Mercurial > repos > iracooke > proteomics_datatypes
changeset 8:6ab4a0bf67df draft
Make splib a composite datatype
| author | iracooke |
|---|---|
| date | Wed, 20 May 2015 00:26:37 -0400 |
| parents | 9cfabf0b942d |
| children | 349af9298ff1 |
| files | README README.rst bundle.sh datatypes_conf.xml proteomics.py |
| diffstat | 5 files changed, 122 insertions(+), 11 deletions(-) [+] |
line wrap: on
line diff
--- a/README Sun Dec 14 22:42:08 2014 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,11 +0,0 @@ -# What is it? - -Galaxy datatype and display-application definitions for Proteomics data - -# Installation - -Install into your local galaxy instance from the main galaxy toolshed at http://toolshed.g2.bx.psu.edu/ - -˝To visualize data you will need to install the protviz visualization web application. This is available at -[https://bitbucket.org/Andrew_Brock/proteomics-visualise](https://bitbucket.org/Andrew_Brock/proteomics-visualise) -
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README.rst Wed May 20 00:26:37 2015 -0400 @@ -0,0 +1,66 @@ +Proteomics Datatypes +==================== + +Support for a proteomics and mass spectrometry datatypes for Galaxy_ + +.. _Galaxy: http://galaxyproject.org/ + + +Included Datatypes +------------------ + +================ ===================== ======= ==================================== +Class Extension Sniffer Application or Purpose +================ ===================== ======= ==================================== +Binary cps False SearchGUI_ / PeptideShaker_ +PepXML_ raw_pepxml True TPP_ Search Engine Outputs +PepXML_ peptideprophet_pepxml True TPP_ PeptideProphet Outputs +PepXML_ interprophet_pepxml True TPP_ iProphet Outputs +ProtXML_ protxml True TPP_ ProteinProphet Outputs +GenericXML trafoxml False OpenMS_ RT Transforms +GenericXML qcml_ False OpenMS_ QC Data +PepXmlReport pepxml.tsv False Tabular PepXML +ProtXmlReport protxml.tsv False Tabular ProtXML +MascotDat mascotdat False Raw Mascot Search Results +MzML_ mzml True Raw Mass Spec Data +Mgf mgf True MS/MS Spectra +IdpDB idpdb False +Wiff wiff False Raw Mass Spec Data +MzXML mzxml True Raw Mass Spec Data +MzQuantML_ mzq True HUPO standard for quant data +MzIdentML_ mzid True HUPO standard for ID data +TraML_ traml True HUPO standard for transition lists +FeatureXML featurexml False OpenMS_ +ConsensusXML consensusxml False OpenMS_ +IdXML idxml False OpenMS_ +TandemXML_ tandem False XTandem output +RAW raw False Raw Mass Spec Data +Msp_ msp True Spectral Library +SPLib_ splib True Spectral Library +Ms2 ms2 False MS/MS Spectra +XHunterAslFormat hlf False Spectral Library +================ ===================== ======= ==================================== + + +.. _qcml: http://code.google.com/p/qcml +.. _PepXML: http://tools.proteomecenter.org/wiki/index.php?title=Formats:pepXML +.. _ProtXML: http://tools.proteomecenter.org/wiki/index.php?title=Formats:protXML +.. _TPP: http://tools.proteomecenter.org/wiki/index.php?title=Software:TPP +.. _OpenMS: https://github.com/OpenMS/OpenMS +.. _SearchGUI: https://code.google.com/p/searchgui/ +.. _PeptideShaker: https://code.google.com/p/peptide-shaker/ +.. _MzML: http://www.psidev.info/mzml_1_0_0%20 +.. _MzQuantML: http://www.psidev.info/mzquantml +.. _MzIdentML: http://www.psidev.info/mzidentml +.. _TraML: http://www.psidev.info/traml +.. _TandemXML: http://www.thegpm.org/docs/X_series_output_form.pdf +.. _Msp: http://chemdata.nist.gov/mass-spc/ftp/mass-spc/PepLib.pdf +.. _SPLib: http://tools.proteomecenter.org/wiki/index.php?title=Software:SpectraST#Developer.27s_Guide + +Visualization +------------- + +This package also installs display applications for mzML, PepXML and ProtXML formats. These are designed to work with the protviz_ web application. Configuring this application requires a fair number of extra steps though. See the protviz_ documentation for more info. + +.. _protviz: https://bitbucket.org/Andrew_Brock/proteomics-visualise +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bundle.sh Wed May 20 00:26:37 2015 -0400 @@ -0,0 +1,2 @@ +tar --exclude=.DS_Store --exclude=.hgcheck --exclude=.git --exclude=*.tar --exclude=*.bz2 \ +--exclude=bundle.sh --exclude=.hg -cvf package.tar ./;bzip2 -f package.tar \ No newline at end of file
--- a/datatypes_conf.xml Sun Dec 14 22:42:08 2014 -0500 +++ b/datatypes_conf.xml Wed May 20 00:26:37 2015 -0400 @@ -46,6 +46,7 @@ <datatype extension="msp" type="galaxy.datatypes.proteomics:Msp" display_in_upload="true" /> <datatype extension="ms2" type="galaxy.datatypes.proteomics:Ms2" display_in_upload="true" /> <datatype extension="hlf" type="galaxy.datatypes.proteomics:XHunterAslFormat" mimetype="application/octet-stream" display_in_upload="true" /> + <datatype extension="splib" type="galaxy.datatypes.proteomics:SPLib" display_in_upload="true" /> </registration> <sniffers> <sniffer type="galaxy.datatypes.proteomics:MzML"/> @@ -57,5 +58,7 @@ <sniffer type="galaxy.datatypes.proteomics:TraML"/> <sniffer type="galaxy.datatypes.proteomics:MzIdentML"/> <sniffer type="galaxy.datatypes.proteomics:MzQuantML"/> + <sniffer type="galaxy.datatypes.proteomics:Msp"/> + <sniffer type="galaxy.datatypes.proteomics:SPLib"/> </sniffers> </datatypes>
--- a/proteomics.py Sun Dec 14 22:42:08 2014 -0500 +++ b/proteomics.py Wed May 20 00:26:37 2015 -0400 @@ -285,6 +285,57 @@ with open(filename, 'r') as contents: return Msp.next_line_starts_with(contents, "Name:") and Msp.next_line_starts_with(contents, "MW:") + +class SPLib( Msp ): + """SpectraST Spectral Library. Closely related to msp format""" + file_ext = "splib" + composite_type = 'auto_primary_file' + + def __init__(self, **kwd): + Msp.__init__(self, **kwd) + self.add_composite_file( 'library.splib', + description = 'Spectral Library. Contains actual library spectra', + is_binary = False ) + self.add_composite_file( 'library.spidx', + description = 'Spectrum index', is_binary = False ) + self.add_composite_file( 'library.pepidx', + description = 'Peptide index', is_binary = False) + + + def generate_primary_file( self, dataset = None ): + rval = ['<html><head><title>Spectral Library Composite Dataset </title></head><p/>'] + rval.append('<div>This composite dataset is composed of the following files:<p/><ul>') + for composite_name, composite_file in self.get_composite_files( dataset = dataset ).iteritems(): + fn = composite_name + opt_text = '' + if composite_file.optional: + opt_text = ' (optional)' + if composite_file.get('description'): + rval.append( '<li><a href="%s" type="text/plain">%s (%s)</a>%s</li>' % ( fn, fn, composite_file.get('description'), opt_text ) ) + else: + rval.append( '<li><a href="%s" type="text/plain">%s</a>%s</li>' % ( fn, fn, opt_text ) ) + rval.append( '</ul></div></html>' ) + return "\n".join( rval ) + + + + def set_peek( self, dataset, is_multi_byte=False ): + """Set the peek and blurb text""" + if not dataset.dataset.purged: + dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte ) + dataset.blurb = 'splib Spectral Library Format' + else: + dataset.peek = 'file does not exist' + dataset.blurb = 'file purged from disk' + + + def sniff(self, filename): + """ Determines whether the file is a SpectraST generated file. + """ + with open(filename, 'r') as contents: + return Msp.next_line_starts_with(contents, "Name:") and Msp.next_line_starts_with(contents, "LibID:") + + class Ms2(Text): file_ext = "ms2"