ViewVC Help

View File | Revision Log | Show Annotations | Root Listing

root/pymsxml/pymsxml.py

#	Line 7 | Line 7
7		import tempfile
8		import csv
9		import gzip
10	<	import zipfile
10	>	import zlib
11		from array import array
12		from base64 import b64encode,b64decode
13		from urllib import quote,unquote
#	Line 17 | Line 17
17		def __init__(self):
18		self.name_ = "PyMsXML"
19		self.majorVer = 0
20	<	self.minorVer = 4
20	>	self.minorVer = 5
21		self.revVer = 0
22		def version(self):
23		return "%d.%d.%d"%(self.majorVer,self.minorVer,self.revVer)
#	Line 36 | Line 36
36		return s.hexdigest().lower()
37
38		class ToMzXML:
39	<	def __init__(self,reader,filename,cmpfmt=None,filt=None):
39	>	def __init__(self,reader,filename,cmpfmt=None,filt=None,peaksCompress=False,version="3.0"):
40		self.filename = filename
41		self.compressfmt = cmpfmt
42		self.reader = reader
#	Line 45 | Line 45
45		self.actualScanCount = 0
46		self.scanIndices = {}
47		self.filter = filt
48	+	if not version in ('2.1','2.2','3.0'):
49	+	raise "Bad mzXML version \"%s\""%(version,)
50	+	self.version = version
51	+	if peaksCompress and float(self.version) < 3.0:
52	+	raise "Cannot compress peaks until mzXML version 3.0"
53	+	self.peakcompress = peaksCompress
54
55		def __del__(self):
56		if hasattr(self,'tmpFileName') and self.tmpFileName and self.tmpFileName != '':
#	Line 97 | Line 103
103		self.writeString (xmlFile,'<?xml version="1.0" encoding="ISO-8859-1"?>\n')
104
105		outStr = "<mzXML "
106	<	outStr += "xmlns=\"http://sashimi.sourceforge.net/schema_revision/mzXML_2.1\" "
106	>	outStr += "xmlns=\"http://sashimi.sourceforge.net/schema_revision/mzXML_%s\" "%(self.version,)
107		outStr += "xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\" "
108	<	outStr += "xsi:schemaLocation=\"http://sashimi.sourceforge.net/schema_revision/mzXML_2.1 http://sashimi.sourceforge.net/schema_revision/mzXML_2.1/mzXML_idx_2.1.xsd\""
108	>	outStr += "xsi:schemaLocation=\"http://sashimi.sourceforge.net/schema_revision/mzXML_%s http://sashimi.sourceforge.net/schema_revision/mzXML_%s/mzXML_idx_%s.xsd\""%(self.version,self.version,self.version)
109		outStr += ">\n"
110
111		self.writeString (xmlFile,outStr)
112
113		outStr = "<msRun"
114		outStr += " scanCount=\"%d\"" % (self.actualScanCount,)
115	<	for (k,v) in self.reader.getMsRunMetaData().items():
115	>	md = self.reader.getMsRunMetaData()
116	>	for (k,v) in md.items():
117		k,f = k.split(':')
118	<	outStr += (" %%s=\"%s\""%(f,))%(k,v)
118	>	if self.version not in ('2.2',) or (k != 'startTime'and k != 'endTime'):
119	>	outStr += (" %%s=\"%s\""%(f,))%(k,v)
120		outStr += ">\n"
121
122		self.writeString (xmlFile,outStr)
#	Line 129 | Line 137
137		outStr += "fileSha1=\"%s\""  % (f[2],)
138		outStr += "/>\n"
139		self.writeString (xmlFile,outStr)
140	<
141	<	outStr = "<msInstrument>\n"
140	>
141	>	if float(self.version) >= 3.0:
142	>	outStr = "<msInstrument msInstrumentID=\"%s\">\n" % (self.reader.msInstrumentID(),)
143	>	else:
144	>	outStr = "<msInstrument>\n"
145	>
146		outStr += "<msManufacturer category=\"msManufacturer\" value=\"%s\"/>\n" % (self.reader.msManufacturer(),)
147		outStr += "<msModel category=\"msModel\" value=\"%s\"/>\n" % (self.reader.msModel(),)
148		if self.reader.msIonisation():
#	Line 179 | Line 191
191		outStr += "/>\n"
192		outStr += "<processingOperation "
193		outStr += "name=\"peak_detection_level_1_software\" "
194	<	outStr += "value=\"Analyst\""
194	>	outStr += "value=\"%s\""%(self.reader.acquisitionSoftware(),)
195		outStr += "/>\n"
196		self.writeString (xmlFile,outStr)
197		if (self.reader.peakDetect(2)):
#	Line 193 | Line 205
205		outStr += "/>\n"
206		outStr += "<processingOperation "
207		outStr += "name=\"peak_detection_level_2_software\" "
208	<	outStr += "value=\"Analyst\""
208	>	outStr += "value=\"%s\""%(self.reader.acquisitionSoftware(),)
209		outStr += "/>\n"
210		self.writeString (xmlFile,outStr)
211
#	Line 357 | Line 369
369		outStr += ">\n"
370		self.writeString(xmlFile,outStr)
371
372	<	any = False
373	<	for (k,v) in d.items():
374	<	if k.startswith('scanOrigin.'):
375	<	if not any:
376	<	any = True
377	<	outStr = "<scanOrigin"
378	<	k,f = k.split(':')
379	<	k = k[11:]
380	<	outStr += (" %%s=\"%s\""%(f,))%(k,v)
381	<	if any:
382	<	outStr += "/>\n"
383	<	self.writeString(xmlFile,outStr)
372	>	if self.version in ('2.2',):
373	>	any = False
374	>	for (k,v) in d.items():
375	>	if k.startswith('scanOrigin.'):
376	>	if not any:
377	>	any = True
378	>	outStr = "<scanOrigin"
379	>	k,f = k.split(':')
380	>	k = k[11:]
381	>	outStr += (" %%s=\"%s\""%(f,))%(k,v)
382	>	if any:
383	>	outStr += "/>\n"
384	>	self.writeString(xmlFile,outStr)
385
386		if msLevel > 1:
387
#	Line 414 | Line 427
427		outStr += "%f</precursorMz>\n" % (pMz,)
428		self.writeString(xmlFile,outStr)
429
430	<	if self.reader.maldi():
430	>	if self.reader.maldi() and self.version in ('2.2',):
431		outStr = '<maldi'
432		for (k,v) in d.items():
433		if k.startswith('maldi.'):
#	Line 426 | Line 439
439		outStr += "/>\n"
440		self.writeString(xmlFile,outStr)
441
442	<	outStr = "<peaks precision=\"32\" byteOrder=\"network\" pairOrder=\"m/z-int\">"
442	>	if sys.byteorder != 'big':
443	>	s.byteswap()
444	>
445	>	if debug:
446	>	s = s[:20]
447	>
448	>	specstr = s.tostring()
449	>	if self.peakcompress:
450	>	specstr = zlib.compress(specstr,9)
451	>	outStr = "<peaks precision=\"32\" byteOrder=\"network\" contentType=\"m/z-int\" compressionType=\"zlib\" compressedLen=\"%d\">"%(len(specstr),)
452	>	else:
453	>	if float(self.version) >= 3.0:
454	>	outStr = "<peaks precision=\"32\" byteOrder=\"network\" contentType=\"m/z-int\" compressionType=\"none\" compressedLen=\"%d\">"%(len(specstr),)
455	>	else:
456	>	outStr = "<peaks precision=\"32\" byteOrder=\"network\" pairOrder=\"m/z-int\">"
457	>
458		self.writeString(xmlFile,outStr)
459
460		# Spec says the byte order shall be
#	Line 435 | Line 463
463		if sys.byteorder != 'big':
464		s.byteswap()
465
466	<	outStr = b64encode(s.tostring())
467	<	if not debug:
440	<	self.writeString(xmlFile,outStr)
441	<	else:
442	<	self.writeString(xmlFile,outStr[0:100])
443	<
444	<	if sys.byteorder != 'big':
445	<	s.byteswap()
466	>	outStr = b64encode(specstr)
467	>	self.writeString(xmlFile,outStr)
468
469		outStr = "</peaks>\n"
470		self.writeString(xmlFile,outStr)
471
472	<	if self.reader.maldi():
472	>	if self.reader.maldi() and self.version not in ('2.2',):
473		outStr = ''
474		for (k,v) in d.items():
475		if k.startswith('maldi.'):
476		k,f = k.split(':')
477		k = k[6:]
478		outStr += '<nameValue'
479	<	outStr += ' name="%s"'%(k,)
480	<	outStr += (' value="%f"'%(f,))%(v,)
479	>	outStr += ' name="maldi.%s"'%(k,)
480	>	outStr += (' value="%s"'%(f,))%(v,)
481		outStr += '/>\n'
482	<	##              outStr += '<nameValue'
483	<	##              outStr += ' name="plateID"'
484	<	##              outStr += ' value="%s"'%(d['plateID'],)
485	<	##              outStr += '/>\n'
486	<	##              outStr += '<nameValue'
487	<	##              outStr += ' name="spotID"'
488	<	##              outStr += ' value="%s"'%(d['spotID'],)
489	<	##              outStr += '/>\n'
482	>	outStr += '<nameValue'
483	>	outStr += ' name="maldi.plateID"'
484	>	outStr += ' value="%s"'%(d['plateID'],)
485	>	outStr += '/>\n'
486	>	outStr += '<nameValue'
487	>	outStr += ' name="maldi.spotID"'
488	>	outStr += ' value="%s"'%(d['spotID'],)
489	>	outStr += '/>\n'
490	>	self.writeString(xmlFile,outStr)
491	>
492	>	if self.version not in ('2.2',):
493	>	outStr = ''
494	>	for (k,v) in d.items():
495	>	if k.startswith('scanOrigin.'):
496	>	k,f = k.split(':')
497	>	k = k[11:]
498	>	outStr += '<nameValue'
499	>	outStr += ' name="scanOrigin.%s"'%(k,)
500	>	outStr += (' value="%s"'%(f,))%(v,)
501	>	outStr += '/>\n'
502	>	self.writeString(xmlFile,outStr)
503	>
504	>	outStr = ''
505	>	for (k,v) in d.items():
506	>	if k.startswith('nameValue.'):
507	>	k,f = k.split(':')
508	>	k = k[10:]
509	>	outStr += '<nameValue'
510	>	outStr += ' name="%s"'%(k,)
511	>	outStr += (' value="%s"'%(f,))%(v,)
512	>	outStr += '/>\n'
513	>	if len(outStr) > 0:
514		self.writeString(xmlFile,outStr)
515
516		xmlFile.flush()
#	Line 921 | Line 967
967		if self.peakDetect(msLevel):
968		peakDetect = 'True'
969		minY,maxY = self.theFMANSpecData.GetYValueRange()
970	<	print minY,maxY
970	>	# print minY,maxY
971		self.theFMANSpecData.Threshold(maxY*0.01)
972		self.theSPL.FindPeaksInDataObject(self.theFMANSpecData,50.0)
973		numPeaks = self.theSPL.GetNumberOfPeaks()
974	<	print numPeaks
974	>	# print numPeaks
975		for m in xrange(1,numPeaks+1):
976		(x,w,y,yp) = self.theSPL.GetPeak(m)
977		if y <= 0:
#	Line 955 | Line 1001
1001
1002		# Scan level attributes
1003		# Required by mzXML (no format spec. needed)
1004	<	d = {'msLevel':msLevel,'scan.peakDetect:%s':peakDetect}
1004	>	d = {'msLevel':msLevel}
1005		# Optional ('scan.' and prefixformat spec. needed)
1006		d.update({
1007		'scan.retentionTime:PT%fS':xValue,
1008		'scan.polarity:%s':polarity_val,
1009		'scan.startMz:%f':startMass,
1010		'scan.endMz:%f':stopMass,
965	–	'scan.sample:%d':i,
966	–	'scan.period:%d':j,
967	–	'scan.experiment:%d':k,
968	–	'scan.sampleName:%s':sampleName
1011		})
1012		d.update({'scanOrigin.parentFileID:%s': self.filehash,
1013		'scanOrigin.num:%d': spectrumCount})
1014	+	d.update({'nameValue.sample:%d':i,
1015	+	'nameValue.period:%d':j,
1016	+	'nameValue.experiment:%d':k,
1017	+	'nameValue.sampleName:%s':sampleName})
1018	+
1019		if msLevel == 1:
1020		yield (dataArr,d)
1021		else:
#	Line 989 | Line 1036
1036		def getFilenames(self):
1037		return [ (self.filename,self.filehash) ]
1038
1039	+	def msInstrumentID(self):
1040	+	return "1"
1041	+
1042		def msManufacturer(self):
1043		return "ABI / SCIEX"
1044
#	Line 1002 | Line 1052
1052		return "Quadrupole"
1053
1054		def msDetector(self):
1055	<	return None
1055	>	return "LE"
1056
1057		def acquisitionSoftware(self):
1058		return "Analyst"
#	Line 1455 | Line 1505
1505
1506		# Scan level attributes
1507		# Required by mzXML (no format spec. needed)
1508	<	d = {'msLevel':msLevel,'scan.peakDetect:%s':peakDetect}
1508	>	d = {'msLevel':msLevel}
1509		# Optional ('scan.' and prefixformat spec. needed)
1510		d.update({
1511		'scan.polarity:%s':polarity_val,
#	Line 1491 | Line 1541
1541		def getFilenames(self):
1542		return [ t for t in self.distinct_datafiles.items() ]
1543
1544	+	def msInstrumentID(self):
1545	+	return "1"
1546	+
1547		def msManufacturer(self):
1548		return "ABI / SCIEX"
1549
#	Line 1504 | Line 1557
1557		return "TOF"
1558
1559		def msDetector(self):
1560	<	return None
1560	>	return "LE"
1561
1562		def acquisitionSoftware(self):
1563		return "DataExplorer"
#	Line 1611 | Line 1664
1664		help="Level(s) of spectra to apply peak detection to (comma separated). QStar,4700 only.")
1665		parser.add_option("-f", "--filter", type="string", dest="filter", default=None,\
1666		help="Filter on mzxml scan meta-data: field.op.value[,field.op.value]. Default: No filter.")
1667	<	parser.add_option("-d", "--debug", action="store_true", dest="debug", default=False,\
1668	<	help="Debug. First 10 spectra only, and truncated peaks data element. Default: False.")
1667	>	parser.add_option("-V", "--version", type='string', dest="version", default="3.0",
1668	>	help="XML version. mzXML only. Valid options '2.1','2.2','3.0'. Default: '3.0'.")
1669	>	parser.add_option("-z", "--compress_peaks", action="store_true", dest="compress_peaks", default=None,\
1670	>	help="Compress mzXML peaks data using zlib. Default: False")
1671		parser.add_option("-Z", "--compress", type="string", dest="compress", default=None,\
1672		help="Compress output file. Valid options 'gz'. Default: None.")
1673	+	parser.add_option("-d", "--debug", action="store_true", dest="debug", default=False,\
1674	+	help="Debug. First 10 spectra only, and truncated peaks data element. Default: False.")
1675
1676		( opts, args ) = parser.parse_args()
1677
#	Line 1665 | Line 1722
1722		sys.exit(1)
1723
1724		if opts.xmlformat.lower() == 'mzxml':
1725	<	x = ToMzXML(r,o,opts.compress,filt)
1725	>	x = ToMzXML(r,o,opts.compress,filt,opts.compress_peaks,opts.version)
1726		elif opts.xmlformat.lower() == 'mzdata':
1727		x = ToMzData(r,o,opts.compress,filt)
1728		elif opts.output[-6:].lower() in ('.mzxml',):
1729	<	x = ToMzXML(r,opts.output,opts.compress,filt)
1729	>	x = ToMzXML(r,opts.output,opts.compress,filt,opts.compress_peaks,opts.version)
1730		elif opts.output[-7:].lower() in ('.mzdata',):
1731		x = ToMzData(r,opts.output,opts.compress,filt)
1732		else:

Diff Legend

–	Removed lines
+	Added lines
<	Changed lines
>	Changed lines