Add Repeatmasking workflow

workflows/repeatmasking/.dockstore.yml

@@ -0,0 +1,11 @@
+version: 1.2
+workflows:
+- name: main
+  subclass: Galaxy
+  publish: true
+  primaryDescriptorPath: /RepeatMasking-Workflow.ga
+  testParameterFiles:
+  - /RepeatMasking-Workflow-tests.yml
+  authors:
+  - name: Romane Libouban
+    email: mailto:[email protected]

workflows/repeatmasking/.workflowhub.yml

@@ -0,0 +1,5 @@
+version: '0.1'
+registries:
+- url: https://workflowhub.eu
+  project: iwc
+  workflow: RepeatMasking-Workflow./main

workflows/repeatmasking/CHANGELOG.md

@@ -0,0 +1,5 @@
+# Changelog
+
+## [0.1]
+
+Initial version of the RepeatMasking workflow for genomic sequencing data.

workflows/repeatmasking/README.md

@@ -0,0 +1,29 @@
+# RepeatMasking Workflow
+
+This workflow uses RepeatModeler and RepeatMasker for genome analysis.
+
+- RepeatModeler is a software package for identifying and modeling de novo families of transposable elements (TEs). At the heart of RepeatModeler are three de novo repeat search programs (RECON, RepeatScout and LtrHarvest/Ltr_retriever) which use complementary computational methods to identify repeat element boundaries and family relationships from sequence data.
+
+- RepeatMasker is a program that analyzes DNA sequences for *interleaved repeats* and *low-complexity* DNA sequences. The result of the program is a detailed annotation of the repeats present in the query sequence, as well as a modified version of the query sequence in which all annotated repeats are present.
+
+## Input dataset for ReapatModeler
+- RepeatModeler requires a single input file, a genome in fasta format.
+
+
+## Outputs dataset for ReapatModeler
+- Two output files are generated:
+    - summary file (.tbl)
+    - fasta file containing alignments in order of appearance in the query sequence
+
+
+## Input dataset for RepeatMasker
+- ReapatMasker requires the fasta file generated by ReapatModeler
+
+## Outputs datasets for RepeatMasker
+- Five output files are generated:
+    - a fasta file
+    - .gff3 file
+    - a table summarizing the repeated content of the sequence analyzed
+    - a file with statistics related to the repeated content of the sequence analyzed
+    - a summary of the mutation sites found and the order of grouping
+

workflows/repeatmasking/RepeatMasking-Workflow-tests.yml

@@ -0,0 +1,34 @@
+- doc: Test outline for RepeatMasking Workflow
+  job:
+    sequence.fasta:
+      class: File
+      path: test-data/sequence.fasta
+      filetype: fasta
+
+  # inputs:
+  #   sequence.fasta.fasta: sequence.fasta
+
+  outputs:
+    'sequences':
+      sequence:
+        path: test-data/repeatmodeler_output_sequences.fasta
+        compare: contents
+      seeds:
+        path: test-data/repeatmodeler_output_seeds.stockholm
+        compare: contents
+    'output_masked_genome':
+      output_masked_genome:
+        path: test-data/repeatmasker_output_masked_genome.fasta
+        compare: contents
+      output_log:
+        path: test-data/repeatmasker_output_log.tabular
+        compare: contents
+      output_table:
+        path: test-data/repeatmasker_output_table.txt
+        compare: contents
+      output_repeat_catalog:
+        path: test-data/repeatmasker_output_repeat_catalog.txt
+        compare: contents
+      output_gff:
+        path: test-data/repeatmasker_output_gff.gff
+        compare: contents

workflows/repeatmasking/RepeatMasking-Workflow.ga

@@ -0,0 +1,168 @@
+{
+    "a_galaxy_workflow": "true",
+    "annotation": "",
+    "format-version": "0.1",
+    "license": "MIT",
+    "release": "0.1",
+    "name": "Workflow constructed from history 'RepeatMasking'",
+    "steps": {
+        "0": {
+            "annotation": "",
+            "content_id": null,
+            "errors": null,
+            "id": 0,
+            "input_connections": {},
+            "inputs": [
+                {
+                    "description": "",
+                    "name": "sequence.fasta"
+                }
+            ],
+            "label": "sequence.fasta",
+            "name": "Input dataset",
+            "outputs": [],
+            "position": {
+                "left": 10,
+                "top": 10
+            },
+            "tool_id": null,
+            "tool_state": "{\"optional\": false, \"tag\": null}",
+            "tool_version": null,
+            "type": "data_input",
+            "uuid": "ab5e19b0-ce35-4e54-a55e-f75243c86e3d",
+            "when": null,
+            "workflow_outputs": []
+        },
+        "1": {
+            "annotation": "",
+            "content_id": "toolshed.g2.bx.psu.edu/repos/csbl/repeatmodeler/repeatmodeler/2.0.4+galaxy1",
+            "errors": null,
+            "id": 1,
+            "input_connections": {
+                "input_file": {
+                    "id": 0,
+                    "output_name": "output"
+                }
+            },
+            "inputs": [],
+            "label": null,
+            "name": "RepeatModeler",
+            "outputs": [
+                {
+                    "name": "sequences",
+                    "type": "fasta"
+                },
+                {
+                    "name": "seeds",
+                    "type": "stockholm"
+                }
+            ],
+            "position": {
+                "left": 230,
+                "top": 10
+            },
+            "post_job_actions": {},
+            "tool_id": "toolshed.g2.bx.psu.edu/repos/csbl/repeatmodeler/repeatmodeler/2.0.4+galaxy1",
+            "tool_shed_repository": {
+                "changeset_revision": "8661b2607b7e",
+                "name": "repeatmodeler",
+                "owner": "csbl",
+                "tool_shed": "toolshed.g2.bx.psu.edu"
+            },
+            "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"input_file\": null, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+            "tool_version": "2.0.4+galaxy1",
+            "type": "tool",
+            "uuid": "9312ba36-4275-4d40-8ba6-95eea1b23b11",
+            "when": null,
+            "workflow_outputs": [
+                {
+                    "output_name": "sequences",
+                    "label": "sequences"
+                },
+                {
+                    "output_name": "seeds",
+                    "label": "seeds"
+                }
+            ]
+        },
+        "2": {
+            "annotation": "",
+            "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/repeat_masker/repeatmasker_wrapper/4.1.5+galaxy0",
+            "errors": null,
+            "id": 2,
+            "input_connections": {
+                "input_fasta": {
+                    "id": 1,
+                    "output_name": "sequences"
+                }
+            },
+            "inputs": [],
+            "label": null,
+            "name": "RepeatMasker",
+            "outputs": [
+                {
+                    "name": "output_masked_genome",
+                    "type": "fasta"
+                },
+                {
+                    "name": "output_log",
+                    "type": "tabular"
+                },
+                {
+                    "name": "output_table",
+                    "type": "txt"
+                },
+                {
+                    "name": "output_repeat_catalog",
+                    "type": "txt"
+                },
+                {
+                    "name": "output_gff",
+                    "type": "gff"
+                }
+            ],
+            "position": {
+                "left": 450,
+                "top": 10
+            },
+            "post_job_actions": {},
+            "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/repeat_masker/repeatmasker_wrapper/4.1.5+galaxy0",
+            "tool_shed_repository": {
+                "changeset_revision": "ba6d2c32f797",
+                "name": "repeat_masker",
+                "owner": "bgruening",
+                "tool_shed": "toolshed.g2.bx.psu.edu"
+            },
+            "tool_state": "{\"__input_ext\": \"input\", \"advanced\": {\"is_only\": false, \"is_clip\": false, \"no_is\": false, \"rodspec\": false, \"primspec\": false, \"nolow\": false, \"noint\": false, \"norna\": false, \"alu\": false, \"div\": false, \"search_speed\": \"\", \"frag\": \"40000\", \"gc\": null, \"gccalc\": false, \"nocut\": false, \"xout\": false, \"keep_alignments\": false, \"invert_alignments\": false, \"poly\": false}, \"chromInfo\": \"/shared/ifbstor1/galaxy/mutable-config/tool-data/shared/ucsc/chrom/?.len\", \"excln\": true, \"gff\": true, \"input_fasta\": null, \"repeat_source\": {\"source_type\": \"dfam\", \"__current_case__\": 0, \"species_source\": {\"species_from_list\": \"no\", \"__current_case__\": 1, \"species_name\": \"\"}}, \"xsmall\": true, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+            "tool_version": "4.1.5+galaxy0",
+            "type": "tool",
+            "uuid": "e6c8e6a1-efe8-4291-b12b-5fdb3795b6ca",
+            "when": null,
+            "workflow_outputs": [
+                {
+                    "output_name": "output_masked_genome",
+                    "label": "output_masked_genome"
+                },
+                {
+                    "output_name": "output_log",
+                    "label": "output_log"
+                },
+                {
+                    "output_name": "output_table",
+                    "label": "output_table"
+                },
+                {
+                    "output_name": "output_repeat_catalog",
+                    "label": "output_repeat_catalog"
+                },
+                {
+                    "output_name": "output_gff",
+                    "label": "output_gff"
+                }
+            ]
+        }
+    },
+    "tags": [],
+    "uuid": "f25be8fa-7823-456f-9707-a497703f48d7",
+    "version": 0
+}