# HG changeset patch
# User pieter.lukasse@wur.nl
# Date 1389177556 -3600
# Node ID d50f079096ee1e381b939d7dcb7e858811946137
Push to main toolshed
diff -r 000000000000 -r d50f079096ee Csv2Apml.jar
Binary file Csv2Apml.jar has changed
diff -r 000000000000 -r d50f079096ee IsoFix.jar
Binary file IsoFix.jar has changed
diff -r 000000000000 -r d50f079096ee LICENSE
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/LICENSE Wed Jan 08 11:39:16 2014 +0100
@@ -0,0 +1,202 @@
+
+ Apache License
+ Version 2.0, January 2004
+ http://www.apache.org/licenses/
+
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+ 1. Definitions.
+
+ "License" shall mean the terms and conditions for use, reproduction,
+ and distribution as defined by Sections 1 through 9 of this document.
+
+ "Licensor" shall mean the copyright owner or entity authorized by
+ the copyright owner that is granting the License.
+
+ "Legal Entity" shall mean the union of the acting entity and all
+ other entities that control, are controlled by, or are under common
+ control with that entity. For the purposes of this definition,
+ "control" means (i) the power, direct or indirect, to cause the
+ direction or management of such entity, whether by contract or
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
+ outstanding shares, or (iii) beneficial ownership of such entity.
+
+ "You" (or "Your") shall mean an individual or Legal Entity
+ exercising permissions granted by this License.
+
+ "Source" form shall mean the preferred form for making modifications,
+ including but not limited to software source code, documentation
+ source, and configuration files.
+
+ "Object" form shall mean any form resulting from mechanical
+ transformation or translation of a Source form, including but
+ not limited to compiled object code, generated documentation,
+ and conversions to other media types.
+
+ "Work" shall mean the work of authorship, whether in Source or
+ Object form, made available under the License, as indicated by a
+ copyright notice that is included in or attached to the work
+ (an example is provided in the Appendix below).
+
+ "Derivative Works" shall mean any work, whether in Source or Object
+ form, that is based on (or derived from) the Work and for which the
+ editorial revisions, annotations, elaborations, or other modifications
+ represent, as a whole, an original work of authorship. For the purposes
+ of this License, Derivative Works shall not include works that remain
+ separable from, or merely link (or bind by name) to the interfaces of,
+ the Work and Derivative Works thereof.
+
+ "Contribution" shall mean any work of authorship, including
+ the original version of the Work and any modifications or additions
+ to that Work or Derivative Works thereof, that is intentionally
+ submitted to Licensor for inclusion in the Work by the copyright owner
+ or by an individual or Legal Entity authorized to submit on behalf of
+ the copyright owner. For the purposes of this definition, "submitted"
+ means any form of electronic, verbal, or written communication sent
+ to the Licensor or its representatives, including but not limited to
+ communication on electronic mailing lists, source code control systems,
+ and issue tracking systems that are managed by, or on behalf of, the
+ Licensor for the purpose of discussing and improving the Work, but
+ excluding communication that is conspicuously marked or otherwise
+ designated in writing by the copyright owner as "Not a Contribution."
+
+ "Contributor" shall mean Licensor and any individual or Legal Entity
+ on behalf of whom a Contribution has been received by Licensor and
+ subsequently incorporated within the Work.
+
+ 2. Grant of Copyright License. Subject to the terms and conditions of
+ this License, each Contributor hereby grants to You a perpetual,
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+ copyright license to reproduce, prepare Derivative Works of,
+ publicly display, publicly perform, sublicense, and distribute the
+ Work and such Derivative Works in Source or Object form.
+
+ 3. Grant of Patent License. Subject to the terms and conditions of
+ this License, each Contributor hereby grants to You a perpetual,
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+ (except as stated in this section) patent license to make, have made,
+ use, offer to sell, sell, import, and otherwise transfer the Work,
+ where such license applies only to those patent claims licensable
+ by such Contributor that are necessarily infringed by their
+ Contribution(s) alone or by combination of their Contribution(s)
+ with the Work to which such Contribution(s) was submitted. If You
+ institute patent litigation against any entity (including a
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
+ or a Contribution incorporated within the Work constitutes direct
+ or contributory patent infringement, then any patent licenses
+ granted to You under this License for that Work shall terminate
+ as of the date such litigation is filed.
+
+ 4. Redistribution. You may reproduce and distribute copies of the
+ Work or Derivative Works thereof in any medium, with or without
+ modifications, and in Source or Object form, provided that You
+ meet the following conditions:
+
+ (a) You must give any other recipients of the Work or
+ Derivative Works a copy of this License; and
+
+ (b) You must cause any modified files to carry prominent notices
+ stating that You changed the files; and
+
+ (c) You must retain, in the Source form of any Derivative Works
+ that You distribute, all copyright, patent, trademark, and
+ attribution notices from the Source form of the Work,
+ excluding those notices that do not pertain to any part of
+ the Derivative Works; and
+
+ (d) If the Work includes a "NOTICE" text file as part of its
+ distribution, then any Derivative Works that You distribute must
+ include a readable copy of the attribution notices contained
+ within such NOTICE file, excluding those notices that do not
+ pertain to any part of the Derivative Works, in at least one
+ of the following places: within a NOTICE text file distributed
+ as part of the Derivative Works; within the Source form or
+ documentation, if provided along with the Derivative Works; or,
+ within a display generated by the Derivative Works, if and
+ wherever such third-party notices normally appear. The contents
+ of the NOTICE file are for informational purposes only and
+ do not modify the License. You may add Your own attribution
+ notices within Derivative Works that You distribute, alongside
+ or as an addendum to the NOTICE text from the Work, provided
+ that such additional attribution notices cannot be construed
+ as modifying the License.
+
+ You may add Your own copyright statement to Your modifications and
+ may provide additional or different license terms and conditions
+ for use, reproduction, or distribution of Your modifications, or
+ for any such Derivative Works as a whole, provided Your use,
+ reproduction, and distribution of the Work otherwise complies with
+ the conditions stated in this License.
+
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
+ any Contribution intentionally submitted for inclusion in the Work
+ by You to the Licensor shall be under the terms and conditions of
+ this License, without any additional terms or conditions.
+ Notwithstanding the above, nothing herein shall supersede or modify
+ the terms of any separate license agreement you may have executed
+ with Licensor regarding such Contributions.
+
+ 6. Trademarks. This License does not grant permission to use the trade
+ names, trademarks, service marks, or product names of the Licensor,
+ except as required for reasonable and customary use in describing the
+ origin of the Work and reproducing the content of the NOTICE file.
+
+ 7. Disclaimer of Warranty. Unless required by applicable law or
+ agreed to in writing, Licensor provides the Work (and each
+ Contributor provides its Contributions) on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+ implied, including, without limitation, any warranties or conditions
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+ PARTICULAR PURPOSE. You are solely responsible for determining the
+ appropriateness of using or redistributing the Work and assume any
+ risks associated with Your exercise of permissions under this License.
+
+ 8. Limitation of Liability. In no event and under no legal theory,
+ whether in tort (including negligence), contract, or otherwise,
+ unless required by applicable law (such as deliberate and grossly
+ negligent acts) or agreed to in writing, shall any Contributor be
+ liable to You for damages, including any direct, indirect, special,
+ incidental, or consequential damages of any character arising as a
+ result of this License or out of the use or inability to use the
+ Work (including but not limited to damages for loss of goodwill,
+ work stoppage, computer failure or malfunction, or any and all
+ other commercial damages or losses), even if such Contributor
+ has been advised of the possibility of such damages.
+
+ 9. Accepting Warranty or Additional Liability. While redistributing
+ the Work or Derivative Works thereof, You may choose to offer,
+ and charge a fee for, acceptance of support, warranty, indemnity,
+ or other liability obligations and/or rights consistent with this
+ License. However, in accepting such obligations, You may act only
+ on Your own behalf and on Your sole responsibility, not on behalf
+ of any other Contributor, and only if You agree to indemnify,
+ defend, and hold each Contributor harmless for any liability
+ incurred by, or claims asserted against, such Contributor by reason
+ of your accepting any such warranty or additional liability.
+
+ END OF TERMS AND CONDITIONS
+
+ APPENDIX: How to apply the Apache License to your work.
+
+ To apply the Apache License to your work, attach the following
+ boilerplate notice, with the fields enclosed by brackets "[]"
+ replaced with your own identifying information. (Don't include
+ the brackets!) The text should be enclosed in the appropriate
+ comment syntax for the file format. We also recommend that a
+ file or class name and description of purpose be included on the
+ same "printed page" as the copyright notice for easier
+ identification within third-party archives.
+
+ Copyright [yyyy] [name of copyright owner]
+
+ Licensed under the Apache License, Version 2.0 (the "License");
+ you may not use this file except in compliance with the License.
+ You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
diff -r 000000000000 -r d50f079096ee MsFilt.jar
Binary file MsFilt.jar has changed
diff -r 000000000000 -r d50f079096ee NOTICE
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/NOTICE Wed Jan 08 11:39:16 2014 +0100
@@ -0,0 +1,13 @@
+PRIMS proteomics toolset & Galaxy wrappers
+==========================================
+
+Tools and wrappers for the PRIMS proteomics toolset.
+Suite of custom tools to enable data processing and
+protein inference for labeled and label-free Mass Spectrometry proteomics data.
+Can be used in combination with PRIMS MASSCOMB (prims_masscomb package).
+Copyright 2010-2013 by Pieter Lukasse, Plant Research International (PRI),
+Wageningen, The Netherlands. All rights reserved. See the license text below.
+
+Galaxy wrappers and installation are available from the Galaxy Tool Shed at:
+http://toolshed.g2.bx.psu.edu/view/pieterlukasse/prims_proteomics
+
diff -r 000000000000 -r d50f079096ee NapQ.jar
Binary file NapQ.jar has changed
diff -r 000000000000 -r d50f079096ee PRIMS.jar
Binary file PRIMS.jar has changed
diff -r 000000000000 -r d50f079096ee ProgenesisConv.jar
Binary file ProgenesisConv.jar has changed
diff -r 000000000000 -r d50f079096ee Quantifere.jar
Binary file Quantifere.jar has changed
diff -r 000000000000 -r d50f079096ee Quantiline.jar
Binary file Quantiline.jar has changed
diff -r 000000000000 -r d50f079096ee README.rst
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/README.rst Wed Jan 08 11:39:16 2014 +0100
@@ -0,0 +1,67 @@
+PRIMS-proteomics toolset & Galaxy wrappers
+==========================================
+
+Proteomics module of Plant Research International's Mass Spectrometry (PRIMS) toolsuite.
+This toolset consists of custom tools to enable data processing and
+protein inference for labeled and label-free Mass Spectrometry proteomics data.
+
+Can be used in combination with PRIMS-MASSCOMB (prims_masscomb package) and
+with PRIMV-visualization (primv_visualization package).
+
+Copyright 2010-2013 by Pieter Lukasse, Plant Research International (PRI),
+Wageningen, The Netherlands. All rights reserved. See the license text below.
+
+Galaxy wrappers and installation are available from the Galaxy Tool Shed at:
+http://toolshed.g2.bx.psu.edu/view/pieterlukasse/prims_proteomics
+
+History
+=======
+
+============== ======================================================================
+Date Changes
+-------------- ----------------------------------------------------------------------
+January 2014 * first release via Tool Shed
+November 2013 * multiple tools used internally at PRI
+end 2011 * first tool
+============== ======================================================================
+
+Tool Versioning
+===============
+
+PRIMS tools will have versions of the form X.Y.Z. Versions
+differing only after the second decimal should be completely
+compatible with each other. Breaking changes should result in an
+increment of the number before and/or after the first decimal. All
+tools of version less than 1.0.0 should be considered beta.
+
+
+Bug Reports & other questions
+=============================
+
+For the time being issues can be reported via the contact form at:
+http://www.wageningenur.nl/en/Persons/PNJ-Pieter-Lukasse.htm
+
+Developers, Contributions & Collaborations
+==========================================
+
+If you wish to join forces and collaborate on some of the
+tools do not hesitate to contact Pieter Lukasse via the contact form above.
+
+
+License (Apache, Version 2.0)
+=============================
+
+Copyright 2013 Pieter Lukasse, Plant Research International (PRI).
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this software except in compliance with the License.
+You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
\ No newline at end of file
diff -r 000000000000 -r d50f079096ee SedMat_cli.jar
Binary file SedMat_cli.jar has changed
diff -r 000000000000 -r d50f079096ee csv2apml.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/csv2apml.xml Wed Jan 08 11:39:16 2014 +0100
@@ -0,0 +1,127 @@
+
+ Converts MS/MS data in CSV format to APML format
+
+
+ Csv2Apml.jar
+ -peptideAndProteinMatchListCSV $peptideAndProteinMatchListCSV
+ -attributesMappingCSV $attributesMappingCSV
+ -apmlFile $apmlFile
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ Generic name,name in S1 table CSV
+mz,${mz}
+rt,${rt}
+charge,${charge}
+pepSequence,${pepSequence}
+ppidScore,${ppidScore}
+proteinAccession,${proteinAccession}
+#if $ppidTheoreticalMz != "None"
+ppidTheoreticalMz,${ppidTheoreticalMz}
+#end if
+#if $modifications != "None"
+modifications,${modifications}
+#end if
+#if $scoringSchemeName != "None"
+scoringSchemeName,${scoringSchemeName}
+#end if
+#if $statisticalMeasure != "None"
+statisticalMeasure,${statisticalMeasure}
+#end if
+#if $protSequenceLength != "None"
+protSequenceLength,${protSequenceLength}
+#end if
+#if $pepProtStart != "None"
+pepProtStart,${pepProtStart}
+#end if
+#if $pepProtEnd != "None"
+pepProtEnd,${pepProtEnd}
+#end if
+#if $sourceName != "None"
+sourceName,${sourceName}
+#end if
+
+
+
+
+
+
+
+
+
+
+.. class:: infomark
+
+This tool converts a CSV file containing MS/MS peptide identifications and their respective protein matches
+to the APML xml format.
+The identifications in APML format can be used for example to annotate unidentified MS features via SEDMAT(*).
+This format is also compatible with what is expected by other post-processing tools like Quantifere (for
+protein inference).
+
+(*)SEDMAT can use MS2 identification data
+and couple it to this MS1 data, thereby annotating the MS1 feature list with identifications.
+
+-----
+
+**Output**
+
+This tools returns the input data in APML xml format.
+
+
+
diff -r 000000000000 -r d50f079096ee datatypes_conf.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/datatypes_conf.xml Wed Jan 08 11:39:16 2014 +0100
@@ -0,0 +1,9 @@
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff -r 000000000000 -r d50f079096ee isofix.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/isofix.xml Wed Jan 08 11:39:16 2014 +0100
@@ -0,0 +1,66 @@
+
+ Identifies in-source decay peptides and corrects protein assignments
+
+
+ IsoFix.jar
+ -identificationsFile $identificationsFile
+ -outputFile $outputFile
+ -format apml
+ -rtTol $rtTol
+ -logFile $logFile
+ #if $useOriginalProteinSequences.useOriginalProteinSequencesFile == True
+ -fastaFile $useOriginalProteinSequences.fastaFile
+ #end if
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ ( createLogFile == True )
+
+
+
+
+
+
+.. class:: infomark
+
+This tool identifies in-source decay peptides and corrects protein assignments.
+
+-----
+
+**Output example**
+
+This tools returns the given input file but then with corrected protein assignments and
+in-source decay peptides identified (by a small modification in their sequence string).
+E.g. if peptide TYNSIMK is found to be an in-source decay of HETTYNSIMK, then
+its sequence is changed to HET}TYNSIMK (so the decayed part + "}" + own sequence).
+E.g. decay from both sides: YNSI, HETTYNSIMK = HET}TYNSI{MK
+
+
+
+
diff -r 000000000000 -r d50f079096ee msfilt.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/msfilt.xml Wed Jan 08 11:39:16 2014 +0100
@@ -0,0 +1,229 @@
+
+ Filters annotations based MS/MS peptide identification and annotation quality measures
+
+
+ MsFilt.jar
+ -apmlFile $apmlFile
+ -datasetCode $apmlFile.metadata.base_name
+ -rankingMetadataFile $rankingMetadataFile
+ -statisticalMeasuresConfigFile $statisticalMeasuresConfigFile
+ -annotationSourceConfigFile $annotationSourceConfigFile
+ -outApml $outputApml
+ -outNewIdsApml $outNewIdsApml
+ -outFullCSV $outputCSV
+ -outRankingTable $outRankingTable
+ -outProteinCoverageCSV $outProteinCoverageCSV
+ -fpCriteriaExpression "$fpCriteriaExpression"
+ -filterOutFPAnnotations $filterOutFPAnnotations
+ -fpCriteriaExpressionForIds "$fpCriteriaExpressionForIds"
+ -filterOutFPIds $filterOutFPIds
+ -filterOutUnannotatedAlignments $filterOutUnannotatedAlignments
+ -addRawRankingInfo $addRawRankingInfo
+ -addScaledIntensityInfo $addScaledIntensityInfo
+ -addRawIntensityInfo $addRawIntensityInfo
+ -outReport $htmlReportFile
+ -outReportPicturesPath $htmlReportFile.files_path
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ ${rankingWeightConfig}
+ ${statisticalMeasuresConfig}
+ ## start comment
+ ## iterate over the selected files and store their names in the config file
+ #for $i, $s in enumerate( $annotationSourceFiles )
+ ${s.identificationsFile}|${s.spectraFile}
+ ## also print out the datatype in the next line, based on previously configured datatype
+ #if isinstance( $s.identificationsFile.datatype, $__app__.datatypes_registry.get_datatype_by_extension('apml').__class__):
+ apml
+ #else:
+ mzid
+ #end if
+ #end for
+ ## end comment
+
+
+
+
+ ( apmlFile != None )
+
+
+ ( filterOutFPIds == True )
+
+
+ ( apmlFile != None )
+
+
+ ( apmlFile != None )
+
+
+
+ ( len(list(enumerate(annotationSourceFiles))) > 0 )
+
+
+
+
+
+
+
+.. class:: infomark
+
+This tool takes in peptide quantification results (e.g. either by SEDMAT for label-free data or by Quantiline for labeled data)
+and calculates a number of quality measures that can help in assessing the correctness of the quantification assignment and of the MS/MS peptide
+identification itself. The user can use any combination of quality measures (qm's) and statistical measures (sm's) to filter out
+low scoring entries.
+
+.. class:: infomark
+
+In the label-free data processed by SEDMAT it is possible that a feature quantification gets assigned to different peptides. This means
+we have an ambiguous assignment. In such a case
+this tool also does a ranking of the different assignments according to their quality measures so that the best scoring assignment
+gets ranked as first.
+
+-----
+
+**List of abbreviations**
+
+QM: Quality Measure
+
+SM: Statistical Measure (e.g. p-value, e-value from MS/MS identification)
+
+PSM: "Peptide to Spectrum Match" (aka peptide identification)
+
+FP: False Positive
+
+-----
+
+**Filtering options details**
+
+The FP criteria will be applied to an annotation even if the corresponding quality measures involved
+in the expression can NOT ALL be determined. QMs that cannot be determined, get the value 0 (zero) which is
+equal to giving it the average value.
+
+The output report shows some plots that visualize the filtering done. This can help in fine-tuning the right filtering
+criteria.
+
+-----
+
+**Output details**
+
+*APML output*
+
+This tools returns the given APML alignment file further annotated at the alignment level with the best ranking
+peptides of each respective alignment. This APML can be used in subsequent Galaxy tools like the proteomics tools
+from NBIC.
+
+The APML output can also be used for the Protein Inference step (see Quantifere tool).
+
+*CSV output*
+
+It also returns a CSV format output with the full quality measures and scoring and ranking details. The user could use
+this to manually determine new weights for some of the quality measures by techniques such as
+linear regression. In other words, this CSV can then be used to fine-tune the weights in a next run.
+
+Many of the quality measures (QMs) are normalized to their Standard Score (aka z-score).
+`See Standard Score for more details...`__
+
+Next to giving insight into how the ranking was established, a more complete version of this CSV file is also
+generated for tools that cannot or won't process the APML output format.
+
+Below an brief overview of the CSV and an illustration of the ranking done in case of ambiguous peptides to feature assignments
+(explained above, can happen in case of label-free data processing by SEDMAT).
+
+
+.. image:: $PATH_TO_IMAGES/msfilt_csv_out.png
+
+
+
+.. __: javascript:window.open('http://en.wikipedia.org/wiki/Standard_score','popUpWindow','height=700,width=800,left=10,top=10,resizable=yes,scrollbars=yes,toolbar=yes,menubar=no,location=no,directories=no,status=yes')
+
+
+
+
+
+
diff -r 000000000000 -r d50f079096ee napq.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/napq.xml Wed Jan 08 11:39:16 2014 +0100
@@ -0,0 +1,93 @@
+
+ 'no alignment'(alignment-free) peptide quantification
+
+
+ NapQ.jar
+ -identificationsConfigFile $identificationsConfigFile
+ -namingConventionCodesForSamples $namingConventionCodesForSamples
+ #if $is2D_LC_MS.fractions == True
+ -namingConventionCodesForFractions $is2D_LC_MS.namingConventionCodesForFractions
+ #end if
+ -outputApml $outputApml
+ -outputTsv $outputTsv
+ -outReport $htmlReportFile
+ -outReportPicturesPath $htmlReportFile.files_path
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ ## start comment
+ ## iterate over the selected files and store their names in the config file
+ #for $i, $s in enumerate( $identificationFileList )
+ ${s.identificationsFile}|${s.spectraFile}
+ ## also print out the datatype in the next line, based on previously configured datatype
+ #if isinstance( $s.identificationsFile.datatype, $__app__.datatypes_registry.get_datatype_by_extension('apml').__class__):
+ apml
+ #else:
+ mzid
+ #end if
+ #end for
+ ## end comment
+
+
+
+
+
+
+
+
+
+
+
+
+.. class:: infomark
+
+This tool takes in multiple peptide identification result files that have peptide identifications
+coupled to some quantification (e.g. precursor intensity information or for example data coming
+from MS^E acquisition where peptide identification and quantification are done in the same run and reported together).
+Then, based on the given experiment design parameters (i.e. how the result files related back to
+replicate runs and samples), it produces a new file in which the peptides are reported with
+their calculated quantifications at the sample level.
+
+The figure below explains this:
+
+.. image:: $PATH_TO_IMAGES/napq_overview.png
+
+
+
+
+
+
+
+
diff -r 000000000000 -r d50f079096ee prims_proteomics_datatypes.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/prims_proteomics_datatypes.py Wed Jan 08 11:39:16 2014 +0100
@@ -0,0 +1,42 @@
+"""
+PRIMS proteomics classes for types defined in datatypes_conf.xml
+"""
+import logging
+import re
+from galaxy.datatypes.data import *
+from galaxy.datatypes.xml import *
+from galaxy.datatypes.sniff import *
+from galaxy.datatypes.binary import *
+from galaxy.datatypes.interval import *
+
+log = logging.getLogger(__name__)
+
+
+class ProteomicsXml(GenericXml):
+ """ An enhanced XML datatype used to reuse code across several
+ proteomic/mass-spec datatypes. (this part of the code is taken from protk proteomics datatypes package) """
+
+ def sniff(self, filename):
+ """ Determines whether the file is the correct XML type. """
+ with open(filename, 'r') as contents:
+ while True:
+ line = contents.readline()
+ if line == None or not line.startswith('
+ Converts Progenesis aligned feature lists in CSV format to APML
+
+
+ ProgenesisConv.jar
+ -progenesisFile $progenesisFile
+ -apmlFile $apmlFile
+ #if $multipleScoringSchemes.containsMultipleScoringSchemes == True
+ -scoringSchemeNameColumn $multipleScoringSchemes.scoringSchemeNameColumn
+ #end if
+ #if $statisticalMeasure.containsStatisticalMeasure == True
+ -statisticalMeasureColumn $statisticalMeasure.statisticalMeasureColumn
+ #end if
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+.. class:: infomark
+
+This tool converts a Progenesis CSV file to the APML xml format.
+This format can be used to submit the data for annotation by SEDMAT. SEDMAT can use MS2 identification data
+and couple it to this MS1 data, thereby annotating the MS1 feature list with identifications.
+
+-----
+
+**Output example**
+
+This tools returns APML output that can be used as input for the SEDMAT tool.
+
+
+
diff -r 000000000000 -r d50f079096ee quantifere.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/quantifere.xml Wed Jan 08 11:39:16 2014 +0100
@@ -0,0 +1,206 @@
+
+ Protein Inference by Peptide Quantification patterns
+
+
+ Quantifere.jar
+ -annotatedQuantificationFilesList $annotatedQuantificationFilesList
+ -identificationFilesList $identificationFilesList
+ -statisticalMeasuresConfigFile $statisticalMeasuresConfigFile
+ -quantificationDataToUse $quantificationDataToUse
+ -minCorrel $minCorrel
+ -minProtCoverage $minProtCoverage
+ -minAboveAverageHits $minAboveAverageHits
+ -minNrIdsForInferencePeptide $minNrIdsForInferencePeptide
+ -refineModel $refineModel
+ -functionalAnnotationCSV $functionalAnnotationCSV
+ -outputCSV $outputCSV
+ -outputInferenceLogCSV $outputInferenceLogCSV
+ -outputSummaryAnnotationCSV $outputSummaryAnnotationCSV
+ -outReport $htmlReportFile
+ -outReportPicturesPath $htmlReportFile.files_path
+ #if $is2D_LC_MS.fractions == True
+ -namingConventionCodesForFractions $is2D_LC_MS.namingConventionCodesForFractions
+ #end if
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ ## start comment
+ ## iterate over the selected files and store their names in the config file
+ #for $i, $s in enumerate( $annotatedQuantificationFiles )
+ ${s.annotatedQuantificationFile}
+ #end for
+ ## end comment
+
+ ## start comment
+ ## iterate over the selected files and store their names in the config file
+ #for $i, $s in enumerate( $identificationFiles )
+ ${s.identificationFile}
+ ## also print out the datatype in the next line, based on previously configured datatype
+ #if isinstance( $s.identificationFile.datatype, $__app__.datatypes_registry.get_datatype_by_extension('apml').__class__):
+ apml
+ #else:
+ mzid
+ #end if
+ #end for
+ ## end comment
+ ## start comment
+ ${statisticalMeasuresConfig}
+
+
+
+
+
+
+
+ ( summaryReport == True )
+
+
+
+ ( functionalAnnotationCSV != None )
+
+
+
+
+
+
+.. class:: infomark
+
+This tool takes Peptide Quantification patterns and uses this to do Protein Inference of both Primary Protein
+identifications as well as Secondary Protein identifications. This last class of protein identifications
+can not be done by traditional protein inference methods that look only at peptide identifications and
+their quality parameters.
+
+
+-----
+
+**List of definitions**
+
+Primary Protein identification: protein identification belonging to the minimum set of proteins needed
+to account for the observed peptides.
+
+Secondary Protein identification: extra protein identifications that do not below to the minimum set
+of proteins mentioned above.
+
+raw intensities : is the intensity value resulting from the integration of the feature peak area
+
+apex intensities: is the intensity value as on the highest point of the feature peak
+
+normalized intensities : is the intensity normalized by some means
+
+-----
+
+**Minimum correlation in a cluster**
+
+TODO - add doc.
+
+-----
+
+**Output details**
+
+*Proteins list (CSV)*
+
+This is the list of primary and secondary proteins and their calculated inference score. Proteins
+with exactly the same peptide hits are also grouped together and labeled as primary_group and secondary_group
+instead of simply primary and secondary.
+
+
+*Inference log (CSV)*
+
+This CSV table shows all data, both inferred and ruled out proteins. This can be used by the user to
+troubleshoot the inference process and understand why certain proteins might have been ruled out.
+The CSV is provided in such a format that the data can easily be explored in a Cytoscape network.
+
+The figure below shows an example of the data being explored in Cytoscape using also the
+`Cytoscape chartplugin`_ to visualize the quantification data when selecting the peptide nodes.
+
+.. image:: $PATH_TO_IMAGES/quantifere_cyto_out.png
+
+
+.. _Cytoscape chartplugin: http://apps.cytoscape.org/apps/chartplugin
+
+
+
+
+
diff -r 000000000000 -r d50f079096ee quantiline.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/quantiline.xml Wed Jan 08 11:39:16 2014 +0100
@@ -0,0 +1,62 @@
+
+ Labeled ms/ms data pre-processing for Protein Quantification (and Inference) pipelines
+
+
+ Quantiline.jar
+ -ppidsFileName $ppidsFileName
+ -spectraDataFile $spectraDataFile
+ -ppidsInputFormat MZID
+ -labelMzValues "$labelMzValues"
+ -labelmTol $labelmTol
+ -outputFile $outputFile
+ -outReport $outReport
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+.. class:: infomark
+
+This tool can read spectra files (mzML) and their respective identification files (mzIdentML) and based
+on the configured label masses produce a file that contains the merged information:
+peptides and their quantification based on label fragment intensity values read from the spectrum in which they
+were identified.
+
+In other words, it produces the peptide (relative) quantification file. This file can subsequently be used
+by other tools for protein inference and protein quantification (e.g. Quantifere).
+
+
+-----
+
+**Output details**
+
+*Peptide quantification file (APML)*
+
+This is the list of peptides with their (relative) quantification based on the labels and their
+intensities found in the label peaks of the corresponding spectrum.
+
+
+
+
+
+
diff -r 000000000000 -r d50f079096ee repository_dependencies.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/repository_dependencies.xml Wed Jan 08 11:39:16 2014 +0100
@@ -0,0 +1,5 @@
+
+
+
+
+
diff -r 000000000000 -r d50f079096ee sedmat.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/sedmat.xml Wed Jan 08 11:39:16 2014 +0100
@@ -0,0 +1,144 @@
+
+ Matches MS and MS/MS results
+
+
+ SedMat_cli.jar
+ -pl $inputMS
+ -plInputFormat apml
+ -ppids $fileType.inputFormatType.ppidsFile
+ -ppidsFileGrouping $fileType.type
+ -ppidsInputFormat $fileType.inputFormatType.ppidsInputFormat
+ -ppidsFileDescription $fileType.inputFormatType.ppidsFile.name
+ #if $fileType.inputFormatType.ppidsInputFormat == "mzid"
+ -spectraDataFile $fileType.inputFormatType.spectraDataFile
+ #end if
+ -out $outputData
+ -outUnmatchedMS2 $outUnmatchedMS2
+ -mtol $mtol
+ -rttol $rttol
+ -rtShiftDetectionWindow $rtShiftDetectionWindow
+ -matchOnSameSourceOnly $matchOnSameSourceOnly
+ -chargeStatesToGenerate $chargeStatesToGenerate
+ -outReport $htmlReportFile
+ -outReportPicturesPath $htmlReportFile.files_path
+ #if $troubleshoot1.troubleshootPeakLocations == True
+ -troubleshootPeakLocations YES
+ -mStart $troubleshoot1.mStart
+ -mEnd $troubleshoot1.mEnd
+ -rtStart $troubleshoot1.rtStart
+ -rtEnd $troubleshoot1.rtEnd
+ -filterSourceName $troubleshoot1.filterSourceName
+ #end if
+ #if $matchOnNamingConvention.match == True
+ -matchOnNamingConvention YES
+ -namingConventionCodesForMatching $matchOnNamingConvention.namingConventionCodesForMatching
+ #end if
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ ( summaryReport == True )
+
+
+
+
+
+
+
+
+
+.. class:: infomark
+
+This tool matches MS and MS/MS results. SEDMAT stands for "Single Experiment Data Matching Tool".
+It can match peaks found in the MS spectra with the peptides found using the MS/MS spectra.
+The result is the list of MS peaks annotated with peptides and proteins.
+
+-----
+
+**Output example**
+
+This tools returns APML output, a Cytoscape network (.xgmml) of the matches and Retention Time plots (.pdf).
+
+
+
diff -r 000000000000 -r d50f079096ee static/images/msfilt_csv_out.png
Binary file static/images/msfilt_csv_out.png has changed
diff -r 000000000000 -r d50f079096ee static/images/napq_overview.png
Binary file static/images/napq_overview.png has changed
diff -r 000000000000 -r d50f079096ee static/images/quantifere_cyto_out.png
Binary file static/images/quantifere_cyto_out.png has changed