# HG changeset patch # User Jim Johnson # Date 1395089758 18000 # Node ID cb2a42d4a5ac3f99862f6b30a5c7bc6f9062d383 Initial upload 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 @@ -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) +======= ====================================================================== + + 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 @@ -0,0 +1,213 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "", + "format-version": "0.1", + "name": "Example Novel Peptide Filter", + "steps": { + "0": { + "annotation": "", + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "Ensembl pep.all (Reference Protein FASTA file)" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 200, + "top": 311 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"Ensembl pep.all (Reference Protein FASTA file)\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "1": { + "annotation": "", + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "cRAP database of MS contaminants" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 199, + "top": 407 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"cRAP database of MS contaminants\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "2": { + "annotation": "", + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "MS Search Peptide ID results" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 644, + "top": 182 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"MS Search Peptide ID results\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "3": { + "annotation": "", + "id": 3, + "input_connections": { + "input1": { + "id": 0, + "output_name": "output" + }, + "queries_0|input2": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [], + "name": "Concatenate datasets", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 420, + "top": 311 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "cat1", + "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}]\"}", + "tool_version": "1.0.0", + "type": "tool", + "user_outputs": [] + }, + "4": { + "annotation": "", + "id": 4, + "input_connections": { + "input": { + "id": 3, + "output_name": "out_file1" + } + }, + "inputs": [], + "name": "FASTA-to-Tabular", + "outputs": [ + { + "name": "output", + "type": "tabular" + } + ], + "position": { + "left": 640, + "top": 311 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "fasta2tab", + "tool_state": "{\"__page__\": 0, \"keep_first\": \"\\\"0\\\"\", \"descr_columns\": \"\\\"1\\\"\", \"input\": \"null\", \"chromInfo\": \"\\\"/website/galaxy.msi.umn.edu/PRODUCTION/tool-data/shared/ucsc/chrom/GRCm38_canon.len\\\"\", \"__rerun_remap_job_id__\": null}", + "tool_version": "1.1.0", + "type": "tool", + "user_outputs": [] + }, + "5": { + "annotation": "", + "id": 5, + "input_connections": { + "input": { + "id": 2, + "output_name": "output" + }, + "reference": { + "id": 4, + "output_name": "output" + } + }, + "inputs": [], + "name": "find in reference", + "outputs": [ + { + "name": "found", + "type": "tabular" + }, + { + "name": "novel", + "type": "tabular" + } + ], + "position": { + "left": 898, + "top": 180 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/jjohnson/find_in_reference/find_in_reference/0.0.1", + "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}", + "tool_version": "0.0.1", + "type": "tool", + "user_outputs": [] + }, + "6": { + "annotation": "", + "id": 6, + "input_connections": { + "input": { + "id": 5, + "output_name": "novel" + }, + "reference": { + "id": 4, + "output_name": "output" + } + }, + "inputs": [], + "name": "find in reference", + "outputs": [ + { + "name": "found", + "type": "tabular" + }, + { + "name": "novel", + "type": "tabular" + } + ], + "position": { + "left": 1129, + "top": 295 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/jjohnson/find_in_reference/find_in_reference/0.0.1", + "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}", + "tool_version": "0.0.1", + "type": "tool", + "user_outputs": [] + } + } +} \ No newline at end of file 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 @@ -0,0 +1,4 @@ + + + +