def background(list_of_replicates, input_fragment_value,
unlabeled_fragment_value, isotope_dict):
parent_frag, daughter_frag = input_fragment_value.frag
iso_elem = helpers.get_isotope_element(parent_frag.isotracer)
parent_label = parent_frag.get_num_labeled_atoms_isotope(
parent_frag.isotracer)
parent_atoms = parent_frag.number_of_atoms(iso_elem)
na = helpers.get_isotope_na(parent_frag.isotracer, isotope_dict)
daughter_atoms = daughter_frag.number_of_atoms(iso_elem)
daughter_label = daughter_frag.get_num_labeled_atoms_isotope(
parent_frag.isotracer)
replicate_value = {}
for replicate_group in list_of_replicates:
background_list = []
for each_replicate in replicate_group:
noise = background_noise(
unlabeled_fragment_value.data[each_replicate], na,
parent_atoms, parent_label, daughter_atoms, daughter_label)
background = background_subtraction(
input_fragment_value.data[each_replicate], noise)
background_list.append(background)
background_value = max(background_list)
for each_replicate in replicate_group:
replicate_value[each_replicate] = background_value
return replicate_value
def make_all_corr_matrices(isotracers, formula_dict, na_dict, autodetect,
corr_limit):
"""
This function forms correction matrix M, such that Mx=y where y is the
observed isotopic distribution and x is the expected distribution of input
labels, for each indistinguishable element for a particular isotracer one by one.
Args:
isotracers - list of isotracers presnt in the formula.
formula_dict - dict of form- element:number of atoms in molecule (e.g. {'C':2,'O':1,'H':6})
na_dict - dict of form- element:expected isotopic distribution
eleme_corr - dict of form- isotracer_element:indistinguishable elements list(elements with identical mass shift)
Eg- { 'C13': ['H', 'O17'], 'N15': ['H']}
Returns:
corr_mats - dict of form- isotracer_element: correction matrix
"""
corr_mats = {}
for isotracer in isotracers:
trac_atom = get_isotope_element(isotracer)
try:
indist_list = corr_limit[str(trac_atom)].keys()
except KeyError:
indist_list = []
corr_mats[isotracer] = make_correction_matrix(isotracer, formula_dict,
na_dict, indist_list,
autodetect,
corr_limit[trac_atom])
return corr_mats
def make_all_corr_matrices(isotracers, formula_dict, na_dict, eleme_corr):
corr_mats = {}
for isotracer in isotracers:
trac_atom = get_isotope_element(isotracer)
try:
indist_list = eleme_corr[trac_atom]
except KeyError:
indist_list = []
corr_mats[isotracer] = make_correction_matrix(trac_atom, formula_dict,
na_dict, indist_list)
return corr_mats
def na_correct_mimosa_algo_array(parent_frag_m, daughter_frag_n, intensity_m_n, intensity_m_1_n, intensity_m_1_n_1,
isotope, na, decimals):
iso_elem = helpers.get_isotope_element(isotope)
p = parent_frag_m.number_of_atoms(iso_elem)
d = daughter_frag_n.number_of_atoms(iso_elem)
m = parent_frag_m.get_num_labeled_atoms_isotope(isotope)
n = daughter_frag_n.get_num_labeled_atoms_isotope(isotope)
corrected_intensity = intensity_m_n * (1 + na * (p - m)) - intensity_m_1_n * na * ((p - d) - (m - n - 1)) -\
intensity_m_1_n_1 * na * (d - (n - 1))
return np.around(corrected_intensity, decimals)
def eleme_corr_invalid_entry(iso_tracers, eleme_corr):
"""
This function raises an error if the user inputs incorrect values in eleme_corr dictionary.
The indistinguishable element specified in the eleme_corr dictionary cannot be an isotracer
element. This is logically incorrect input, hence raises an error.
"""
for key, value in eleme_corr.iteritems():
for isotracer in iso_tracers:
el = get_isotope_element(isotracer)
if el in value:
raise KeyError('An iso tracer cannot'
' be an Indistinguishable element (' + el +
') , invalid input in eleme_corr dictionary')
def add_mass_and_no_of_atoms_info_frm_label(df):
"""
This function adds column of parent isotopic mass, daughter isotopic mass, parent molecular mass,
daughter molecular mass, no of labeled atoms parent and daughter,
total no of atoms parent and daughter and isotracer column to the dataframe.
"""
msms_df = get_parent_daughter_iso_mass_col_and_isotracer_from_label(df)
isotracer = msms_df[multiquant.ISOTRACER].unique()
iso_elem = hlp.get_isotope_element(isotracer[0])
input_df = pd.DataFrame()
final_df = pd.DataFrame()
input_df = get_mol_mass_and_number_of_atoms(msms_df,
multiquant.PARENT_FORM,
'PARENT', isotracer[0],
iso_elem, input_df)
final_df = get_mol_mass_and_number_of_atoms(input_df, multiquant.FORMULA,
'DAUGHTER', isotracer[0],
iso_elem, final_df)
return final_df, isotracer
def test_get_isotope_details():
assert help.get_isotope_element('C13') == 'C'
def make_correction_matrix(isotracer, formuladict, na_dict, indist_elems,
autodetect, corr_limit):
"""create matrix M such that Mx=y where y is the observed isotopic distribution
and x is the expected distribution of input labels
formuladict: dict of element:number of atoms in molecule (e.g. {'C':2,'O':1,'H':6})
trac_atom: element with input labeling
indist_elems: elements with identical mass shift
na_dict: dict of - element:expected isotopic distribution
:TODO This function relates to issue NCT-247. Need to change the function
in more appropriate way.
"""
lookup_dict = {
'O': ['O16', 'O17', 'O18'],
'S': ['S32', 'S33', 'S34'],
'Si': ['Si28', 'Si29', 'Si30']
}
trac_atom = get_isotope_element(isotracer)
if (isotracer == 'O18' or isotracer == 'S34' or isotracer == 'Si30'):
M = make_expected_na_matrix_heavy(formuladict.get(trac_atom, 0),
na_dict[trac_atom])
else:
M = make_expected_na_matrix(formuladict.get(trac_atom, 0),
na_dict[trac_atom])
M_indist = []
indist_elems_copy = copy(indist_elems)
na_dict_copy = copy(na_dict)
for e in indist_elems:
if e in indist_elems_copy:
e2 = get_isotope_element(e)
if e2 in formuladict:
try:
if (lookup_dict[e2][1]
in indist_elems_copy) and (lookup_dict[e2][2]
in indist_elems_copy):
corr_limit_1 = int(corr_limit[lookup_dict[e2][1]])
corr_limit_2 = int(corr_limit[lookup_dict[e2][2]])
M_indist.append(
add_indistinguishable_element_for_autodetect_heavy(
M, formuladict[e2], na_dict_copy[e2],
corr_limit_1, corr_limit_2))
indist_elems_copy.remove(lookup_dict[e2][1])
indist_elems_copy.remove(lookup_dict[e2][2])
elif ((lookup_dict[e2][1] in indist_elems_copy) and (lookup_dict[e2][2] not in indist_elems_copy)) or \
((lookup_dict[e2][1] not in indist_elems_copy) and (lookup_dict[e2][2] in indist_elems_copy)):
pos = lookup_dict[e2].index(str(e))
list_values = [0] * 3
list_values[0] = na_dict_copy[e2][0]
list_values[pos] = na_dict_copy[e2][pos]
na_dict_copy[str(e)] = list_values
corr_limit_1 = int(corr_limit[e])
M_indist.append(
add_indistinguishable_element_for_autodetect(
M, formuladict[e2], na_dict_copy[e],
corr_limit_1))
else:
corr_limit_1 = int(corr_limit[e])
M_indist.append(
add_indistinguishable_element_for_autodetect(
M, formuladict[e2], na_dict_copy[e],
corr_limit_1))
except Exception, exception_str:
corr_limit_1 = int(corr_limit[e])
M_indist.append(
add_indistinguishable_element_for_autodetect(
M, formuladict[e2], na_dict_copy[e], corr_limit_1))