Repository 'proteomics_novel_peptide_filter_workflow'
hg clone https://toolshed.g2.bx.psu.edu/repos/galaxyp/proteomics_novel_peptide_filter_workflow

Changeset 0:cb2a42d4a5ac (2014-03-17)
Commit message:
Initial upload
added:
README.rst
proteomics_novel_peptide_filter_workflow.ga
repository_dependencies.xml
b
diff -r 000000000000 -r cb2a42d4a5ac README.rst
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/README.rst Mon Mar 17 15:55:58 2014 -0500
b
@@ -0,0 +1,46 @@
+This package contains a Galaxy workflow that determines if peptides identified from MS searches are present in the reference proteome.  
+Tool also allows for peptide annotation, for each novel peptide, by retrieving accession headers for those polypeptide sequences that exactly match the novel peptide.
+
+See http://www.galaxyproject.org for information about the Galaxy Project.
+
+
+Availability
+============
+
+This workflow is available to download and/or install from the main
+Galaxy Tool Shed:
+
+http://toolshed.g2.bx.psu.edu/view/galaxyp/proteomics_novel_peptide_filter_workflow
+
+
+Reference Data
+==============
+
+For Human RNAseq data this workflow was tested using reference data from:
+
+* ftp://ftp.ensembl.org/pub/release-73/fasta/homo_sapiens/pep/Homo_sapiens.GRCh37.73.pep.all.fa.gz
+
+
+For Mouse RNAseq data this workflow was tested using reference data from:
+
+* ftp://ftp.ensembl.org/pub/release-73/fasta/mus_musculus/pep/Mus_musculus.GRCm38.73.pep.all.fa.gz
+
+
+Dependencies
+============
+
+These dependencies should be resolved automatically via the Galaxy Tool Shed:
+
+* http://toolshed.g2.bx.psu.edu/view//jjohnson/find_in_reference
+
+
+History
+=======
+
+======= ======================================================================
+Version Changes
+------- ----------------------------------------------------------------------
+v0.0.1  - Initial release to Tool Shed (March, 2014)
+======= ======================================================================
+
+
b
diff -r 000000000000 -r cb2a42d4a5ac proteomics_novel_peptide_filter_workflow.ga
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/proteomics_novel_peptide_filter_workflow.ga Mon Mar 17 15:55:58 2014 -0500
[
b'@@ -0,0 +1,213 @@\n+{\n+    "a_galaxy_workflow": "true", \n+    "annotation": "", \n+    "format-version": "0.1", \n+    "name": "Example Novel Peptide Filter", \n+    "steps": {\n+        "0": {\n+            "annotation": "", \n+            "id": 0, \n+            "input_connections": {}, \n+            "inputs": [\n+                {\n+                    "description": "", \n+                    "name": "Ensembl pep.all (Reference Protein FASTA file)"\n+                }\n+            ], \n+            "name": "Input dataset", \n+            "outputs": [], \n+            "position": {\n+                "left": 200, \n+                "top": 311\n+            }, \n+            "tool_errors": null, \n+            "tool_id": null, \n+            "tool_state": "{\\"name\\": \\"Ensembl pep.all (Reference Protein FASTA file)\\"}", \n+            "tool_version": null, \n+            "type": "data_input", \n+            "user_outputs": []\n+        }, \n+        "1": {\n+            "annotation": "", \n+            "id": 1, \n+            "input_connections": {}, \n+            "inputs": [\n+                {\n+                    "description": "", \n+                    "name": "cRAP database of MS contaminants"\n+                }\n+            ], \n+            "name": "Input dataset", \n+            "outputs": [], \n+            "position": {\n+                "left": 199, \n+                "top": 407\n+            }, \n+            "tool_errors": null, \n+            "tool_id": null, \n+            "tool_state": "{\\"name\\": \\"cRAP database of MS contaminants\\"}", \n+            "tool_version": null, \n+            "type": "data_input", \n+            "user_outputs": []\n+        }, \n+        "2": {\n+            "annotation": "", \n+            "id": 2, \n+            "input_connections": {}, \n+            "inputs": [\n+                {\n+                    "description": "", \n+                    "name": "MS Search Peptide ID results"\n+                }\n+            ], \n+            "name": "Input dataset", \n+            "outputs": [], \n+            "position": {\n+                "left": 644, \n+                "top": 182\n+            }, \n+            "tool_errors": null, \n+            "tool_id": null, \n+            "tool_state": "{\\"name\\": \\"MS Search Peptide ID results\\"}", \n+            "tool_version": null, \n+            "type": "data_input", \n+            "user_outputs": []\n+        }, \n+        "3": {\n+            "annotation": "", \n+            "id": 3, \n+            "input_connections": {\n+                "input1": {\n+                    "id": 0, \n+                    "output_name": "output"\n+                }, \n+                "queries_0|input2": {\n+                    "id": 1, \n+                    "output_name": "output"\n+                }\n+            }, \n+            "inputs": [], \n+            "name": "Concatenate datasets", \n+            "outputs": [\n+                {\n+                    "name": "out_file1", \n+                    "type": "input"\n+                }\n+            ], \n+            "position": {\n+                "left": 420, \n+                "top": 311\n+            }, \n+            "post_job_actions": {}, \n+            "tool_errors": null, \n+            "tool_id": "cat1", \n+            "tool_state": "{\\"__page__\\": 0, \\"__rerun_remap_job_id__\\": null, \\"input1\\": \\"null\\", \\"chromInfo\\": \\"\\\\\\"/website/galaxy.msi.umn.edu/PRODUCTION/tool-data/shared/ucsc/chrom/GRCm38_canon.len\\\\\\"\\", \\"queries\\": \\"[{\\\\\\"input2\\\\\\": null, \\\\\\"__index__\\\\\\": 0}]\\"}", \n+            "tool_version": "1.0.0", \n+            "type": "tool", \n+            "user_outputs": []\n+        }, \n+        "4": {\n+            "annotation": "", \n+            "id": 4, \n+            "input_connections": {\n+                "input": {\n+                    "id": 3, \n+                    "output_name": "out_file1"\n+                }\n+            }, \n+            "inputs": [], \n+            "name": "FASTA-to-Tabular", \n+            "outputs": [\n+                {\n+                    "name": "'..b'du/PRODUCTION/tool-data/shared/ucsc/chrom/GRCm38_canon.len\\\\\\"\\", \\"__rerun_remap_job_id__\\": null}", \n+            "tool_version": "1.1.0", \n+            "type": "tool", \n+            "user_outputs": []\n+        }, \n+        "5": {\n+            "annotation": "", \n+            "id": 5, \n+            "input_connections": {\n+                "input": {\n+                    "id": 2, \n+                    "output_name": "output"\n+                }, \n+                "reference": {\n+                    "id": 4, \n+                    "output_name": "output"\n+                }\n+            }, \n+            "inputs": [], \n+            "name": "find in reference", \n+            "outputs": [\n+                {\n+                    "name": "found", \n+                    "type": "tabular"\n+                }, \n+                {\n+                    "name": "novel", \n+                    "type": "tabular"\n+                }\n+            ], \n+            "position": {\n+                "left": 898, \n+                "top": 180\n+            }, \n+            "post_job_actions": {}, \n+            "tool_errors": null, \n+            "tool_id": "toolshed.g2.bx.psu.edu/repos/jjohnson/find_in_reference/find_in_reference/0.0.1", \n+            "tool_state": "{\\"__page__\\": 0, \\"reference\\": \\"null\\", \\"column\\": \\"{\\\\\\"set\\\\\\": \\\\\\"yes\\\\\\", \\\\\\"reference_column\\\\\\": {\\\\\\"__class__\\\\\\": \\\\\\"UnvalidatedValue\\\\\\", \\\\\\"value\\\\\\": \\\\\\"2\\\\\\"}, \\\\\\"input_column\\\\\\": {\\\\\\"__class__\\\\\\": \\\\\\"UnvalidatedValue\\\\\\", \\\\\\"value\\\\\\": \\\\\\"2\\\\\\"}, \\\\\\"__current_case__\\\\\\": 1}\\", \\"outputs\\": \\"\\\\\\"novel\\\\\\"\\", \\"case_insensitive\\": \\"\\\\\\"True\\\\\\"\\", \\"annotate\\": \\"{\\\\\\"from_ref\\\\\\": \\\\\\"no\\\\\\", \\\\\\"__current_case__\\\\\\": 0}\\", \\"input\\": \\"null\\", \\"chromInfo\\": \\"\\\\\\"/website/galaxy.msi.umn.edu/PRODUCTION/tool-data/shared/ucsc/chrom/GRCm38_canon.len\\\\\\"\\", \\"__rerun_remap_job_id__\\": null}", \n+            "tool_version": "0.0.1", \n+            "type": "tool", \n+            "user_outputs": []\n+        }, \n+        "6": {\n+            "annotation": "", \n+            "id": 6, \n+            "input_connections": {\n+                "input": {\n+                    "id": 5, \n+                    "output_name": "novel"\n+                }, \n+                "reference": {\n+                    "id": 4, \n+                    "output_name": "output"\n+                }\n+            }, \n+            "inputs": [], \n+            "name": "find in reference", \n+            "outputs": [\n+                {\n+                    "name": "found", \n+                    "type": "tabular"\n+                }, \n+                {\n+                    "name": "novel", \n+                    "type": "tabular"\n+                }\n+            ], \n+            "position": {\n+                "left": 1129, \n+                "top": 295\n+            }, \n+            "post_job_actions": {}, \n+            "tool_errors": null, \n+            "tool_id": "toolshed.g2.bx.psu.edu/repos/jjohnson/find_in_reference/find_in_reference/0.0.1", \n+            "tool_state": "{\\"__page__\\": 0, \\"reference\\": \\"null\\", \\"column\\": \\"{\\\\\\"set\\\\\\": \\\\\\"yes\\\\\\", \\\\\\"reference_column\\\\\\": {\\\\\\"__class__\\\\\\": \\\\\\"UnvalidatedValue\\\\\\", \\\\\\"value\\\\\\": \\\\\\"2\\\\\\"}, \\\\\\"input_column\\\\\\": {\\\\\\"__class__\\\\\\": \\\\\\"UnvalidatedValue\\\\\\", \\\\\\"value\\\\\\": \\\\\\"2\\\\\\"}, \\\\\\"__current_case__\\\\\\": 1}\\", \\"outputs\\": \\"\\\\\\"found\\\\\\"\\", \\"case_insensitive\\": \\"\\\\\\"True\\\\\\"\\", \\"annotate\\": \\"{\\\\\\"annotation_col_sep\\\\\\": \\\\\\",\\\\\\", \\\\\\"annotation_separator\\\\\\": \\\\\\";\\\\\\", \\\\\\"from_ref\\\\\\": \\\\\\"yes\\\\\\", \\\\\\"__current_case__\\\\\\": 1, \\\\\\"annotation_columns\\\\\\": {\\\\\\"__class__\\\\\\": \\\\\\"UnvalidatedValue\\\\\\", \\\\\\"value\\\\\\": [\\\\\\"1\\\\\\"]}}\\", \\"input\\": \\"null\\", \\"chromInfo\\": \\"\\\\\\"/website/galaxy.msi.umn.edu/PRODUCTION/tool-data/shared/ucsc/chrom/GRCm38_canon.len\\\\\\"\\", \\"__rerun_remap_job_id__\\": null}", \n+            "tool_version": "0.0.1", \n+            "type": "tool", \n+            "user_outputs": []\n+        }\n+    }\n+}\n\\ No newline at end of file\n'
b
diff -r 000000000000 -r cb2a42d4a5ac repository_dependencies.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/repository_dependencies.xml Mon Mar 17 15:55:58 2014 -0500
b
@@ -0,0 +1,4 @@
+<?xml version="1.0"?>
+<repositories description="Required tools for proteomics_rnaseq_splice_db_workflow">
+    <repository name="find_in_reference" owner="jjohnson" toolshed="http://toolshed.g2.bx.psu.edu" changeset_revision="e7e56b51d156" />
+</repositories>