def ric(self, *args, **kwargs):
'''This method is deprecated, use xic() instead.
Kept for backwards compatibility.'''
logger_message(40, 'ric() is deprecated: use xic() instead')
return self.xic(*args, **kwargs)
def prot_report(self, report_file, prot_report):
'''Adds a protein page to a report (XLS or MZD)'''
logger_message(30, 'Adding Protein Info...')
if report_file.lower().endswith('.mzd'):
prot_rep = mzReport.mzDB.sqlite3.connect(report_file)
prot_rep.execute(
'create view ProteinData as select '
'"Protein Rank","Accession Number","Protein Description",'
'"Protein Mass","Protein Matches","Protein Score",'
'count(distinct "Peptide Sequence") as "Unique Peptides"'
' from PeptideData group by "Protein Rank","Accession Number"')
prot_rep.close()
else:
cols = [
'Protein Rank', 'Accession Number', 'Protein Description',
'Protein Mass', 'Protein Matches', 'Protein Score',
'Unique Peptides'
]
prot_rep = mzReport.writer(report_file,
columns=cols,
sheet_name='Protein')
for line in prot_report:
prot_rep.write(line)
prot_rep.close()
def mascot_headers(self, report_file, mascot_headers):
'''Combines a list of Mascot header pages into a single page (XLS or MZD)'''
logger_message(30, 'Adding Mascot Headers...')
first_columns = set()
columns = defaultdict(dict)
report_files = [f for f, mh in mascot_headers]
for f, mascot_header in mascot_headers:
first_col = []
for line in mascot_header[1:]:
if line[0] == ' ' or (isinstance(line[1], (str, unicode))
and line[1].startswith('-----')):
continue
columns[f][line[0]] = line[1]
first_col.append(line[0])
first_columns.add(tuple(first_col))
if len(first_columns) > 1:
logger_message(20,
'Headers seems different, will try to merge them')
main_h = list(max(first_columns, key=len))
main_h += sorted(
reduce(set.union, first_columns, set()).difference(main_h))
else:
main_h = list(first_columns.pop())
cols = ['Header'] + [(os.path.basename(f) if f else ('-' * 50))
for f in report_files]
if report_file.lower().endswith('.mzd'):
mascot_rep = mzReport.writer(report_file,
columns=cols,
table_name='MascotHeader')
else:
mascot_rep = mzReport.writer(report_file,
columns=cols,
sheet_name='Mascot_Header')
for col in main_h:
row = [col]
for f in report_files:
if col in columns[f]:
row.append(columns[f][col])
else:
row.append(None)
mascot_rep.write(row)
mascot_rep.close()
def OnSubmit(self, event):
self.writeback('Submitting Mascot search to %s...' % settings.mascot_server)
if not self.parameters['FILE']:
wx.MessageBox("Please select a file","Error")
return
elif not self.Validate():
return
wx.BeginBusyCursor()
self.UpdateValues()
file_list = self.parameters['FILE']
self.parameters['MULTI_SITE_MODS'] = '1'
if isinstance(file_list, basestring):
file_list = [file_list] # How did this ever work previously??
ms = MascotSearcher(settings.mascot_server,
open_tabs=self.open_tabs.IsChecked()) #, verbose=True)
if settings.mascot_security:
ms.login(self.login, self.password)
results = []
for f in file_list:
self.writeback('Performing Mascot search on %s...' % os.path.basename(f))
self.parameters['FILE'] = f
logger_message(30, 'Submitting %s...' % os.path.basename(f))
(dat,err) = ms.search(self.parameters.items())
if dat:
results.append(dat)
if err:
wx.MessageBox(err[1], 'Mascot Error: %s' % err[0],
style=wx.OK|wx.CENTER|wx.ICON_ERROR)
#ms.close(sys.stdout)
ms.close()
self.parameters['FILE'] = file_list
wx.EndBusyCursor()
logger_message(40, 'Finished Mascot Search')
self.writeback('Mascot search completed.')
if self.getIDs.IsChecked():
self.mascot_tab.login_text.SetValue(self.login)
self.mascot_tab.password_text.SetValue(self.password)
self.mascot_tab.mascot_id_text.SetValue(', '.join(results))
self.mascot_tab.SetFocus()
def write(self, row, metadata=None, ignore_extra=False):
# error checking: want one value per column and nothing more
# if row is a dict, keys should be in lower-case
if len(row) < len(self.columns):
raise ValueError('Must have values for each column')
elif (not ignore_extra) and len(row) > len(self.columns):
raise ValueError('Too many values')
elif isinstance(row, dict):
row = dict((k.lower(), v) for k, v in list(row.items()))
#if not all(k.lower() in row for k in self.columns):
#raise ValueError('Value dictionary does not match column headers')
if isinstance(row, dict):
self.csv.writerow([row[col.lower()] for col in self.columns])
else:
self.csv.writerow(row)
if metadata:
logger_message(40, 'Metadata not supported in CSV files')
def write(self, row, metadata=None):
# error checking: want one value per column and nothing more
# if row is a dict, keys should be in lower-case
if len(row) < len(self.columns):
raise ValueError('Must have values for each column')
elif len(row) > len(self.columns):
raise ValueError('Too many values')
elif isinstance(row,dict):
row = dict((k.lower(),v) for k,v in row.items())
if not all(k.lower() in row for k in self.columns):
raise ValueError('Value dictionary does not match column headers')
if isinstance(row,dict):
self.csv.writerow([row[col.lower()] for col in self.columns])
else:
self.csv.writerow(row)
if metadata:
logger_message(40, 'Metadata not supported in CSV files')
def mascot_header(self, report_file, mascot_header):
'''Adds a Mascot Header page to a report (XLS or MZD)'''
logger_message(30, 'Adding Mascot Header...')
if report_file.lower().endswith('.mzd'):
mascot_rep = mzReport.writer(report_file,
columns=mascot_header[0],
table_name='MascotHeader')
else:
mascot_rep = mzReport.writer(report_file,
columns=mascot_header[0],
sheet_name='Mascot_Header')
for line in mascot_header[1:]:
mascot_rep.write(line)
mascot_rep.close()
logger_message(20, 'Mascot Header Complete')
def mascot_prot_coverage(self, mascot_id, ion_cutoff, date=None):
logger_message(30, 'Downloading Mascot Protein Coverage...')
prots = {}
row = (yield None)
#for row in dataFile:
while row:
acc = row['Accession Number']
start_pos = row['Start Position']
end_pos = row['End Position']
db_idx = row.get('protein database', None)
if db_idx:
db_idx = db_idx.split('::')[0]
if acc in prots:
(coverage, start_end, cov_per) = prots[acc]
else:
logger_message(10, "Getting coverage for: %s" % acc)
(coverage, start_end,
cov_per) = self.mascot.get_coverage(acc,
mascot_id=mascot_id,
date=date,
cutoff=ion_cutoff,
db_idx=db_idx)
prots[acc] = (coverage, start_end, cov_per)
#check if connection error
if coverage == 'error':
logger_message(
30,
'Mascot Login Error. Please check your username and password and try again'
)
fh = open('multiplierz_error.txt', 'a')
fh.write(
"Mascot Login Error. Please check your username and password and try again\n"
)
fh.close()
break
# convert protein-index into text-index
conv_x = lambda i: i + 6 + ((i - 1) / 50) * 11 + (
(i - 1) % 50) / 10
nse = self.mascot.get_range(
[conv_x(i) for i in range(start_pos, end_pos + 1)])
metadatatuple = (coverage, start_end, nse)
row = (yield (cov_per, ('Accession Number', 'prot coverage',
metadatatuple)))
arg = sys.argv[1]
if arg == '--run_register_interfaces':
print "PERFORMING MZAPI SETUP"
from multiplierz.mzAPI.management import registerInterfaces
registerInterfaces()
print "Setup complete; exiting."
else:
arg_ext = os.path.splitext(arg)[1]
if arg_ext == '.mzd':
app = wx.App(False)
_icon = wx.Icon(_exe_name, wx.BITMAP_TYPE_ICO)
logger_message(60, 'Loading mzResults...')
from gui.report_viewer import ReportViewer
report_viewer = ReportViewer(None, arg)
report_viewer.SetIcon(_icon)
report_viewer.Show()
app.MainLoop()
else:
app = wx.App(False)
_icon = wx.Icon(_exe_name, wx.BITMAP_TYPE_ICO)
from gui import MultiplierzFrame
def legacy_get_reports(self,
mascot_ids,
dates=None,
chosen_folder=None,
combined_file=False,
rank_one=False,
protein_report=False,
mascot_options=None,
peaks=False,
peaks_options=None,
mascot_web=False,
mascot_web_options=None,
mascot_prot_cov=False,
ext='.xlsx',
local_dat_files=None,
mascotIDInResultName=False,
percolatorDirectory=None,
**kwargs):
# mascot_ids should be a list/tuple of IDs. dates should be a matching list/tuple of dates,
# or False. combined_file should be None for individual files or an output file name
# mascot options: (max_hits, ion_cutoff, bold_red, unassigned_queries,
# show_query_data, show_same_set, show_sub_set, quant) + mascot_id, date
# mascot_web options: (ms2_img, mascot_ms2, mascot_var_mods,
# draw_pep, instrument, im_size) + mascot_id, date
# mascot_prot_cov options: ion_cutoff, mascot_id, date
# defaults and overrides. The priority is: keyword > option_dict > default
# Using local .DATs means you don't have access to certain fancy
# Mascot features.
if local_dat_files:
mascot_web = False
mascot_prot_cov = False
assert not peaks, (
"precursor_peaks and images in result files are no longer supported; "
"peaks argument to get_reports must be False.")
# defaults
_mascot_options = dict(max_hits=1000,
ion_cutoff=20,
bold_red=True,
unassigned_queries=False,
show_query_data=True,
show_same_set=False,
show_sub_set=False,
quant=False)
# option_dict
if mascot_options:
_mascot_options.update(mascot_options)
# keywords
_mascot_options.update(
(k, kwargs[k]) for k in kwargs if k in _mascot_options)
for k in _mascot_options:
if k in kwargs:
_mascot_options[k] = kwargs[k]
if peaks:
# defaults
_peaks_options = dict(time_window=(0.5, 0.5),
mz_window=(0.1, 0.1),
plot_ms1=False,
plot_xic=False,
plot_ms2=False,
peak_area=False,
reporter_ions=False,
peakfilter=None,
ion_list=['b', 'y'],
instrument='ESI-TRAP',
im_size=(8.0, 6.0))
# option_dict
if peaks_options:
_peaks_options.update(peaks_options)
# keywords
_peaks_options.update(
(k, kwargs[k]) for k in kwargs
if (k in _peaks_options or k == 'peak_data_path'))
# need a path (file or directory) to actually do this,
# so we raise an exception if it's not present
if 'peak_data_path' not in _peaks_options:
raise ValueError(
'peak_data_path value is required for peak extraction')
if mascot_web:
# defaults
_mascot_web_options = dict(ms2_img=True,
mascot_ms2=True,
mascot_var_mods=True,
instrument='ESI-TRAP',
im_size=(8.0, 6.0))
# option_dict
if mascot_web_options:
_mascot_web_options.update(mascot_web_options)
# keywords
_mascot_web_options.update(
(k, kwargs[k]) for k in kwargs if k in _mascot_web_options)
# if version is 2.2+, mod positions are extracted automatically
if mascot_web and self.mascot.version >= '2.2':
_mascot_web_options['mascot_var_mods'] = False
if not _mascot_web_options['ms2_img']:
mascot_web = False
# require agreement 'instrument' between two dictionaries
if peaks and mascot_web:
if _peaks_options['instrument'] != _mascot_web_options[
'instrument']:
raise ValueError(
'instrument value must be consistent; input dictionaries disagree'
)
# Getting both of these would be redundant, so force at most one
if mascot_web and peaks and _mascot_web_options['ms2_img']:
_peaks_options['plot_ms2'] = False
if chosen_folder is None:
chosen_folder = myData
# if creating a single file, we'll create the writer now
if combined_file:
# figuring out the report columns. start with defaults...
repcols = mzReport.default_columns[:]
# mascot 2.3 can have multiple databases so add a column for that
if self.mascot.version >= '2.3':
repcols.insert(1, 'Protein Database')
# these are the columns coming out of the dat file, need them separate
res_cols = repcols[:]
# add columns for peak extraction
if peaks:
repcols.extend(c for c in [
'MS2 Time', 'Peak Time', 'Peak Intensity',
'Peak Width (sec)', 'Peak Comment'
] if c not in repcols)
if _peaks_options['peak_area'] and 'Peak Area' not in repcols:
repcols.append('Peak Area')
if _peaks_options['reporter_ions']:
repcols.extend(
c for c in ['Rep114', 'Rep115', 'Rep116', 'Rep117']
if c not in repcols)
repcols.insert(0, 'File')
report_file = os.path.join(chosen_folder, combined_file)
if os.path.exists(report_file):
os.remove(report_file)
report = mzReport.writer(report_file, columns=repcols)
isMZD = isinstance(report, mzReport.mzDB.SQLiteWriter)
mascot_headers = []
else:
report_files = []
if dates:
mid_d = zip(mascot_ids, dates, [None] * len(mascot_ids))
elif local_dat_files:
mid_d = zip(["Local File"] * len(local_dat_files),
[None] * len(local_dat_files), local_dat_files)
else:
mid_d = [(mid, None, None) for mid in mascot_ids]
for mascot_id, date, local in mid_d:
mascot_id = str(mascot_id)
if ':' in mascot_id:
(mascot_id, date) = mascot_id.split(':', 1)
mascot_id = str(mascot_id).zfill(6)
if not (date or local):
date = self.mascot.get_date(mascot_id)
logger_message(
30, 'Generating Multiplierz-Mascot Report for JobID %s...' %
mascot_id)
if ext == '.mzid':
logger_message(30, 'Downloading mzIdentML File...')
destination = chosen_folder if chosen_folder else myData
reportfilename = "F%s.mzid" % mascot_id
outputfile = os.path.join(destination, reportfilename)
report_file = self.mascot.download_mzid(mascot_id,
save_file=outputfile,
date=date)
assert report_file == outputfile
report_files.append(report_file)
continue
# mzIdentML files don't use the rest of this function;
# what they contain is essentially fixed, to multiplierz.
if not local:
logger_message(30, 'Downloading Mascot DAT File...')
dat_file = self.mascot.download_dat(chosen_folder, mascot_id,
date)
else:
dat_file = os.path.abspath(local)
mascot_id = os.path.basename(local).split('.')[0]
if dat_file:
logger_message(20, 'Mascot DAT File Downloaded!')
mascot_dat_file = interface.MascotDatFile(
dat_file, **_mascot_options)
if percolatorDirectory and mascot_dat_file.hasDecoyHits():
print "Running Mascot Percolator..."
mascot_dat_file.close()
percolatedDatFile = runPercolator(dat_file,
percolatorDirectory)
mascot_dat_file = interface.MascotDatFile(
dat_file, **mascot_options)
if self.cleanup:
os.remove(dat_file)
dat_file = percolatedDatFile
else:
logger_message(
40, 'Failed to download DAT file for %s' % mascot_id)
continue
if self.mascot.version != mascot_dat_file.res_file.getMascotVer(
)[:len(self.mascot.version)]:
print(
"Mascot version mismatch detected; changing version from %s to %s"
% (self.mascot.version,
mascot_dat_file.res_file.getMascotVer()
[:len(self.mascot.version)]))
self.mascot.version = mascot_dat_file.res_file.getMascotVer(
)[:len(self.mascot.version)]
if not combined_file:
# Report column stuff moved from above, in order to handle version dependency. (Heavy sigh.)
# figuring out the report columns. start with defaults...
repcols = mzReport.default_columns[:]
# mascot 2.3 can have multiple databases so add a column for that
if self.mascot.version >= '2.3':
repcols.insert(1, 'Protein Database')
# these are the columns coming out of the dat file, need them separate
res_cols = repcols[:]
# add columns for peak extraction
if peaks:
repcols.extend(c for c in [
'MS2 Time', 'Peak Time', 'Peak Intensity',
'Peak Width (sec)', 'Peak Comment'
] if c not in repcols)
if _peaks_options[
'peak_area'] and 'Peak Area' not in repcols:
repcols.append('Peak Area')
if _peaks_options['reporter_ions']:
repcols.extend(
c
for c in ['Rep114', 'Rep115', 'Rep116', 'Rep117']
if c not in repcols)
if mascot_prot_cov:
repcols.append('Protein Coverage')
#Get MS File Name
mascot_header = mascot_dat_file.mascot_header()
ms_file_name = mascot_header[7][1] or ('F%s' % mascot_id)
if not combined_file:
filename = os.path.basename(ms_file_name)
if mascotIDInResultName and filename.endswith('.mgf'):
filename = filename[:-4] + "." + mascot_id
report_file = os.path.join(chosen_folder, filename + ext)
if os.path.exists(report_file):
os.remove(report_file)
report = mzReport.writer(report_file, columns=repcols)
isMZD = isinstance(report, mzReport.mzDB.SQLiteWriter)
if mascot_web and (_mascot_web_options['ms2_img']
or _mascot_web_options['mascot_var_mods']):
gen_options = {}
try:
gen_options['ms2_img'] = _mascot_web_options['ms2_img']
except KeyError:
pass
try:
gen_options['mascot_var_mods'] = _mascot_web_options[
'mascot_var_mods']
except KeyError:
pass
mascot_web_gen = self.mascot_web(
mascot_id,
date=date,
dat_file=(dat_file
if _mascot_web_options['mascot_ms2'] else None),
isMZD=isMZD,
**gen_options)
mascot_web_gen.next()
if mascot_prot_cov:
prot_cov_gen = self.mascot_prot_coverage(
mascot_id, _mascot_options['ion_cutoff'], date)
prot_cov_gen.next()
prot_desc_dict = {}
if self.mascot.version != mascot_dat_file.res_file.getMascotVer(
)[:len(self.mascot.version)]:
raise TypeError, "Incorrect version of Mascot selected. %s %s" % (
self.mascot.version, mascot_dat_file.res_file.getMascotVer(
)[:len(self.mascot.version)])
missing_desc_count = 0
for row in mascot_dat_file.peptide_report():
row = mzReport.ReportEntry(res_cols, row)
if rank_one and row['Peptide Rank'] != 1:
continue
if (not local) and not (row['Protein Description']
or row['Protein Mass']):
if row['Accession Number'] not in prot_desc_dict:
missing_desc_count += 1
# Very slow!
#prot_desc_dict[row['Accession Number']] = self.mascot.get_description(row['Accession Number'],
#row.get('protein database', '1').split('::')[0],
#mascot_id,
#date)
row['Protein Description'], row[
'Protein Mass'] = prot_desc_dict.get(
row['Accession Number'], ('-', '-'))
md = []
#if peaks:
#(new_row, img_tuples) = peak_gen.send(row)
#row.update(new_row)
#md.extend(img_tuples)
if mascot_web and (_mascot_web_options['ms2_img']
or _mascot_web_options['mascot_var_mods']):
(vartext, img_tup) = mascot_web_gen.send(row)
if _mascot_web_options['mascot_var_mods']:
row['Variable Modifications'] = vartext
if _mascot_web_options['ms2_img']:
md.append(img_tup)
if mascot_prot_cov:
(prot_cov, md_tup) = prot_cov_gen.send(row)
row['Protein Coverage'] = prot_cov
md.append(md_tup)
if combined_file:
row['File'] = ms_file_name
report.write(row, metadata=md)
if missing_desc_count:
print "Missing protein info for %d PSMs." % missing_desc_count
if peaks:
peak_gen.close()
if mascot_web and (_mascot_web_options['ms2_img']
or _mascot_web_options['mascot_var_mods']):
mascot_web_gen.close()
if mascot_prot_cov:
prot_cov_gen.close()
# Mascot-decoy-data finder!
if mascot_dat_file.hasDecoyHits():
decoy_dat_file = interface.MascotDatFile(dat_file,
decoyMode=True,
**_mascot_options)
for row in decoy_dat_file.peptide_report():
report.write(row)
decoy_dat_file.close()
if not combined_file:
if os.path.splitext(report_file)[1].lower() in ('.xls',
'.xlsx',
'.mzd'):
report.close()
self.mascot_headers(report_file, [(None, mascot_header)])
if protein_report:
self.prot_report(report_file,
mascot_dat_file.protein_report())
else:
report.close()
report_files.append(report_file)
else:
if os.path.splitext(report_file)[1].lower() in ('.xls',
'.xlsx',
'.mzd'):
mascot_headers.append((ms_file_name, mascot_header))
mascot_dat_file.close()
if self.cleanup and not local_dat_files:
os.remove(dat_file)
logger_message(
30, 'Multiplierz-Mascot Report for JobID %s Generated!' %
mascot_id)
if combined_file:
if os.path.splitext(report_file)[1].lower() in ('.xls', '.xlsx',
'.mzd'):
report.close()
self.mascot_headers(report_file, mascot_headers)
# not supported right now: protein reports for XLS.
if isMZD and protein_report:
self.prot_report(report_file, None)
else:
report.close()
return [report_file] if combined_file else report_files
def AddImage(self, *args, **kwargs):
logger_message(50, 'This method is deprecated, use add_image() instead')
self.add_image(*args, **kwargs)
def cursor(self):
logger_message(
50, "The cursor attribute is deprecated, use self.conn instead")
return self.conn
def cursor(self):
logger_message(50, "The cursor attribute is deprecated, use self.conn instead")
return self.conn
def __init__(self, parent, login='', password='', writeback = (lambda x: None)):
"""Instantiate the MascotSearch class. This creates a window for submitting to Mascot via Multiplierz.
The basic workflow of this editor is:
1. Select file(s)
2. Customize settings via the GUI
3. Submit to Mascot server
4. Wait (or do other things) while the search runs
"""
wx.Frame.__init__(self, None, -1, "Mascot MS/MS Ions Search", style=wx.DEFAULT_FRAME_STYLE ^ (wx.RESIZE_BORDER | wx.MAXIMIZE_BOX))
self.SetExtraStyle(wx.WS_EX_VALIDATE_RECURSIVELY)
pane = wx.Panel(self, -1, style = wx.TAB_TRAVERSAL | wx.CLIP_CHILDREN)
for i in range(parent.nb.GetPageCount()):
if parent.nb.GetPageText(i) == "Download Mascot":
self.mascot_tab = parent.nb.GetPage(i)
break
else:
logger_message(40, "Couldn't find Mascot downloader")
self.mascot_tab = None
self.login = login
self.password = password
self.writeback = writeback
ms = MascotSearcher(settings.mascot_server)
if settings.mascot_security:
err = ms.login(self.login, self.password)
if err:
logger_message(40, "Error logging in to server: %s" % err)
self.Close()
return
fields = ms.get_fields(settings.mascot_version)
#fields = ms.get_fields_better()
ms.close()
menu_bar = wx.MenuBar()
file_menu = wx.Menu()
load_par = wx.MenuItem(file_menu, -1, "&Open PAR File\tCtrl+O")
file_menu.AppendItem(load_par)
self.Bind(wx.EVT_MENU, self.OnLoadPar, load_par)
save_par = wx.MenuItem(file_menu, -1, "&Save Parameters\tCtrl+S")
file_menu.AppendItem(save_par)
self.Bind(wx.EVT_MENU, self.OnSavePar, save_par)
menu_bar.Append(file_menu, "&File")
output_menu = wx.Menu()
self.open_tabs = wx.MenuItem(output_menu, -1, "&Open Results in Browser", kind=wx.ITEM_CHECK)
output_menu.AppendItem(self.open_tabs)
self.getIDs = wx.MenuItem(output_menu, -1, "&Send IDs to Mascot Downloader", kind=wx.ITEM_CHECK)
output_menu.AppendItem(self.getIDs)
if settings.mascot_server.find('www.matrixscience.com') != -1 or self.mascot_tab is None:
self.getIDs.Enable(False)
self.open_tabs.Check() # set default to open a browser
else:
self.getIDs.Check() # for non-public server, default to report-downloader
menu_bar.Append(output_menu, "&Output")
self.SetMenuBar(menu_bar)
gbs = wx.GridBagSizer(10, 5)
# parameter hash stores the values
self.parameters = {'USERNAME':'',
'USEREMAIL':'',
'COM':'',
'DB':'',
'TAXONOMY':'',
'CLE':'',
'PFA':'',
'MODS':'',
'IT_MODS':'',
'TOL':'',
'TOLU':'',
'PEP_ISOTOPE_ERROR':'',
'ITOL':'',
'ITOLU':'',
'CHARGE':'',
'MASS':'',
'FILE':'',
'FORMAT':'',
'PRECURSOR':'',
'INSTRUMENT':'',
'REPORT':''
}
if settings.mascot_version == '2.1':
self.parameters.update( { 'SEG':'', 'ICAT':'', 'OVERVIEW':'' } )
elif settings.mascot_version >= '2.2':
self.parameters.update( { 'QUANTITATION':'', 'ERRORTOLERANT':'', 'DECOY':'', } )
# labels
labels = (zip(range(6) + range(7,11) + [0,4,5,7,10,11],
[0 for i in range(10)] + [5 for i in range(6)],
['Name',
'Search title',
'Database',
'Taxonomy',
'Enzyme',
'Fixed\nModifications',
u'Peptipe tol. \xb1',
'Peptide Charge',
'Data File',
'Instrument',
'Email',
'Missed\nCleavages',
'Variable\nModifications',
u'MS/MS tol. \xb1',
'Precursor',
'Report Top']))
if settings.mascot_version == '2.1':
labels += (6, 0, 'Protein Mass'),
gbs.Add( wx.StaticText(pane, -1, 'kDa'), (6,3), flag=wx.EXPAND )
elif settings.mascot_version >= '2.2':
labels += (6, 0, 'Quantitation'),
# one fancytext label (for superscript)
gbs.Add( FT.StaticFancyText(pane, -1, '# <sup>13</sup>C', style=wx.ALIGN_RIGHT),
(7,3), flag=wx.EXPAND )
else:
wx.MessageBox("This version of Mascot may not be supported correctly.")
# ----- add labels -----
for x,y,lbl in labels:
gbs.Add( wx.StaticText(pane, -1, lbl, style=wx.ALIGN_RIGHT), (x,y), flag=wx.EXPAND )
gbs.Add( wx.StaticText(pane, -1, 'm/z'), (10,8), flag=wx.EXPAND )
# ----- add controls -----
# name
gbs.Add( wx.TextCtrl(pane, -1, "Your name here", name="USERNAME"), (0,1), (1,4), flag=wx.EXPAND )
# email
gbs.Add( wx.TextCtrl(pane, -1, "", name="USEREMAIL"), (0,6), (1,4), flag=wx.EXPAND )
# title
gbs.Add( wx.TextCtrl(pane, -1, "", name="COM"), (1,1), (1,7), flag=wx.EXPAND )
# database
if settings.mascot_version < '2.3':
gbs.Add( wx.Choice(pane, -1, choices=fields['DB'], name="DB"), (2,1), (1,4), flag=wx.EXPAND )
else:
dbSelector = wx.CheckListBox(pane, -1, choices=fields['DB'], size=(228,81), name="DB")
gbs.Add(dbSelector, (2,1), (1,4), flag=wx.EXPAND )
self.Bind(wx.EVT_CHECKLISTBOX, self.onDatabaseSelect, dbSelector)
# taxonomy
gbs.Add( wx.Choice(pane, -1, choices=fields['TAXONOMY'], name="TAXONOMY"), (3,1), (1,8) )
# enzyme
gbs.Add( wx.Choice(pane, -1, choices=fields['CLE'], name="CLE"), (4,1), (1,4), flag=wx.EXPAND )
# missed cleavages
pfa_min = min(int(s) for s in fields['PFA'])
pfa_max = max(int(s) for s in fields['PFA'])
gbs.Add( wx.SpinCtrl(pane, -1, min=pfa_min, max=pfa_max, initial=int(fields['PFA'][0]), size=(40,21),
style=wx.SP_WRAP|wx.SP_ARROW_KEYS, name="PFA"), (4,6) )
# fixed and variable modifications
mods = wx.CheckListBox(pane, -1, choices=fields['MODS'], size=(228,81), name="MODS")
gbs.Add( mods, (5,1), (1,4), flag=wx.EXPAND )
mods.Bind(wx.EVT_CHECKLISTBOX, self.OnModSelect)
it_mods = wx.CheckListBox(pane, -1, choices=fields['IT_MODS'], size=(228,81), name="IT_MODS")
gbs.Add( it_mods, (5,6), (1,4), flag=wx.EXPAND )
it_mods.Bind(wx.EVT_CHECKLISTBOX, self.OnModSelect)
if settings.mascot_version == '2.1':
gbs.Add( wx.TextCtrl(pane, -1, "", name="SEG", validator=ProtMassVal()), (6,1), (1,2), flag=wx.EXPAND )
gbs.Add( wx.CheckBox(pane, -1, "ICAT", style=wx.ALIGN_RIGHT, name="ICAT"), (6,6), (1,2) )
elif settings.mascot_version >= '2.2':
# quantitation
gbs.Add( wx.Choice(pane, -1, choices=fields['QUANTITATION'], name="QUANTITATION"), (6,1), (1,4), flag=wx.EXPAND )
# peptide tolerance
gbs.Add( wx.TextCtrl(pane, -1, "1.2", size=(40,21), validator=TolValidator(), name="TOL"), (7,1) )
# pep tol units
gbs.Add( wx.Choice(pane, -1, choices=fields['TOLU'], name="TOLU"), (7,2) )
if settings.mascot_version >= '2.2':
# isotope error (# 13C)
pie_min = min(int(s) for s in fields['PEP_ISOTOPE_ERROR'])
pie_max = max(int(s) for s in fields['PEP_ISOTOPE_ERROR'])
gbs.Add( wx.SpinCtrl(pane, -1, min=pie_min, max=pie_max, initial=int(fields.selected['PEP_ISOTOPE_ERROR']),
size=(40,21), style=wx.SP_WRAP|wx.SP_ARROW_KEYS, name="PEP_ISOTOPE_ERROR"), (7,4) )
# MS/MS tolerance
gbs.Add( wx.TextCtrl(pane, -1, "0.6", size=(40,21), validator=TolValidator(), name="ITOL"), (7,6) )
# MS/MS tol units
gbs.Add( wx.Choice(pane, -1, choices=fields['ITOLU'], name="ITOLU"), (7,7) )
# peptide charge
gbs.Add( wx.Choice(pane, -1, choices=fields['CHARGE'], name="CHARGE"), (8,1), (1,4) )
# monoisotopic/average radiobox
gbs.Add( wx.RadioBox( pane, -1, choices=['Monoisotopic','Average'], style=wx.ALIGN_RIGHT, name="MASS"), (8,6), (2,4) )
# file control
self.fname = wx.TextCtrl(pane, -1, "", style=wx.TE_READONLY)
self.fname.BackgroundColour = wx.NamedColour("LIGHT GREY")
gbs.Add( self.fname, (9,1), (1,4), flag=wx.EXPAND )
self.fname.Bind(wx.EVT_LEFT_UP, self.OnChooseFile)
fbutton = wx.Button(pane, -1, "Browse...")
gbs.Add( fbutton, (9,5) )
fbutton.Bind(wx.EVT_BUTTON, self.OnChooseFile)
# instrument
gbs.Add( wx.Choice(pane, -1, choices=fields['INSTRUMENT'], name="INSTRUMENT"), (10,1), (1,4), flag=wx.EXPAND )
# precursor
gbs.Add( wx.TextCtrl(pane, -1, "", size=(60,21), name="PRECURSOR", validator=PreValidator()),
(10,6), (1,2), flag=wx.EXPAND )
if settings.mascot_version == '2.1':
gbs.Add( wx.CheckBox(pane, -1, "Overview", style=wx.ALIGN_RIGHT, name="OVERVIEW"), (11,1), (1,2) )
elif settings.mascot_version >= '2.2':
# decoy/error tolerant checkboxes
gbs.Add( wx.CheckBox(pane, -1, "Decoy", style=wx.ALIGN_RIGHT, name="DECOY"), (11,1), (1,2) )
gbs.Add( wx.CheckBox(pane, -1, "Error Tolerant",
style=wx.ALIGN_RIGHT, name="ERRORTOLERANT", validator=ErrorTolVal()), (11,3), (1,2) )
# report top hits
gbs.Add( wx.Choice(pane, -1, choices=fields['REPORT'], name="REPORT"), (11, 6), (1,2) )
# Submit button
submit = wx.Button(pane, -1, "Submit")
gbs.Add( submit, (12,0), (1,10), flag=wx.EXPAND )
submit.Bind(wx.EVT_BUTTON, self.OnSubmit)
box = wx.BoxSizer()
box.Add(gbs, 0, wx.ALL, 10)
for child in pane.GetChildren():
if isinstance(child,wx.Choice):
if child.GetName() in fields.selected:
child.SetSelection(child.FindString(fields.selected[child.GetName()]))
else:
child.SetSelection(0)
pane.SetSizerAndFit(box)
self.SetClientSize(pane.GetSize())
def Close(self, *args, **kwargs):
logger_message(50, 'This method is deprecated, use close() instead')
self.close(*args, **kwargs)
def add_image(self, column, image):
logger_message(40, 'Images are not supported in CSV files')
def format(self, new_file_name=None):
fh = open(self.orig_file)
#Change header names
header_line = fh.readline()
headers = header_line.strip().split('\t')
new_headers = multiplierz.mzReport.default_columns[:]
new_headers.extend(('MS2 Time', 'Protein Coverage'))
new_headers.remove('Peptide Rank')
new_headers.remove('Query')
new_headers.extend(h for h in headers if h not in self.reps)
if 'Unused' in new_headers:
new_headers.remove('Unused')
if 'Contrib' in new_headers:
new_headers.remove('Contrib')
if 'Sc' in new_headers:
new_headers.remove('Sc')
rows = []
protein_matches = defaultdict(int)
for line in fh:
new_data = dict((h, None) for h in new_headers)
data = dict(zip(headers, line[:-1].split('\t')))
protein_matches[data['Accessions']] += 1
for h in data:
if h in self.reps and self.reps[h] in new_data:
new_data[self.reps[h]] = data[h]
elif h in new_data:
new_data[h] = data[h]
elif h not in ('Unused', 'Contrib', 'Sc'):
logger_message(10, 'Missing key: %s' % h)
if 'Modifications' in data:
new_data['Variable Modifications'] = self.convert_var_mod(
data['Modifications'])
if 'Cleavages' in data:
new_data['Missed Cleavages'] = data['Cleavages'].count(
'missed')
if 'Time' in data and 'Spectrum' in data:
new_data['Spectrum Description'] = self.convert_spectrum(
data['Spectrum'], data['Time'])
rows.append(new_data)
fh.close()
for row in rows:
row['Protein Matches'] = protein_matches[row['Accession Number']]
dir_split = os.path.split(self.orig_file)
if not new_file_name:
new_file_name = os.path.join(dir_split[0], "mz_" + dir_split[1])
report = multiplierz.mzReport.writer(new_file_name,
columns=new_headers)
for row in rows:
report.write(row)
report.close()
def mascot_web(self,
mascot_id,
ms2_img,
mascot_var_mods=True,
instrument='ESI-TRAP',
date=None,
isMZD=False,
dat_file=None,
im_size=(8.0, 6.0)):
logger_message(30, 'Downloading Mascot Spectra...')
if mascot_var_mods and not ms2_img:
mods_only = True
if ms2_img:
mods_only = False
if mascot_var_mods and self.mascot.version >= '2.2':
logger_message(
40,
'Warning: Variable modifications already present, overwriting')
if dat_file:
info_gen = interface.mascot_ms2(dat_file)
info_gen.next()
row = (yield None)
while row:
query = row['Query']
logger_message(10,
'Downloading Mascot Spectra for query: %s' % query)
peptide = row['Peptide Sequence']
charge = row['Charge']
score = row['Peptide Score']
pep_rank = row['Peptide Rank']
if dat_file:
(peptide, var_text, mass_int, mass_labels,
ion_list) = info_gen.send((query, pep_rank))
mass_int = tuple(sorted(mass_int))
if ms2_img:
if isMZD:
image_tup = ('Peptide Sequence', 'ms2',
(mass_int, 'c', peptide, mass_labels,
ion_list, charge, score))
else:
(h, img_file) = mkstemp(suffix='.png',
prefix='mascot_',
dir=myTemp)
os.close(h)
logger_message(20, 'Drawing MS MS Mass Plot...')
mz_image.make_ms2_im(img_file[:-4],
mass_int,
'c',
peptide,
mass_labels,
ion_list,
charge,
score,
im_size=im_size)
image_tup = ('Peptide Sequence', 'image', img_file)
else:
image_tup = None
else:
(h, img_file) = mkstemp(suffix='.gif',
prefix='mascot_',
dir=myTemp)
os.close(h)
(var_text, ionInfo, phosphoPos,
oxidPos) = self.mascot.get_msms(query,
img_file,
mascot_id=mascot_id,
score=score,
pep_rank=pep_rank,
date=date,
sequence=peptide,
mod_only=mods_only,
dat_file=dat_file)
if ms2_img:
(h, gifpath) = mkstemp(suffix='.png',
prefix='combo_',
dir=myTemp)
os.close(h)
mz_image.make_mascot_ms2_im(gifpath, img_file, peptide,
charge, score, ionInfo,
phosphoPos, oxidPos,
instrument)
image_tup = ('Peptide Sequence', 'image', gifpath)
else:
image_tup = None
if not mascot_var_mods:
var_text = None
row = (yield (var_text, image_tup))
def add_image(self, column, image):
logger_message(40, 'Images are not supported in CSV files')
def WriteRow(self, *args, **kwargs):
logger_message(50, 'This method is deprecated, use write() instead')
self.write(*args, **kwargs)
