Mercurial > repos > iracooke > proteomics_datatypes
changeset 9:6ca516faacfc draft
Uploaded
| author | iracooke |
|---|---|
| date | Thu, 05 Jun 2014 18:08:35 -0400 |
| parents | 58469754fd82 |
| children | ef74edade8be |
| files | README datatypes_conf.xml display_applications/proteomics/PepXml.xml display_applications/proteomics/ProtXml.xml display_applications/proteomics/mzML.xml proteomics.py tool-data/protk_display_site.txt.sample |
| diffstat | 7 files changed, 448 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README Thu Jun 05 18:08:35 2014 -0400 @@ -0,0 +1,11 @@ +# 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/datatypes_conf.xml Thu Jun 05 18:08:35 2014 -0400 @@ -0,0 +1,55 @@ +<?xml version="1.0"?> +<datatypes> + <datatype_files> + <datatype_file name="proteomics.py"/> + </datatype_files> + <registration display_path="display_applications"> + <datatype extension="cps" type="galaxy.datatypes.binary:Binary" subclass="True" display_in_upload="true" /> + <datatype extension="pepxml" type="galaxy.datatypes.proteomics:PepXml" mimetype="application/xml" display_in_upload="true"> + <display file="proteomics/PepXml.xml" /> + </datatype> + <datatype extension="raw_pepxml" type="galaxy.datatypes.proteomics:PepXml" mimetype="application/xml" subclass="true"> + <display file="proteomics/PepXml.xml" /> + </datatype> + <datatype extension="peptideprophet_pepxml" type="galaxy.datatypes.proteomics:PepXml" mimetype="application/xml" subclass="true"> + <display file="proteomics/PepXml.xml" /> + </datatype> + <datatype extension="interprophet_pepxml" type="galaxy.datatypes.proteomics:PepXml" mimetype="application/xml" subclass="true"> + <display file="proteomics/PepXml.xml" /> + </datatype> + <datatype extension="protxml" type="galaxy.datatypes.proteomics:ProtXML" mimetype="application/xml" display_in_upload="true" > + <display file="proteomics/ProtXml.xml"/> + </datatype> + <datatype extension="pepxml.tsv" type="galaxy.datatypes.proteomics:PepXmlReport" display_in_upload="true" /> + <datatype extension="protxml.tsv" type="galaxy.datatypes.proteomics:ProtXmlReport" display_in_upload="true" /> + <datatype extension="mascotdat" type="galaxy.datatypes.proteomics:MascotDat" display_in_upload="false" /> + <datatype extension="mzml" type="galaxy.datatypes.proteomics:MzML" mimetype="application/xml" display_in_upload="true"> + <display file="proteomics/mzML.xml"/> + <display file="proteomics/protvis_mzml.xml"/> + </datatype> + <datatype extension="mgf" type="galaxy.datatypes.proteomics:Mgf" display_in_upload="true" /> + <datatype extension="idpdb" type="galaxy.datatypes.proteomics:IdpDB" display_in_upload="true" /> + <datatype extension="wiff" type="galaxy.datatypes.proteomics:Wiff" display_in_upload="true" /> + <datatype extension="mzxml" type="galaxy.datatypes.proteomics:MzXML" mimetype="application/xml" display_in_upload="true" /> + <datatype extension="mzq" type="galaxy.datatypes.proteomics:MzQuantML" mimetype="application/xml" display_in_upload="true" /> + <datatype extension="mzid" type="galaxy.datatypes.proteomics:MzIdentML" mimetype="application/xml" display_in_upload="true" /> + <datatype extension="traml" type="galaxy.datatypes.proteomics:TraML" mimetype="application/xml" display_in_upload="true" /> + <datatype extension="featurexml" type="galaxy.datatypes.proteomics:FeatureXML" mimetype="application/xml" display_in_upload="true" /> + <datatype extension="consensusxml" type="galaxy.datatypes.proteomics:ConsensusXML" mimetype="application/xml" display_in_upload="true" /> + <datatype extension="idxml" type="galaxy.datatypes.proteomics:IdXML" mimetype="application/xml" display_in_upload="true" /> + <datatype extension="raw" type="galaxy.datatypes.proteomics:RAW" mimetype="application/octet-stream" display_in_upload="true" /> + <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" /> + </registration> + <sniffers> + <sniffer type="galaxy.datatypes.proteomics:MzML"/> + <sniffer type="galaxy.datatypes.proteomics:PepXml"/> + <sniffer type="galaxy.datatypes.proteomics:Mgf"/> + <sniffer type="galaxy.datatypes.proteomics:ProtXML"/> + <sniffer type="galaxy.datatypes.proteomics:MzXML"/> + <sniffer type="galaxy.datatypes.proteomics:TraML"/> + <sniffer type="galaxy.datatypes.proteomics:MzIdentML"/> + <sniffer type="galaxy.datatypes.proteomics:MzQuantML"/> + </sniffers> +</datatypes>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/display_applications/proteomics/PepXml.xml Thu Jun 05 18:08:35 2014 -0400 @@ -0,0 +1,18 @@ +<display id="proteomics_pepxml" version="1.0.0" name="view pepXML in"> + <dynamic_links from_file="tool-data/protk_display_site.txt" skip_startswith="#" id="0" name="0"> + <!-- Define parameters by column from file --> + <dynamic_param name="site_id" value="0"/> + <dynamic_param name="site_url" value="1"/> + <!-- We define url and params as normal, but values defined in dynamic_param are available by specified name --> + <url target_frame="galaxy_main">${site_url}/init_local?file=${encoded_filename.qp}&type=pepxml</url> + <param type="data" name="pep_file" viewable="False" format="pepxml"/> + <param type="data" dataset="pep_file" name="pepxml_file" format="pepxml" viewable="False" /> + <param type="template" name="encoded_filename" strip="True" > + #import binascii + ${binascii.hexlify( $pepxml_file.file_name )} + </param> + <param type="template" name="galaxy_url" strip="True" > + ${BASE_URL.split(":")[1][2:]} + </param> + </dynamic_links> +</display>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/display_applications/proteomics/ProtXml.xml Thu Jun 05 18:08:35 2014 -0400 @@ -0,0 +1,18 @@ +<display id="proteomics_protxml" version="1.0.0" name="view protXML in"> + <dynamic_links from_file="tool-data/protk_display_site.txt" skip_startswith="#" id="0" name="0"> + <!-- Define parameters by column from file --> + <dynamic_param name="site_id" value="0"/> + <dynamic_param name="site_url" value="1"/> + <!-- We define url and params as normal, but values defined in dynamic_param are available by specified name --> + <url target_frame="galaxy_main">${site_url}/init_local?file=${encoded_filename.qp}&type=protxml</url> + <param type="data" name="prot_file" viewable="False" format="protxml"/> + <param type="data" dataset="prot_file" name="protxml_file" format="protxml" viewable="False" /> + <param type="template" name="encoded_filename" strip="True" > + #import binascii + ${binascii.hexlify( $protxml_file.file_name )} + </param> + <param type="template" name="galaxy_url" strip="True" > + ${BASE_URL.split(":")[1][2:]} + </param> + </dynamic_links> +</display>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/display_applications/proteomics/mzML.xml Thu Jun 05 18:08:35 2014 -0400 @@ -0,0 +1,18 @@ +<display id="proteomics_mzml" version="1.0.2" name="view mzML data"> + <dynamic_links from_file="tool-data/protk_display_site.txt" skip_startswith="#" id="0" name="0"> + <!-- Define parameters by column from file --> + <dynamic_param name="site_id" value="0"/> + <dynamic_param name="site_url" value="1"/> + <!-- We define url and params as normal, but values defined in dynamic_param are available by specified name --> + <url target_frame="galaxy_main">${site_url}/init_local?file=${encoded_filename.qp}&type=mzml</url> + <param type="data" name="raw_file" viewable="False" format="mzml"/> + <param type="data" dataset="raw_file" name="mzml_file" format="mzml" viewable="False" /> + <param type="template" name="encoded_filename" strip="True" > + #import binascii + ${binascii.hexlify( $mzml_file.file_name )} + </param> + <param type="template" name="galaxy_url" strip="True" > + ${BASE_URL.split(":")[1][2:]} + </param> + </dynamic_links> +</display>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/proteomics.py Thu Jun 05 18:08:35 2014 -0400 @@ -0,0 +1,325 @@ +""" +Proteomics format classes +""" +import logging +import re +import binascii + +from galaxy.datatypes.sniff import * +from galaxy.datatypes import data +from galaxy.datatypes.data import Text +from galaxy.datatypes.xml import GenericXml +from galaxy.datatypes.binary import Binary +from galaxy.datatypes.tabular import Tabular +from galaxy.datatypes.interval import Gff + +log = logging.getLogger(__name__) + + +class Wiff( Binary ): + """Class for wiff files.""" + file_ext = 'wiff' + allow_datatype_change = False + composite_type = 'auto_primary_file' + + def __init__(self, **kwd): + Binary.__init__(self, **kwd) + self.add_composite_file( 'wiff', + description = 'AB SCIEX files in .wiff format. This can contain all needed information or only metadata.', + is_binary = True ) + self.add_composite_file( 'wiff_scan', + description = 'AB SCIEX spectra file (wiff.scan), if the corresponding .wiff file only contains metadata.', + optional = 'True', is_binary = True ) + + def generate_primary_file( self, dataset = None ): + rval = ['<html><head><title>Wiff 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 ) + + + +if hasattr(Binary, 'register_unsniffable_binary_ext'): + Binary.register_unsniffable_binary_ext('wiff') + + +class IdpDB( Binary ): + file_ext = "idpDB" + +if hasattr(Binary, 'register_unsniffable_binary_ext'): + Binary.register_unsniffable_binary_ext('idpDB') + + +class PepXmlReport( Tabular ): + """pepxml converted to tabular report""" + file_ext = "tsv" + + def __init__(self, **kwd): + Tabular.__init__( self, **kwd ) + self.column_names = ['Protein', 'Peptide', 'Assumed Charge', 'Neutral Pep Mass (calculated)', 'Neutral Mass', 'Retention Time', 'Start Scan', 'End Scan', 'Search Engine', 'PeptideProphet Probability', 'Interprophet Probabaility'] + + def display_peek( self, dataset ): + """Returns formated html of peek""" + return Tabular.make_html_table( self, dataset, column_names=self.column_names ) + + +class ProtXmlReport( Tabular ): + """protxml converted to tabular report""" + file_ext = "tsv" + comment_lines = 1 + + def __init__(self, **kwd): + Tabular.__init__( self, **kwd ) + self.column_names = ["Entry Number", "Group Probability", "Protein", "Protein Link", "Protein Probability", "Percent Coverage", "Number of Unique Peptides", "Total Independent Spectra", "Percent Share of Spectrum ID's", "Description", "Protein Molecular Weight", "Protein Length", "Is Nondegenerate Evidence", "Weight", "Precursor Ion Charge", "Peptide sequence", "Peptide Link", "NSP Adjusted Probability", "Initial Probability", "Number of Total Termini", "Number of Sibling Peptides Bin", "Number of Instances", "Peptide Group Designator", "Is Evidence?"] + + def display_peek( self, dataset ): + """Returns formated html of peek""" + return Tabular.make_html_table( self, dataset, column_names=self.column_names ) + +class ProteomicsXml( GenericXml ): + """ An enhanced XML datatype used to reuse code across several + proteomic/mass-spec datatypes. """ + + 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('<?'): + break + pattern = '^<(\w*:)?%s' % self.root # pattern match <root or <ns:root for any ns string + return line != None and re.match(pattern, line) != None + + 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 = self.blurb + else: + dataset.peek = 'file does not exist' + dataset.blurb = 'file purged from disk' + + +class PepXml(ProteomicsXml): + """pepXML data""" + file_ext = "pepxml" + blurb = 'pepXML data' + root = "msms_pipeline_analysis" + + +class MzML(ProteomicsXml): + """mzML data""" + file_ext = "mzml" + blurb = 'mzML Mass Spectrometry data' + root = "(mzML|indexedmzML)" + + +class ProtXML(ProteomicsXml): + """protXML data""" + file_ext = "protxml" + blurb = 'prot XML Search Results' + root = "protein_summary" + + +class MzXML(ProteomicsXml): + """mzXML data""" + file_ext = "mzxml" + blurb = "mzXML Mass Spectrometry data" + root = "mzXML" + +## PSI datatypes +class MzIdentML(ProteomicsXml): + file_ext = "mzid" + blurb = "XML identified peptides and proteins." + root = "MzIdentML" + + +class TraML(ProteomicsXml): + file_ext = "traml" + blurb = "TraML transition list" + root = "TraML" + + +class MzQuantML(ProteomicsXml): + file_ext = "mzq" + blurb = "XML quantification data" + root = "MzQuantML" + + +class ConsensusXML(ProteomicsXml): + file_ext = "consensusxml" + blurb = "OpenMS multiple LC-MS map alignment file" + root = "consensusXML" + + +class FeatureXML(ProteomicsXml): + file_ext = "featurexml" + blurb = "OpenMS feature file" + root = "featureMap" + + +class IdXML(ProteomicsXml): + file_ext = "idxml" + blurb = "OpenMS identification file" + root = "IdXML" + + +class Mgf( Text ): + """Mascot Generic Format data""" + file_ext = "mgf" + + 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 = 'mgf Mascot Generic Format' + else: + dataset.peek = 'file does not exist' + dataset.blurb = 'file purged from disk' + + def sniff( self, filename ): + mgf_begin_ions = "BEGIN IONS" + max_lines=100 + + for i, line in enumerate( file( filename ) ): + line = line.rstrip( '\n\r' ) + if line==mgf_begin_ions: + return True + if i>max_lines: + return False + + +class MascotDat( Text ): + """Mascot search results """ + file_ext = "mascotdat" + + 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 = 'mascotdat Mascot Search Results' + else: + dataset.peek = 'file does not exist' + dataset.blurb = 'file purged from disk' + + + def sniff( self, filename ): + mime_version = "MIME-Version: 1.0 (Generated by Mascot version 1.0)" + max_lines=10 + + for i, line in enumerate( file( filename ) ): + line = line.rstrip( '\n\r' ) + if line==mime_version: + return True + if i>max_lines: + return False + + +class RAW( Binary ): + """Class describing a Thermo Finnigan binary RAW file""" + file_ext = "raw" + def sniff( self, filename ): + # Thermo Finnigan RAW format is proprietary and hence not well documented. + # Files start with 2 bytes that seem to differ followed by F\0i\0n\0n\0i\0g\0a\0n + # This combination represents 17 bytes, but to play safe we read 20 bytes from + # the start of the file. + try: + header = open( filename ).read(20) + hexheader = binascii.b2a_hex( header ) + finnigan = binascii.hexlify( 'F\0i\0n\0n\0i\0g\0a\0n' ) + if hexheader.find(finnigan) != -1: + return True + return False + except: + return False + def set_peek( self, dataset, is_multi_byte=False ): + if not dataset.dataset.purged: + dataset.peek = "Thermo Finnigan RAW file" + dataset.blurb = data.nice_size( dataset.get_size() ) + else: + dataset.peek = 'file does not exist' + dataset.blurb = 'file purged from disk' + def display_peek( self, dataset ): + try: + return dataset.peek + except: + return "Thermo Finnigan RAW file (%s)" % ( data.nice_size( dataset.get_size() ) ) + + +if hasattr(Binary, 'register_sniffable_binary_format'): + Binary.register_sniffable_binary_format('raw', 'raw', RAW) + + +class Msp( Text ): + """ Output of NIST MS Search Program chemdata.nist.gov/mass-spc/ftp/mass-spc/PepLib.pdf """ + file_ext = "msp" + + @staticmethod + def next_line_starts_with(contents, prefix): + next_line = contents.readline() + return next_line != None and next_line.startswith(prefix) + + def sniff(self, filename): + """ Determines whether the file is a NIST MSP output file. + + >>> fname = get_test_fname('test.msp') + >>> Msp().sniff(fname) + True + >>> fname = get_test_fname('test.mzXML') + >>> Msp().sniff(fname) + False + """ + with open(filename, 'r') as contents: + return Msp.next_line_starts_with(contents, "Name:") and Msp.next_line_starts_with(contents, "MW:") + +class Ms2(Text): + file_ext = "ms2" + + def sniff(self, filename): + """ Determines whether the file is a valid ms2 file. + + >>> fname = get_test_fname('test.msp') + >>> Ms2().sniff(fname) + False + >>> fname = get_test_fname('test.ms2') + >>> Ms2().sniff(fname) + True + """ + + with open(filename, 'r') as contents: + header_lines = [] + while True: + line = contents.readline() + if line == None or len(line) == 0: + pass + elif line.startswith('H\t'): + header_lines.append(line) + else: + break + for header_field in ['CreationDate', 'Extractor', 'ExtractorVersion', 'ExtractorOptions']: + found_header = False + for header_line in header_lines: + if header_line.startswith('H\t%s' % (header_field)): + found_header = True + break + if not found_header: + return False + + return True + +# unsniffable binary format, should do something about this +class XHunterAslFormat( Binary ): + """ Annotated Spectra in the HLF format http://www.thegpm.org/HUNTER/format_2006_09_15.html """ + file_ext = "hlf" + +if hasattr(Binary, 'register_unsniffable_binary_ext'): + Binary.register_unsniffable_binary_ext('hlf')
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/protk_display_site.txt.sample Thu Jun 05 18:08:35 2014 -0400 @@ -0,0 +1,3 @@ +#Proteomic Visualization application should be hosted on the same server as galaxy +#Entries in this file are of the format "site_id" <TAB> "site_url" +Proteomics Visualize http://127.0.0.1:8500