def convert_pilot_to_peptagram(params, print_fn=sys.stdout.write):
if len(params['files_and_labels']) == 0:
raise ValueError('No files were selected.')
size = parse.size_str(params['fasta'])
print_fn("Using sequences from %s (%s)...\n" % (params['fasta'], size))
proteins = {}
labels = []
for fname, label in params['files_and_labels']:
labels.append(label)
size = parse.size_str(fname)
print_fn("Processing %s (%s)...\n" % (fname, size))
these_proteins = peptagram.pilot.get_proteins(fname)
proteins = peptagram.proteins.merge_two_proteins(
proteins, these_proteins)
peptagram.proteins.filter_proteins(proteins, params)
peptagram.proteins.make_graphical_comparison_visualisation({
'title': params['title'],
'proteins': proteins,
'source_labels': labels,
'color_names': [0, 1],
'mask_labels': [],
'out_dir': params['out_dir'],
})
html = os.path.join(params['out_dir'], 'index.html')
size = parse.size_str(params['out_dir'])
print_fn('Successfully built peptagram (%s): %s\n' % (size, html))
return os.path.abspath(html)
def convert_morpheus_to_peptagram(params, print_fn=sys.stdout.write):
if len(params['files_and_labels']) == 0:
raise ValueError('No files were selected.')
q_good = float(params['q_good'])
q_cutoff = float(params['q_cutoff'])
modifications = params['modifications']
proteins = {}
labels = []
for entry in params['files_and_labels']:
fname = entry[0]
size = parse.size_str(fname)
print_fn("Processing %s (%s)...\n" % (fname, size))
protein_group = fname.replace('PSMs', 'protein_groups')
size = parse.size_str(protein_group)
print_fn("Inferring protein group: %s (%s)\n" % (protein_group, size))
these_proteins, these_sources = \
peptagram.morpheus.get_proteins_and_sources(
protein_group, fname, modifications, q_good, q_cutoff)
proteins = peptagram.proteins.merge_two_proteins(
proteins, these_proteins)
labels.extend(map(parse.basename, these_sources))
n_peak = int(params['n_peak'])
for i_source, (mzml, label) in enumerate(params['mzmls_and_labels']):
print_fn("Extracting spectra from %s (%s)...\n" %
(mzml, parse.size_str(mzml)))
peptagram.mzml.load_mzml(proteins, i_source, mzml, n_peak)
peptagram.proteins.filter_proteins(proteins, params)
peptagram.proteins.make_graphical_comparison_visualisation({
'title':
params['title'],
'proteins':
proteins,
'source_labels':
labels,
'color_names': ['Q=%s' % q_good, 'Q=%s' % q_cutoff],
'mask_labels': [],
'out_dir':
params['out_dir'],
})
html = os.path.join(params['out_dir'], 'index.html')
size = parse.size_str(params['out_dir'])
print_fn('Successfully built peptagram (%s): %s\n' % (size, html))
return os.path.abspath(html)
def convert_morpheus_to_peptagram(params, print_fn=sys.stdout.write):
if len(params['files_and_labels']) == 0:
raise ValueError('No files were selected.')
q_good = float(params['q_good'])
q_cutoff = float(params['q_cutoff'])
modifications = params['modifications']
proteins = {}
labels = []
for entry in params['files_and_labels']:
fname = entry[0]
size = parse.size_str(fname)
print_fn("Processing %s (%s)...\n" % (fname, size))
protein_group = fname.replace('PSMs', 'protein_groups')
size = parse.size_str(protein_group)
print_fn("Inferring protein group: %s (%s)\n" % (protein_group, size))
these_proteins, these_sources = \
peptagram.morpheus.get_proteins_and_sources(
protein_group, fname, modifications, q_good, q_cutoff)
proteins = peptagram.proteins.merge_two_proteins(
proteins, these_proteins)
labels.extend(map(parse.basename, these_sources))
n_peak = int(params['n_peak'])
for i_source, (mzml, label) in enumerate(params['mzmls_and_labels']):
print_fn("Extracting spectra from %s (%s)...\n" % (mzml, parse.size_str(mzml)))
peptagram.mzml.load_mzml(
proteins, i_source, mzml, n_peak)
peptagram.proteins.filter_proteins(proteins, params)
peptagram.proteins.make_graphical_comparison_visualisation({
'title': params['title'],
'proteins': proteins,
'source_labels': labels,
'color_names': ['Q=%s' % q_good, 'Q=%s' % q_cutoff],
'mask_labels': [],
'out_dir': params['out_dir'],
})
html = os.path.join(params['out_dir'], 'index.html')
size = parse.size_str(params['out_dir'])
print_fn('Successfully built peptagram (%s): %s\n' % (size, html))
return os.path.abspath(html)
def convert_maxquant_to_peptagram(params, print_fn=sys.stdout.write):
if len(params['files_and_labels']) == 0:
raise ValueError('No files were selected.')
size = parse.size_str(params['fasta'])
print_fn("Using sequences from %s (%s)...\n" % (params['fasta'], size))
great_expect = float(params['great_expect'])
cutoff_expect = float(params['cutoff_expect'])
proteins = {}
labels = []
for entry in params['files_and_labels']:
fname = entry[0]
size = parse.size_str(fname)
print_fn("Processing %s (%s)...\n" % (fname, size))
these_proteins, sources = \
peptagram.maxquant.get_proteins_and_sources(
fname, great_expect=great_expect, cutoff_expect=cutoff_expect)
proteins = peptagram.proteins.merge_two_proteins(
proteins, these_proteins)
labels.extend(map(parse.basename, sources))
peptagram.proteins.filter_proteins(proteins, params)
peptagram.proteins.make_graphical_comparison_visualisation({
'title':
params['title'],
'proteins':
proteins,
'source_labels':
labels,
'color_names': [
'PEP=%s' % params['great_expect'],
'PEP=%s' % params['cutoff_expect']
],
'mask_labels': [],
'out_dir':
params['out_dir'],
})
html = os.path.join(params['out_dir'], 'index.html')
size = parse.size_str(params['out_dir'])
print_fn('Successfully built peptagram (%s): %s\n' % (size, html))
return os.path.abspath(html)
def run(self, params):
self.print_output("Building new peptagram...\n")
seqids = []
proteins = {}
for data in self.datas:
for seqid, protein in data['proteins'].iteritems():
if seqid not in proteins:
new_protein = peptagram.proteins.new_protein(seqid)
new_protein['sources'] = []
for key in ['sequence', 'description']:
new_protein[key] = protein[key]
new_protein['attr'] = protein['attr']
seqids.append(seqid)
proteins[seqid] = new_protein
new_sources = []
labels = []
for source_label, label in params['in_peptagram']:
i_data, i_source = self.extract_indices_from_source_label(
source_label)
new_sources.append((i_data, i_source))
labels.append(label)
for seqid in seqids:
protein = proteins[seqid]
for i_data, i_source in new_sources:
old_data = self.datas[i_data]
if seqid in old_data['proteins']:
old_protein = old_data['proteins'][seqid]
old_source = old_protein['sources'][i_source]
protein['sources'].append(old_source)
else:
protein['sources'].append({'matches': []})
peptagram.proteins.filter_proteins(proteins, params)
data = {
'title': params['title'],
'proteins': proteins,
'source_labels': labels,
'color_names': ['1.5', '1', '0.66'],
'mask_labels': [],
}
out_dir = os.path.abspath(params['out_dir'])
peptagram.proteins.make_graphical_comparison_visualisation(
data, out_dir)
self.print_output(
'Successfully built peptagram webpage (%s):\n' % \
parse.size_str(out_dir))
html = os.path.join(out_dir, 'index.html')
cmd_fn = lambda: webbrowser.open('file://' + html)
self.print_output(html, cmd_fn)
def convert_prophet_peptagram(params, print_fn=sys.stdout.write):
if len(params['files_and_labels']) == 0:
raise ValueError('No files were selected.')
size = parse.size_str(params['fasta'])
print_fn("Using sequences from %s (%s)...\n" % (params['fasta'], size))
size = parse.size_str(params['prot_xml'])
print_fn('Processing %s (%s)...\n' % (params['prot_xml'], size))
proteins = {}
prot_xml = params['prot_xml']
peptide_error = float(params['peptide_error'])
protein_error = float(params['protein_error'])
great_expect = float(params['great_expect'])
cutoff_expect = float(params['cutoff_expect'])
pep_xmls = [e[0] for e in params['files_and_labels']]
size = parse.size_str(*pep_xmls)
print_fn('Processing %s (%s)...\n' % (pep_xmls, size))
proteins, labels = peptagram.prophet.get_proteins_and_sources(
prot_xml,
pep_xmls,
peptide_error=peptide_error,
protein_error=protein_error,
good_expect=great_expect,
cutoff_expect=cutoff_expect)
labels = map(parse.basename, labels)
peptagram.proteins.filter_proteins(proteins, params)
peptagram.proteins.make_graphical_comparison_visualisation({
'title': params['title'],
'proteins': proteins,
'source_labels': labels,
'color_names': ['expect=%s' % great_expect, 'expect=%s' % cutoff_expect],
'mask_labels': [],
'out_dir': params['out_dir'],
})
html = os.path.join(params['out_dir'], 'index.html')
size = parse.size_str(params['out_dir'])
print_fn('Successfully built peptagram (%s): %s\n' % (size, html))
return os.path.abspath(html)
def run(self, params):
self.print_output("Building new peptagram...\n")
seqids = []
proteins = {}
for data in self.datas:
for seqid, protein in data['proteins'].iteritems():
if seqid not in proteins:
new_protein = peptagram.proteins.new_protein(seqid)
new_protein['sources'] = []
for key in ['sequence', 'description']:
new_protein[key] = protein[key]
new_protein['attr'] = protein['attr']
seqids.append(seqid)
proteins[seqid] = new_protein
new_sources = []
labels = []
for source_label, label in params['in_peptagram']:
i_data, i_source = self.extract_indices_from_source_label(source_label)
new_sources.append((i_data, i_source))
labels.append(label)
for seqid in seqids:
protein = proteins[seqid]
for i_data, i_source in new_sources:
old_data = self.datas[i_data]
if seqid in old_data['proteins']:
old_protein = old_data['proteins'][seqid]
old_source = old_protein['sources'][i_source]
protein['sources'].append(old_source)
else:
protein['sources'].append({'matches':[]})
peptagram.proteins.filter_proteins(proteins, params)
data = {
'title': params['title'],
'proteins': proteins,
'source_labels': labels,
'color_names': ['1.5', '1', '0.66'],
'mask_labels': [],
}
out_dir = os.path.abspath(params['out_dir'])
peptagram.proteins.make_graphical_comparison_visualisation(
data, out_dir)
self.print_output(
'Successfully built peptagram webpage (%s):\n' % \
parse.size_str(out_dir))
html = os.path.join(out_dir, 'index.html')
cmd_fn = lambda: webbrowser.open('file://' + html)
self.print_output(html, cmd_fn)
def convert_xtandem_to_peptagram(params, print_fn=sys.stdout.write):
if len(params['files_and_labels']) == 0:
raise ValueError('No files were selected.')
n_peak = int(params['n_peak'])
great_expect = float(params['great_expect'])
cutoff_expect = float(params['cutoff_expect'])
proteins = {}
labels = []
for fname, label in params['files_and_labels']:
labels.append(label)
size = parse.size_str(fname)
print_fn("Processing %s (%s)...\n" % (fname, size))
these_proteins = peptagram.xtandem.get_proteins(
fname,
n_peak=n_peak,
good_expect=great_expect,
cutoff_expect=cutoff_expect)
proteins = peptagram.proteins.merge_two_proteins(
proteins, these_proteins)
peptagram.proteins.filter_proteins(proteins, params)
peptagram.proteins.make_graphical_comparison_visualisation({
'title':
params['title'],
'proteins':
proteins,
'source_labels':
labels,
'color_names': [great_expect, cutoff_expect],
'mask_labels': [],
'out_dir':
params['out_dir'],
})
html = os.path.join(params['out_dir'], 'index.html')
size = parse.size_str(params['out_dir'])
print_fn('Successfully built peptagram (%s): %s\n' % (size, html))
return os.path.abspath(html)
def convert_maxquant_to_peptagram(params, print_fn=sys.stdout.write):
if len(params['files_and_labels']) == 0:
raise ValueError('No files were selected.')
size = parse.size_str(params['fasta'])
print_fn("Using sequences from %s (%s)...\n" % (params['fasta'], size))
great_expect = float(params['great_expect'])
cutoff_expect = float(params['cutoff_expect'])
proteins = {}
labels = []
for entry in params['files_and_labels']:
fname = entry[0]
size = parse.size_str(fname)
print_fn("Processing %s (%s)...\n" % (fname, size))
these_proteins, sources = \
peptagram.maxquant.get_proteins_and_sources(
fname, great_expect=great_expect, cutoff_expect=cutoff_expect)
proteins = peptagram.proteins.merge_two_proteins(
proteins, these_proteins)
labels.extend(map(parse.basename, sources))
peptagram.proteins.filter_proteins(proteins, params)
peptagram.proteins.make_graphical_comparison_visualisation({
'title': params['title'],
'proteins': proteins,
'source_labels': labels,
'color_names': ['PEP=%s'%params['great_expect'],
'PEP=%s'%params['cutoff_expect']],
'mask_labels': [],
'out_dir': params['out_dir'],
})
html = os.path.join(params['out_dir'], 'index.html')
size = parse.size_str(params['out_dir'])
print_fn('Successfully built peptagram (%s): %s\n' % (size, html))
return os.path.abspath(html)
def convert_xtandem_to_peptagram(params, print_fn=sys.stdout.write):
if len(params['files_and_labels']) == 0:
raise ValueError('No files were selected.')
n_peak = int(params['n_peak'])
great_expect = float(params['great_expect'])
cutoff_expect = float(params['cutoff_expect'])
proteins = {}
labels = []
for fname, label in params['files_and_labels']:
labels.append(label)
size = parse.size_str(fname)
print_fn("Processing %s (%s)...\n" % (fname, size))
these_proteins = peptagram.xtandem.get_proteins(
fname,
n_peak=n_peak,
good_expect=great_expect,
cutoff_expect=cutoff_expect)
proteins = peptagram.proteins.merge_two_proteins(
proteins, these_proteins)
peptagram.proteins.filter_proteins(proteins, params)
peptagram.proteins.make_graphical_comparison_visualisation({
'title': params['title'],
'proteins': proteins,
'source_labels': labels,
'color_names': [great_expect, cutoff_expect],
'mask_labels': [],
'out_dir': params['out_dir'],
})
html = os.path.join(params['out_dir'], 'index.html')
size = parse.size_str(params['out_dir'])
print_fn('Successfully built peptagram (%s): %s\n' % (size, html))
return os.path.abspath(html)
def convert_mascot_to_peptagram(params, print_fn=sys.stdout.write):
if len(params['files_and_labels']) == 0:
raise ValueError('No files were selected.')
size = parse.size_str(params['fasta'])
print_fn("Using sequences from %s (%s)...\n" % (params['fasta'], size))
great_ionscore = float(params['great_ionscore'])
cutoff_ionscore = float(params['cutoff_ionscore'])
proteins = {}
labels = []
for fname, label in params['files_and_labels']:
labels.append(label)
size = parse.size_str(fname)
print_fn("Processing %s (%s)...\n" % (fname, size))
these_proteins = peptagram.mascot.get_proteins(
fname, great_ionscore, cutoff_ionscore)
proteins = peptagram.proteins.merge_two_proteins(
proteins, these_proteins)
peptagram.proteins.filter_proteins(proteins, params)
peptagram.proteins.make_graphical_comparison_visualisation({
'title': params['title'],
'proteins': proteins,
'source_labels': labels,
'color_names': [great_ionscore, cutoff_ionscore],
'out_dir': params['out_dir'],
})
html = os.path.join(params['out_dir'], 'index.html')
size = parse.size_str(params['out_dir'])
print_fn('Successfully built peptagram (%s): %s\n' % (size, html))
return os.path.abspath(html)