def _parse_input_old_style(self, input_str):
"""Re-initialize the class with a new sequence using the old style
Args:
input_str (str): possible input formats include the following examples
Examples:
'+H2O2H2-OH',
'+{0}'.format('H2O'),
'{peptide}'.format(pepitde='ELVISLIVES'),
'{peptide}+{0}'.format('PO3', peptide='ELVISLIVES'),
'{peptide}#{unimod}:{pos}'.format(
peptide = 'ELVISLIVES',
unimod = 'Oxidation',
pos = 1
)
"""
self.clear()
# reset the shiznit
if "#" in input_str:
# Unimod Style format
if self._unimod_parser is None:
self._unimod_parser = unimod_mapper.UnimodMapper(
xml_file_list=self.unimod_files,
add_default_files=self.add_default_files,
)
self._parse_sequence_unimod_style(input_str)
else:
self._parse_sequence_piqdb_style(input_str)
def test_read_usermod_file_exclude_defaults(self):
# the order of the files shouldn't change the unimodIDs
for data in MULTIFILE_TESTS:
um = unimod_mapper.UnimodMapper(xml_file_list=data["order"],
add_default_files=False)
assert len(um.data_list) == data["entries"]
for case in data["excluded"]:
assert case["out"] == um.name2id_list(case["in"])
#!/usr/bin/env python
# encoding: utf-8
import os
import sys
import pytest
# this block is not needed anymore, when we have a proper package
sys.path.append(
os.path.abspath(os.path.join(os.path.dirname(__file__), os.pardir)))
# EOBlock
import unimod_mapper
M = unimod_mapper.UnimodMapper()
CONVERSIONS = [
{
"function": M.name2mass,
"cases": [{
"in": {
"args": ["ICAT-G:2H(8)"]
},
"out": 494.30142
}],
},
{
"function":
M.name2composition,
"cases": [{
"in": {
"args": ["ICAT-G:2H(8)"]
def add_modifications(self, modifications):
"""Adds modifications to the instance.
Args:
modifications (str): modifications given as unimod names with positional information,
separated by semicolons, i.e: "unimod1:pos;unimod2:pos"
"""
if self._unimod_parser is None:
self._unimod_parser = unimod_mapper.UnimodMapper(
xml_file_list=self.unimod_files,
add_default_files=self.add_default_files,
)
modification_list = []
if self.modifications is not None:
modification_list = self.modifications.split(";")
modification_list.extend(modifications.split(";"))
self.modifications = ";".join(modification_list)
pattern = re.compile(r""":(?P<pos>[0-9]*$)""")
for unimod in modifications.split(";"):
if unimod == "":
continue
unimod = unimod.strip()
if ":" not in unimod:
raise Exception("""
Error in chemical_composition.py:
This unimod: {0} requires positional information
""".format(unimod))
for occ, match in enumerate(pattern.finditer(unimod)):
unimodcomposition = self._unimod_parser.name_to_composition(
unimod[:match.start()])
if len(unimodcomposition) == 0:
raise Exception("""
Error in chemical_composition.py:
Cannot map unimod {0}
""".format(unimod[:match.start()]))
unimodcomposition = unimodcomposition[0]
if occ >= 1:
raise Exception("""
Error in chemical_composition.py:
The unimod {0} contains multiple ":", preventing to map the position correctly
""".format(unimod))
position = int(match.group("pos"))
if position not in self.unimod_at_pos.keys():
self.unimod_at_pos[position] = []
self.unimod_at_pos[position].append(unimod[:match.start()])
for k, v in unimodcomposition.items():
self[k] += v
# Storing position related modifications
position = int(match.group("pos"))
if position == 0:
# E.g. Acetylation at pos 0 indicates N-Term
# but has to be counted for position 1 in this class
position = 1
if position not in self.composition_of_mod_at_pos.keys():
self.composition_of_mod_at_pos[position] = ddict(int)
if position not in self.composition_at_pos.keys():
self.composition_at_pos[position] = ddict(int)
for k, v in unimodcomposition.items():
self.composition_of_mod_at_pos[position][k] += v
self.composition_at_pos[position][k] += v
return
def test_unimod_files_is_none(self):
um = unimod_mapper.UnimodMapper(xml_file_list=None)
names = [x.name for x in um.unimod_xml_names]
assert names == ["usermod.xml", "unimod.xml"]
def test_read_multiple_unimod_files(self):
# the order of the files shouldn't change the unimodIDs
for data in MULTIFILE_TESTS:
um = unimod_mapper.UnimodMapper(xml_file_list=data["order"])
for case in data["included"]:
assert case["out"] == um.name2id_list(case["in"])
# this block is not needed anymore, when we have a proper package
# test_dir = Path(__file__).parent
# package_dir = test_dir.parent
# sys.path.append(package_dir)
# EOBlock
import unimod_mapper
package_dir = Path(unimod_mapper.__file__).parent
test_dir = Path(__file__).parent
# test_dir = Path(unimod_mapper.__file__).parent.parent / "tests"
# package_dir = test_dir.parent
unimod_path = package_dir.joinpath("unimod.xml")
usermod_path = test_dir.joinpath("usermod.xml")
M = unimod_mapper.UnimodMapper(
xml_file_list=[unimod_path, usermod_path, unimod_path])
CONVERSIONS = [
{
"function":
M.name2mass_list,
"cases": [{
"in": {
"args": ["ICAT-G:2H(8)"]
},
"out": [494.30142, 494.30142]
}],
},
{
"function": M.name2first_mass,
"cases": [{