/usr/share/mmass/mspy/parser_mgf.py is in mmass 5.5.0-5.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 | # -------------------------------------------------------------------------
# Copyright (C) 2005-2013 Martin Strohalm <www.mmass.org>
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3 of the License, or
# (at your option) any later version.
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
# Complete text of GNU GPL can be found in the file LICENSE.TXT in the
# main directory of the program.
# -------------------------------------------------------------------------
# load libs
import re
import os.path
from copy import deepcopy
# load stopper
from mod_stopper import CHECK_FORCE_QUIT
# load objects
import obj_peak
import obj_peaklist
import obj_scan
# PARSE MGF DATA
# --------------
class parseMGF():
"""Parse data from MGF."""
def __init__(self, path):
self.path = path
self._scans = None
self._scanlist = None
# check path
if not os.path.exists(path):
raise IOError, 'File not found! --> ' + self.path
# ----
def load(self):
"""Load all scans into memory."""
self._parseData()
# ----
def info(self):
"""Get document info."""
data = {
'title': '',
'operator': '',
'contact': '',
'institution': '',
'date': '',
'instrument': '',
'notes': '',
}
return data
# ----
def scanlist(self):
"""Get list of all scans in the document."""
# use preloaded data if available
if self._scanlist:
return self._scanlist
# parse data
self._parseData()
return self._scanlist
# ----
def scan(self, scanID=None, dataType=None):
"""Get spectrum from document."""
# parse file
if not self._scans:
self._parseData()
# check data
if not self._scans:
return False
# check selected scan
if scanID in self._scans:
data = self._scans[scanID]
elif scanID == None:
data = self._scans[0]
# return scan
return self._makeScan(data, dataType)
# ----
def _parseData(self):
"""Parse data."""
# clear buffers
self._scans = {}
self._scanlist = None
# open document
try:
document = file(self.path)
rawData = document.readlines()
document.close()
except IOError:
return False
headerPattern = re.compile('^([A-Z]+)=(.+)')
pointPattern = re.compile('[ \t]?')
currentID = None
# parse each line
for line in rawData:
line = line.strip()
# discard comments
if not line or line[0] in ('#', ';', '!', '/'):
continue
# append default scan
if currentID == None or line == 'BEGIN IONS':
currentID = len(self._scans)
scan = {
'title': '',
'scanNumber': currentID,
'parentScanNumber': None,
'msLevel': None,
'pointsCount': 0,
'polarity': None,
'retentionTime': None,
'lowMZ': None,
'highMZ': None,
'basePeakMZ': None,
'basePeakIntensity': None,
'totIonCurrent': None,
'precursorMZ': None,
'precursorIntensity': None,
'precursorCharge': None,
'spectrumType': 'unknown',
'data': [],
}
self._scans[currentID] = scan
# scan ended, use default scan
if line == 'END IONS':
currentID = 0
continue
# get header data
parts = headerPattern.match(line)
if parts:
if parts.group(1) == 'TITLE':
self._scans[currentID]['title'] = parts.group(2).strip()
elif parts.group(1) == 'PEPMASS':
try: self._scans[currentID]['precursorMZ'] = float(pointPattern.split(parts.group(2))[0])
except: pass
elif parts.group(1) == 'CHARGE':
charge = parts.group(2).strip()
if charge[-1] in ('+', '-'):
charge = charge[-1]+charge[:-1]
try: self._scans[currentID]['precursorCharge'] = int(charge)
except: pass
continue
# append datapoint
parts = pointPattern.split(line)
if parts:
point = [0,100.]
try: point[0] = float(parts[0])
except ValueError: continue
try: point[1] = float(parts[1])
except ValueError, IndexError: pass
self._scans[currentID]['data'].append(point)
self._scans[currentID]['pointsCount'] += 1
continue
# make scanlist
if self._scans:
self._scanlist = deepcopy(self._scans)
for scanNumber in self._scanlist:
del self._scanlist[scanNumber]['data']
# ----
def _makeScan(self, scanData, dataType):
"""Make scan object from raw data."""
# parse data as peaklist (discrete points)
if dataType == 'peaklist' or (dataType==None and len(scanData['data'])<3000):
buff = []
for point in scanData['data']:
buff.append(obj_peak.peak(point[0], point[1]))
scan = obj_scan.scan(peaklist=obj_peaklist.peaklist(buff))
# parse data as spectrum (continuous line)
else:
scan = obj_scan.scan(profile=scanData['data'])
# set metadata
scan.title = scanData['title']
scan.scanNumber = scanData['scanNumber']
scan.parentScanNumber = scanData['parentScanNumber']
scan.msLevel = scanData['msLevel']
scan.polarity = scanData['polarity']
scan.retentionTime = scanData['retentionTime']
scan.totIonCurrent = scanData['totIonCurrent']
scan.basePeakMZ = scanData['basePeakMZ']
scan.basePeakIntensity = scanData['basePeakIntensity']
scan.precursorMZ = scanData['precursorMZ']
scan.precursorIntensity = scanData['precursorIntensity']
scan.precursorCharge = scanData['precursorCharge']
return scan
# ----
|