45370", + "uuid": "b200fce8-1003-44d3-bb14-ad5c862fa985", "when": null, "workflow_outputs": [] }, - "51": { + "66": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_column_join/collection_column_join/0.0.3", "errors": null, - "id": 51, + "id": 66, "input_connections": { "input_tabular": { - "id": 46, + "id": 62, "output_name": "output" } }, @@ -2698,7 +3284,7 @@ ], "position": { "left": 10948.203552291923, - "top": 1968.3588981326773 + "top": 2544.8588981326775 }, "post_job_actions": { "TagDatasetActiontabular_output": { @@ -2717,73 +3303,27 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"fill_char\": \".\", \"has_header\": \"1\", \"identifier_column\": \"1\", \"include_outputs\": null, \"input_tabular\": {\"__class__\": \"ConnectedValue\"}, \"old_col_in_header\": false, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "0.0.3", "type": "tool", - "uuid": "1c080e86-ea03-425f-9309-c9267cd51cf0", + "uuid": "a6dda306-8aa4-450a-9017-cec4b5a5c87f", "when": null, "workflow_outputs": [ { "label": "Merged CoverM Output", "output_name": "tabular_output", - "uuid": "7d77c4e8-2fd7-49ee-8591-d046476faf19" + "uuid": "366639bd-ac82-4155-84d6-511097d2fb4d" } ] }, - "52": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.5+galaxy2", - "errors": null, - "id": 52, - "input_connections": { - "infile": { - "id": 48, - "output_name": "summary_txt" - } - }, - "inputs": [], - "label": "Format Bakta output", - "name": "Text reformatting", - "outputs": [ - { - "name": "outfile", - "type": "input" - } - ], - "position": { - "left": 11039.303567915207, - "top": 263.5885387720886 - }, - "post_job_actions": { - "ChangeDatatypeActionoutfile": { - "action_arguments": { - "newtype": "tabular" - }, - "action_type": "ChangeDatatypeAction", - "output_name": "outfile" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.5+galaxy2", - "tool_shed_repository": { - "changeset_revision": "c41d78ae5fee", - "name": "text_processing", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"code\": \"BEGIN {\\n print \\\"Annotation\\\\tCount\\\"\\n}\\n\\n/^Annotation:/ { in_block = 1; next }\\n/^Bakta:/ { in_block = 0 }\\n\\nin_block {\\n if ($0 ~ /^[[:space:]]*$/) next # skip blank lines\\n sub(/[[:space:]]*:[[:space:]]*/, \\\"\\\\t\\\", $0) # replace first colon+spaces with a tab\\n print $0\\n}\", \"infile\": {\"__class__\": \"ConnectedValue\"}, \"variables\": [], \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_version": "9.5+galaxy2", - "type": "tool", - "uuid": "4d0cef05-858d-4ccd-80d4-f8c4daad297e", - "when": null, - "workflow_outputs": [] - }, - "53": { + "67": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_column_join/collection_column_join/0.0.3", "errors": null, - "id": 53, + "id": 67, "input_connections": { "input_tabular": { - "id": 49, + "id": 64, "output_name": "report_tabular_meta" } }, @@ -2798,7 +3338,7 @@ ], "position": { "left": 11307.779777465532, - "top": 1826.5704096431516 + "top": 2403.070409643152 }, "post_job_actions": { "TagDatasetActiontabular_output": { @@ -2817,47 +3357,40 @@ "tool_shed": "toolshed.g2.bx.psu.edu" }, "tool_state": "{\"fill_char\": \".\", \"has_header\": \"1\", \"identifier_column\": \"1\", \"include_outputs\": null, \"input_tabular\": {\"__class__\": \"ConnectedValue\"}, \"old_col_in_header\": false, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "0.0.3", "type": "tool", - "uuid": "a11189fc-6375-44d8-bcb5-93d04ece9eb0", + "uuid": "79887223-e44f-4ca7-81fc-0c54c3eb6693", "when": null, "workflow_outputs": [ { "label": "Merged Quast Output", "output_name": "tabular_output", - "uuid": "b9b34d5a-d502-4ffd-97cd-c5564a19152d" + "uuid": "0c73acee-580e-4b8f-8bfc-075c1523d8c4" } ] }, - "54": { + "68": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/multiqc/multiqc/1.27+galaxy4", "errors": null, - "id": 54, + "id": 68, "input_connections": { "results_0|software_cond|input": { - "id": 49, + "id": 64, "output_name": "report_tabular_meta" }, "results_1|software_cond|input": { - "id": 50, + "id": 65, "output_name": "quality" }, "results_2|software_cond|input": { - "id": 51, - "output_name": "tabular_output" + "id": 63, + "output_name": "results" }, "results_3|software_cond|input": { - "id": 45, - "output_name": "output_summary" - }, - "results_4|software_cond|input": { - "id": 48, - "output_name": "summary_txt" - }, - "results_5|software_cond|input": { - "id": 47, - "output_name": "results" + "id": 66, + "output_name": "tabular_output" } }, "inputs": [ @@ -2880,7 +3413,7 @@ ], "position": { "left": 11359.784387681611, - "top": 1340.837190217281 + "top": 1917.337190217281 }, "post_job_actions": { "TagDatasetActionhtml_report": { @@ -2898,69 +3431,17 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"comment\": \"\", \"export\": false, \"flat\": false, \"image_content_input\": {\"__class__\": \"RuntimeValue\"}, \"png_plots\": false, \"results\": [{\"__index__\": 0, \"software_cond\": {\"software\": \"quast\", \"__current_case__\": 21, \"input\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 1, \"software_cond\": {\"software\": \"custom_content\", \"__current_case__\": 46, \"plot_type\": \"table\", \"section_name\": \"CheckM2 Bin quality\", \"title\": null, \"description\": null, \"xlab\": null, \"ylab\": null, \"input\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 2, \"software_cond\": {\"software\": \"custom_content\", \"__current_case__\": 46, \"plot_type\": \"table\", \"section_name\": \"CoverM Bin coverage\", \"title\": null, \"description\": null, \"xlab\": null, \"ylab\": null, \"input\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 3, \"software_cond\": {\"software\": \"custom_content\", \"__current_case__\": 46, \"plot_type\": \"table\", \"section_name\": \"GTDB-Tk taxonomy\", \"title\": null, \"description\": null, \"xlab\": null, \"ylab\": null, \"input\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 4, \"software_cond\": {\"software\": \"bakta\", \"__current_case__\": 34, \"input\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 5, \"software_cond\": {\"software\": \"custom_content\", \"__current_case__\": 46, \"plot_type\": \"table\", \"section_name\": \" CheckM Bin quality\", \"title\": null, \"description\": null, \"xlab\": null, \"ylab\": null, \"input\": {\"__class__\": \"ConnectedValue\"}}}], \"title\": \"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"comment\": \"\", \"export\": false, \"flat\": false, \"image_content_input\": {\"__class__\": \"RuntimeValue\"}, \"png_plots\": false, \"results\": [{\"__index__\": 0, \"software_cond\": {\"software\": \"quast\", \"__current_case__\": 21, \"input\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 1, \"software_cond\": {\"software\": \"custom_content\", \"__current_case__\": 46, \"plot_type\": \"table\", \"section_name\": \"CheckM Bin quality\", \"title\": null, \"description\": null, \"xlab\": null, \"ylab\": null, \"input\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 2, \"software_cond\": {\"software\": \"custom_content\", \"__current_case__\": 46, \"plot_type\": \"table\", \"section_name\": \"CheckM2 Bin quality\", \"title\": null, \"description\": null, \"xlab\": null, \"ylab\": null, \"input\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 3, \"software_cond\": {\"software\": \"custom_content\", \"__current_case__\": 46, \"plot_type\": \"table\", \"section_name\": \" CoverM Bin coverage\", \"title\": null, \"description\": null, \"xlab\": null, \"ylab\": null, \"input\": {\"__class__\": \"ConnectedValue\"}}}], \"title\": \"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, "tool_version": "1.27+galaxy4", "type": "tool", - "uuid": "58e8b947-0100-41d5-89be-cd6add7fe210", + "uuid": "1ee3626f-8b00-4d4c-a574-e1e310788110", "when": null, "workflow_outputs": [ { "label": "Full MultiQC Report", "output_name": "html_report", - "uuid": "ed25bee2-0a5e-4e0a-9d53-a7cd2ba5292f" - } - ] - }, - "55": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_column_join/collection_column_join/0.0.3", - "errors": null, - "id": 55, - "input_connections": { - "input_tabular": { - "id": 52, - "output_name": "outfile" - } - }, - "inputs": [], - "label": "Merge Bakta Output", - "name": "Column join", - "outputs": [ - { - "name": "tabular_output", - "type": "tabular" - } - ], - "position": { - "left": 11142.086195383856, - "top": 543.7784868751125 - }, - "post_job_actions": { - "TagDatasetActiontabular_output": { - "action_arguments": { - "tags": "bin-bakta-annotation" - }, - "action_type": "TagDatasetAction", - "output_name": "tabular_output" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_column_join/collection_column_join/0.0.3", - "tool_shed_repository": { - "changeset_revision": "3ddd99c7efee", - "name": "collection_column_join", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"fill_char\": \".\", \"has_header\": \"1\", \"identifier_column\": \"1\", \"include_outputs\": null, \"input_tabular\": {\"__class__\": \"ConnectedValue\"}, \"old_col_in_header\": false, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_version": "0.0.3", - "type": "tool", - "uuid": "b7daf2fe-39a2-4356-b508-f22cc9b23572", - "when": null, - "workflow_outputs": [ - { - "label": "bin-bakta-annotation", - "output_name": "tabular_output", - "uuid": "4e247612-413c-43eb-8800-085159446cf1" + "uuid": "cdf15c25-b19a-43f2-9956-7a3a91ecbac8" } ] } @@ -2968,6 +3449,6 @@ "tags": [ "name:FAIRyMAGs" ], - "uuid": "0fd322e3-653b-49b5-a851-14fdf74d0045", - "version": 15 -} + "uuid": "f985aaad-9023-465c-ad89-6abea077e42f", + "version": 1 +} \ No newline at end of file diff --git a/workflows/microbiome/mags-building/README.md b/workflows/microbiome/mags-building/README.md index d81c066bbf..2c2ab8f532 100644 --- a/workflows/microbiome/mags-building/README.md +++ b/workflows/microbiome/mags-building/README.md @@ -1,43 +1,62 @@ -# Metagenome-Assembled Genomes (MAGs) Generation +# Metagenome-Assembled Genomes (MAGs) Generation -This workflow generates Metagenome-Assembled Genomes (MAGs) from paired short reads. +This workflow generates Metagenome-Assembled Genomes (MAGs) from paired short reads and optional long reads. +The use of long reads is only supported for assembly with **metaSPADES**. Dereplicated MAGs for the complete input sample set are reported. -## Workflow Logic +## Workflow Logic -The workflow supports assembly using **metaSPADES** and **MEGAHIT**. -For binning, it utilizes four different tools: **MetaBAT2, MaxBin2, SemiBin, and CONCOCT**. The resulting bins are then refined using **Binette**, the successor of metaWRAP. +The workflow supports assembly using **metaSPADES** and **MEGAHIT**. +For binning, it utilizes five different tools: **MetaBAT2, MaxBin2, SemiBin, COMEBin, and CONCOCT**. The resulting bins are then refined using **Binette**, the successor of metaWRAP. -## MAGs Annotation and Quality Control +## MAGs Annotation and Quality Control -After binning, the resulting MAGs are **dereplicated** across all input samples based on **CheckM2 quality metrics** using **dRep**. The following processing steps are then performed: +After binning, the resulting MAGs are **dereplicated** across all input samples based on **CheckM2 quality metrics** using **dRep**. The following processing steps are then performed: -- **Annotation** with Bakta -- **Taxonomic Assignment** using GTDB-Tk -- **Quality Control** via QUAST and CheckM/CheckM2 -- **Abundance Estimation** per sample with CoverM +* **Quality Control** via QUAST and CheckM/CheckM2 +* **Abundance Estimation** per sample with CoverM -All results are consolidated into a single **MultiQC report** for easy analysis. +In previous versions, genome annotation and taxonomic annotation were also performed. This can now be done with dedicated and more comprehensive IWC workflows if needed: -## Input Requirements +* [MAG Genome Annotation](https://iwc.galaxyproject.org/workflow/mag-genome-annotation-parallel-main) +* [MAGs Taxonomy Annotation](https://iwc.galaxyproject.org/workflow/mags-taxonomy-annotation-main) +* [Functional Annotation of Sequences](https://iwc.galaxyproject.org/workflow/functional-annotation-of-sequences-main) +* [AMR Gene Detection](https://iwc.galaxyproject.org/workflow/amr_gene_detection-main) -Input reads must be quality-filtered, with host reads removed. -See other MAGs workflows in IWC for quality filtering and host removal. +All results are consolidated into a single **MultiQC report**. -- **Trimmed reads**: Quality-trimmed reads from individual samples. -- **Trimmed reads from grouped samples**: These reads need to be grouped based on the desired MAGs generation approach. The tool [fastq_groupmerge](toolshed.g2.bx.psu.edu/repos/iuc/fastq_groupmerge/fastq_groupmerge/1.0.1+galaxy0) can be used to perform the grouping. - - **Individual MAGs Generation**: Use the same input as `Trimmed Reads` to generate MAGs per sample. - - **Pooled MAGs Generation (Co-assembly/Binning)**: Merge all reads input one file for a fully pooled MAGs approach. - - **Grouped MAGs Generation (Co-assembly/Binning)**: Merge samples based on predefined groups. - - **Hybrid MAGs Generation**: Combine individual and grouped reads for a mixed approach. +## Input Requirements -> **Note**: Merging reads can result in large input files, significantly increasing computational demands—especially during assembly and binning, which may require substantial RAM. Our tests with synthetic samples up to **50 GB** showed feasible performance. For larger datasets, we recommend limiting the approach to **individual or pooled MAGs generation**. +Input reads must be quality-filtered, with host reads removed. +See other MAG workflows in IWC for quality filtering and host removal. -## Optional modifications +**Short reads:** -Some modifications that can be done via the workflow editor for specific use cases: -- Compare binners / bin refinement: add checkM/M2 to each binner / refiner and compare completeness, contamination, n. of bins. -- Optionally use DAS tool instead of Binette (our benchmark showed that Binette produce better MAGs on average). -- Add annotation for Bakta (currently Bakta only reports rRNAs to save resources), other annotations can be selected in the Bakta options. -- Downstream: compare differential abundance of MAGs in your samples based on metadata using maaslin2. -- Downstream: compare your MAGs to a catalogue of MAGs for similar samples. Download desired MAGs e.g. from [MGnify genomes](https://www.ebi.ac.uk/metagenomics/browse/genomes) you can query your MAGs via the [MGnify API](https://www.ebi.ac.uk/metagenomics/browse/genomes?browse-by=mag-search); download the Genomes and compare in Galaxy e.g. using dREP. \ No newline at end of file +* QC: [Short Read QC & Trimming](https://iwc.galaxyproject.org/workflow/short-read-qc-trimming-main) +* Host removal: [Host Contamination Removal (Short Reads)](https://iwc.galaxyproject.org/workflow/host-contamination-removal-short-reads-main) + +**Long reads:** + +* QC: [Nanopore Pre-processing](https://iwc.galaxyproject.org/workflow/nanopore-pre-processing-main) +* Host removal: [Host Contamination Removal (Long Reads)](https://iwc.galaxyproject.org/workflow/host-contamination-removal-long-reads-main) + +**Workflow input:** + +* **Trimmed reads**: Quality-trimmed reads from individual samples. +* **Trimmed reads from grouped samples**: These reads need to be grouped based on the desired MAGs generation approach. The tool [fastq_groupmerge](toolshed.g2.bx.psu.edu/repos/iuc/fastq_groupmerge/fastq_groupmerge/1.0.1+galaxy0) can be used to perform the grouping. Long reads and short reads must be grouped using the same logic. + + * **Individual MAGs Generation**: Use the same input as `Trimmed Reads` to generate MAGs per sample. + * **Pooled MAGs Generation (Co-assembly/Binning)**: Merge all reads into one file for a fully pooled MAGs approach. + * **Grouped MAGs Generation (Co-assembly/Binning)**: Merge samples based on predefined groups. + * **Hybrid MAGs Generation**: Combine individual and grouped reads for a mixed approach. + +> **Note**: Merging reads can result in large input files, significantly increasing computational demands—especially during assembly and binning, which may require substantial RAM. Our tests with synthetic samples up to **50 GB** showed feasible performance. For larger datasets, we recommend limiting the approach to **individual or pooled MAGs generation**. + +## Optional Modifications + +Some modifications can be made via the workflow editor for specific use cases: + +* Compare binners/bin refinement: add CheckM/CheckM2 to each binner/refiner and compare completeness, contamination, and number of bins. +* Optionally use DAS Tool instead of Binette (our benchmark showed that Binette produces better MAGs on average). +* Downstream: compare differential abundance of MAGs in your samples based on metadata using Maaslin2. +* Downstream: compare your MAGs to a catalogue of MAGs for similar samples. Download desired MAGs from [MGnify genomes](https://www.ebi.ac.uk/metagenomics/browse/genomes) and query your MAGs via the [MGnify API](https://www.ebi.ac.uk/metagenomics/browse/genomes?browse-by=mag-search); download the genomes and compare in Galaxy, e.g., using dRep. \ No newline at end of file