add taxonomic analysis and human reads removal wf

workflows/sars-cov-2-variant-calling/sars-cov-2-ww-taxonomic-analysis-with-human-reads-removal/.dockstore.yml

@@ -0,0 +1,15 @@
+version: 1.2
+workflows:
+- name: main
+  subclass: Galaxy
+  publish: true
+  primaryDescriptorPath: /Taxonomic-Analysis-of-SARS-CoV-2-Wastewater-Samples-with-Human-Read-Removal.ga
+  testParameterFiles:
+  - /Taxonomic-Analysis-of-SARS-CoV-2-Wastewater-Samples-with-Human-Read-Removal-tests.yml
+  authors:
+  - name: Polina Polunina
+    orcid: 0000-0002-0507-460
+  - name: "B\xE9r\xE9nice Batut"
+    orcid: 0000-0001-9852-198
+  - name: Wolfgang Maier
+    orcid: 0000-0002-9464-664

workflows/sars-cov-2-variant-calling/sars-cov-2-ww-taxonomic-analysis-with-human-reads-removal/Taxonomic-Analysis-of-SARS-CoV-2-Wastewater-Samples-with-Human-Read-Removal-tests.yml

@@ -0,0 +1,51 @@
+- doc: Test outline for Taxonomic-Analysis-of-SARS-CoV-2-Wastewater-Samples-with-Human-Read-Removal
+  job:
+    SARS-CoV-2 reference genome:
+      class: File
+      path: test-data/SARS-CoV-2 reference genome.fasta
+      filetype: fasta
+    Paired Collection:
+      class: Collection
+      collection_type: list:paired
+      elements:
+      - class: Collection
+        type: paired
+        identifier: SRR12596170.fastq
+        elements:
+        - class: File
+          identifier: forward
+          path: test-data/Paired Collection_forward.fastqsanger.gz
+        - class: File
+          identifier: reverse
+          path: test-data/Paired Collection_reverse.fastqsanger.gz
+      - class: Collection
+        type: paired
+        identifier: SRR12596172.fastq
+        elements:
+        - class: File
+          identifier: forward
+          path: test-data/Paired Collection_forward.fastqsanger.gz
+        - class: File
+          identifier: reverse
+          path: test-data/Paired Collection_reverse.fastqsanger.gz
+  outputs:
+    kraken2 report output:
+      element_tests:
+        SRR12596170.fastq:
+          asserts:
+            has_text:
+              text: "root"
+        SRR12596172.fastq:
+          asserts:
+            has_text:
+              text: "unclassified"
+  Converted Kraken2 output:
+      element_tests:
+        SRR12596170.fastq:
+          asserts:
+            has_text:
+              text: "root"
+        SRR12596172.fastq:
+          asserts:
+            has_text:
+              text: "root"

workflows/sars-cov-2-variant-calling/sars-cov-2-ww-taxonomic-analysis-with-human-reads-removal/Taxonomic-Analysis-of-SARS-CoV-2-Wastewater-Samples-with-Human-Read-Removal.ga

@@ -0,0 +1 @@
+{"a_galaxy_workflow": "true", "annotation": "The workflow for SARS-CoV-2 wastewater Illumina-sequenced metatranscriptomics data analysis", "creator": [{"class": "Person", "identifier": "0000-0002-0507-4602", "name": "Polina Polunina"}, {"class": "Person", "identifier": "0000-0001-9852-1987", "name": "B\u00e9r\u00e9nice Batut"}, {"class": "Person", "identifier": "0000-0002-9464-6640", "name": "Wolfgang Maier"}], "format-version": "0.1", "license": "MIT", "release": "0.1", "name": "Taxonomic Analysis of SARS-CoV-2 Wastewater Samples with Human Read Removal", "steps": {"0": {"annotation": "SARS-CoV-2 reference fasta sequence (typically NC_045512.2, alias MN908947.3 of isolate Wuhan-Hu-1)", "content_id": null, "errors": null, "id": 0, "input_connections": {}, "inputs": [{"description": "SARS-CoV-2 reference fasta sequence (typically NC_045512.2, alias MN908947.3 of isolate Wuhan-Hu-1)", "name": "SARS-CoV-2 reference genome"}], "label": "SARS-CoV-2 reference genome", "name": "Input dataset", "outputs": [], "position": {"left": 14.870905894625793, "top": 0.0}, "tool_id": null, "tool_state": "{\"optional\": false, \"format\": [\"fasta\", \"fasta.gz\"], \"tag\": \"\"}", "tool_version": null, "type": "data_input", "uuid": "f16ff677-b40e-4479-b54f-96e705e82134", "when": null, "workflow_outputs": []}, "1": {"annotation": "Illumina reads with fastqsanger encoding", "content_id": null, "errors": null, "id": 1, "input_connections": {}, "inputs": [{"description": "Illumina reads with fastqsanger encoding", "name": "Paired Collection"}], "label": "Paired Collection", "name": "Input dataset collection", "outputs": [], "position": {"left": 0.0, "top": 374.662597070828}, "tool_id": null, "tool_state": "{\"optional\": false, \"format\": [\"fastqsanger\", \"fastqsanger.gz\"], \"tag\": \"\", \"collection_type\": \"list:paired\"}", "tool_version": null, "type": "data_collection_input", "uuid": "27a89012-46f7-4c46-b82d-7eac01a3024c", "when": null, "workflow_outputs": []}, "2": {"annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/fastp/fastp/0.20.1+galaxy0", "errors": null, "id": 2, "input_connections": {"single_paired|paired_input": {"id": 1, "output_name": "output"}}, "inputs": [], "label": null, "name": "fastp", "outputs": [{"name": "output_paired_coll", "type": "input"}, {"name": "report_html", "type": "html"}, {"name": "report_json", "type": "json"}], "position": {"left": 283.89489706096515, "top": 224.05028983352798}, "post_job_actions": {"HideDatasetActionreport_json": {"action_arguments": {}, "action_type": "HideDatasetAction", "output_name": "report_json"}}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/fastp/fastp/0.20.1+galaxy0", "tool_shed_repository": {"changeset_revision": "dbf9c561ef29", "name": "fastp", "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu"}, "tool_state": "{\"filter_options\": {\"quality_filtering_options\": {\"disable_quality_filtering\": false, \"qualified_quality_phred\": null, \"unqualified_percent_limit\": null, \"n_base_limit\": null}, \"length_filtering_options\": {\"disable_length_filtering\": false, \"length_required\": null, \"length_limit\": null}, \"low_complexity_filter\": {\"enable_low_complexity_filter\": false, \"complexity_threshold\": null}}, \"output_options\": {\"report_html\": true, \"report_json\": true}, \"overrepresented_sequence_analysis\": {\"overrepresentation_analysis\": false, \"overrepresentation_sampling\": null}, \"read_mod_options\": {\"polyg_tail_trimming\": {\"trimming_select\": \"\", \"__current_case__\": 1, \"poly_g_min_len\": null}, \"polyx_tail_trimming\": {\"polyx_trimming_select\": \"\", \"__current_case__\": 1}, \"umi_processing\": {\"umi\": false, \"umi_loc\": \"\", \"umi_len\": null, \"umi_prefix\": \"\"}, \"cutting_by_quality_options\": {\"cut_by_quality5\": false, \"cut_by_quality3\": false, \"cut_window_size\": null, \"cut_mean_quality\": null}, \"base_correction_options\": {\"correction\": false}}, \"single_paired\": {\"single_paired_selector\": \"paired_collection\", \"__current_case__\": 2, \"paired_input\": {\"__class__\": \"ConnectedValue\"}, \"adapter_trimming_options\": {\"disable_adapter_trimming\": false, \"adapter_sequence1\": \"\", \"adapter_sequence2\": \"\"}, \"global_trimming_options\": {\"trim_front1\": null, \"trim_tail1\": null, \"trim_front2\": null, \"trim_tail2\": null}}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "0.20.1+galaxy0", "type": "tool", "uuid": "574667b3-fb80-4da0-b76a-7c6941f94777", "when": null, "workflow_outputs": [{"label": "fastp_pe", "output_name": "output_paired_coll", "uuid": "95cc6cb9-8571-4ad8-9dfe-2fb81022a960"}, {"label": "fastp_html_report", "output_name": "report_html", "uuid": "b988c650-2522-4fb9-a255-ecab9a5a1dd9"}]}, "3": {"annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/kraken2/kraken2/2.1.1+galaxy1", "errors": null, "id": 3, "input_connections": {"single_paired|input_pair": {"id": 1, "output_name": "output"}}, "inputs": [], "label": null, "name": "Kraken2", "outputs": [{"name": "report_output", "type": "tabular"}, {"name": "output", "type": "tabular"}], "position": {"left": 277.3152676445572, "top": 496.4841750655785}, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/kraken2/kraken2/2.1.1+galaxy1", "tool_shed_repository": {"changeset_revision": "e674066930b2", "name": "kraken2", "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu"}, "tool_state": "{\"confidence\": \"0.0\", \"kraken2_database\": \"viral2019-03\", \"min_base_quality\": \"0\", \"minimum_hit_groups\": \"2\", \"quick\": false, \"report\": {\"create_report\": true, \"use_mpa_style\": false, \"report_zero_counts\": false, \"report_minimizer_data\": false}, \"single_paired\": {\"single_paired_selector\": \"collection\", \"__current_case__\": 0, \"input_pair\": {\"__class__\": \"ConnectedValue\"}}, \"split_reads\": false, \"use_names\": false, \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "2.1.1+galaxy1", "type": "tool", "uuid": "0e8ced84-9abd-4435-b45b-2362530d60a5", "when": null, "workflow_outputs": [{"label": "Kraken2 on input dataset(s): Classification", "output_name": "output", "uuid": "3a16b606-a868-48e7-9696-8128655dc1f1"}, {"label": "kraken2 report output", "output_name": "report_output", "uuid": "610c591a-9347-4957-938f-0a8f43b6b363"}]}, "4": {"annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/read_it_and_keep/read_it_and_keep/0.2.2+galaxy0", "errors": null, "id": 4, "input_connections": {"reads|paired_reads": {"id": 2, "output_name": "output_paired_coll"}, "ref_source|ref_fasta": {"id": 0, "output_name": "output"}}, "inputs": [], "label": null, "name": "Read It and Keep", "outputs": [{"name": "output_collection", "type": "input"}], "position": {"left": 635.8491400306144, "top": 201.57228705933926}, "post_job_actions": {"HideDatasetActionoutput_collection": {"action_arguments": {}, "action_type": "HideDatasetAction", "output_name": "output_collection"}}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/read_it_and_keep/read_it_and_keep/0.2.2+galaxy0", "tool_shed_repository": {"changeset_revision": "1563b58905f4", "name": "read_it_and_keep", "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu"}, "tool_state": "{\"adv\": {\"min_map_length\": \"50\", \"min_map_length_pc\": \"50.0\", \"enumerate_names\": false}, \"reads\": {\"read_type\": \"paired_collection\", \"__current_case__\": 1, \"paired_reads\": {\"__class__\": \"ConnectedValue\"}}, \"ref_source\": {\"source\": \"history\", \"__current_case__\": 0, \"ref_fasta\": {\"__class__\": \"ConnectedValue\"}}, \"sequencing_tech\": \"illumina\", \"trim_reference\": true, \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "0.2.2+galaxy0", "type": "tool", "uuid": "101ddc69-2eaf-472d-b8d0-b419b303ac3c", "when": null, "workflow_outputs": []}, "5": {"annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/devteam/kraken2tax/Kraken2Tax/1.1", "errors": null, "id": 5, "input_connections": {"input": {"id": 3, "output_name": "report_output"}}, "inputs": [], "label": null, "name": "Convert Kraken", "outputs": [{"name": "out_file", "type": "taxonomy"}], "position": {"left": 534.9780458180148, "top": 525.8335410291587}, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/kraken2tax/Kraken2Tax/1.1", "tool_shed_repository": {"changeset_revision": "d844fdcce44e", "name": "kraken2tax", "owner": "devteam", "tool_shed": "toolshed.g2.bx.psu.edu"}, "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"ncbi_taxonomy\": \"2020-12-03\", \"read_name\": \"2\", \"tax_id\": \"3\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "1.1", "type": "tool", "uuid": "bc2a9bf1-9c2a-484d-a41c-d01b7247b18f", "when": null, "workflow_outputs": [{"label": "Converted Kraken2 output", "output_name": "out_file", "uuid": "e03381ed-e828-4037-8334-b5a6c910976e"}]}, "6": {"annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/crs4/taxonomy_krona_chart/taxonomy_krona_chart/2.7.1", "errors": null, "id": 6, "input_connections": {"type_of_data|input": {"id": 5, "output_name": "out_file"}}, "inputs": [], "label": null, "name": "Krona pie chart", "outputs": [{"name": "output", "type": "html"}], "position": {"left": 808.8290375111392, "top": 428.5225963831433}, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/crs4/taxonomy_krona_chart/taxonomy_krona_chart/2.7.1", "tool_shed_repository": {"changeset_revision": "1334cb4c6b68", "name": "taxonomy_krona_chart", "owner": "crs4", "tool_shed": "toolshed.g2.bx.psu.edu"}, "tool_state": "{\"combine_inputs\": false, \"root_name\": \"Root\", \"type_of_data\": {\"type_of_data_selector\": \"taxonomy\", \"__current_case__\": 0, \"input\": {\"__class__\": \"ConnectedValue\"}, \"max_rank\": \"8\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "2.7.1", "type": "tool", "uuid": "1d0f9115-bb1a-4d5a-94b0-a351185da810", "when": null, "workflow_outputs": [{"label": "Krona pie chart on input dataset(s): HTML", "output_name": "output", "uuid": "9504027b-01d5-40a2-bae7-d9625b26f74e"}]}, "7": {"annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/crs4/taxonomy_krona_chart/taxonomy_krona_chart/2.7.1", "errors": null, "id": 7, "input_connections": {"type_of_data|input": {"id": 5, "output_name": "out_file"}}, "inputs": [], "label": null, "name": "Krona pie chart", "outputs": [{"name": "output", "type": "html"}], "position": {"left": 810.6724382640716, "top": 632.069973577796}, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/crs4/taxonomy_krona_chart/taxonomy_krona_chart/2.7.1", "tool_shed_repository": {"changeset_revision": "1334cb4c6b68", "name": "taxonomy_krona_chart", "owner": "crs4", "tool_shed": "toolshed.g2.bx.psu.edu"}, "tool_state": "{\"combine_inputs\": true, \"root_name\": \"Root\", \"type_of_data\": {\"type_of_data_selector\": \"taxonomy\", \"__current_case__\": 0, \"input\": {\"__class__\": \"ConnectedValue\"}, \"max_rank\": \"8\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "2.7.1", "type": "tool", "uuid": "6f391336-5aad-45de-9f49-40f77d88a96c", "when": null, "workflow_outputs": [{"label": "Combined Krona pie chart on input dataset(s): HTML", "output_name": "output", "uuid": "e01b0fcd-79b5-4cbc-82d2-35c4cc28eb37"}]}}, "tags": [], "uuid": "b648d141-01d2-4f4d-8cb5-f9cbffe8179e", "version": 2}