corems.mass_spectrum.input.massList
1__author__ = "Yuri E. Corilo" 2__date__ = "Jun 12, 2019" 3 4import warnings 5 6import pandas as pd 7 8from corems.encapsulation.constant import Atoms, Labels 9from corems.mass_spectrum.factory.MassSpectrumClasses import ( 10 MassSpecCentroid, 11 MassSpecProfile, 12) 13from corems.mass_spectrum.input.baseClass import MassListBaseClass 14from corems.molecular_formula.factory.MolecularFormulaFactory import MolecularFormula 15 16 17class ReadCoremsMasslist(MassListBaseClass): 18 """ 19 The ReadCoremsMasslist object reads processed mass list data types 20 and returns the mass spectrum obj with the molecular formula obj 21 22 **Only available for centroid mass spectrum type:** it will ignore the parameter **isCentroid** 23 Please see MassListBaseClass for more details 24 25 """ 26 27 def get_mass_spectrum( 28 self, loadSettings: bool = True, auto_process: bool = True 29 ) -> MassSpecCentroid: 30 """ 31 Get the mass spectrum object from the processed mass list data. 32 33 Parameters 34 ---------- 35 loadSettings : bool, optional 36 Whether to load the settings for the mass spectrum. Default is True. 37 auto_process : bool, optional 38 Whether to automatically process the mass spectrum on instantiation. 39 When False, molecular formulas are not attached; call 40 ``process_mass_spec`` and then ``add_molecular_formula`` on the 41 returned object. Default is True. 42 43 Returns 44 ------- 45 MassSpecCentroid 46 The mass spectrum object. 47 48 Raises 49 ------ 50 ValueError 51 If the input file is not a valid CoreMS file. 52 """ 53 54 dataframe = self.get_dataframe() 55 56 if not set( 57 ["H/C", "O/C", "Heteroatom Class", "Ion Type", "Is Isotopologue"] 58 ).issubset(dataframe.columns): 59 raise ValueError( 60 "%s it is not a valid CoreMS file" % str(self.file_location) 61 ) 62 63 self.check_columns(dataframe.columns) 64 65 dataframe.rename(columns=self.parameters.header_translate, inplace=True) 66 67 # "Ion Charge" is dual-purpose in CoreMS tables: spectrum/peak polarity 68 # for unassigned rows (±1), formula assignment charge when assigned 69 # (may be |z|>1). Spectrum polarity is only the sign. 70 # Use iloc for pandas 3 / CoW-safe indexing. 71 raw_charge = int(dataframe["Ion Charge"].iloc[0]) 72 if raw_charge == 0: 73 raise ValueError("Ion Charge column must be non-zero to derive polarity") 74 polarity = 1 if raw_charge > 0 else -1 75 76 output_parameters = self.get_output_parameters(polarity) 77 78 mass_spec_obj = MassSpecCentroid( 79 dataframe.to_dict(orient="list"), 80 output_parameters, 81 auto_process=auto_process, 82 ) 83 84 if loadSettings is True: 85 self.load_settings(mass_spec_obj, output_parameters) 86 87 if auto_process: 88 # Formulas first. add_molecular_formula matches the uncalibrated 89 # "m/z" column against mz_exp, which returns mz_cal once restored. 90 self.add_molecular_formula(mass_spec_obj, dataframe) 91 self.restore_peak_calibration(mass_spec_obj, dataframe) 92 93 return mass_spec_obj 94 95 def restore_peak_calibration(self, mass_spec_obj, dataframe): 96 """Restore each peak's ``mz_cal`` from the stored "Calibrated m/z" column. 97 98 The peak table always stores both the uncalibrated "m/z" and the 99 (possibly calibrated) "Calibrated m/z", but ``MassSpecCentroid`` is 100 built only from "m/z" -- so without this, a reloaded peak loses its 101 own calibration even when the spectrum it came from had been 102 calibrated. Only peaks whose "Calibrated m/z" actually differs from 103 "m/z" are touched; an unmatched or never-calibrated peak's ``mz_cal`` 104 is left as ``None``, same as before this method existed. 105 106 Parameters 107 ---------- 108 mass_spec_obj : MassSpecCentroid 109 The mass spectrum object whose peaks' ``mz_cal`` to restore. 110 dataframe : pandas.DataFrame 111 The processed mass list data, with column names already 112 translated via ``header_translate`` (same dataframe passed to 113 ``add_molecular_formula``). 114 """ 115 if "Calibrated m/z" not in dataframe.columns: 116 return 117 118 mz_exp_col = dataframe[Labels.mz].astype(float) 119 mz_cal_col = dataframe["Calibrated m/z"] 120 121 # A missing "Calibrated m/z" cell is NaN (pandas' representation of 122 # missing data), not None -- and NaN is truthy in Python, so letting 123 # it through would set mz_cal to NaN, and MSPeak.mz_exp 124 # (`self.mz_cal if self.mz_cal else self._mz_exp`) would then return 125 # NaN instead of correctly falling back to the uncalibrated value. 126 # pd.isna() catches it; `is None` would not. 127 present = ~pd.isna(mz_cal_col) 128 mz_cal_col = mz_cal_col.astype(float) 129 differs = present & (mz_cal_col != mz_exp_col) 130 if not differs.any(): 131 return 132 133 # Built once -- O(n_peaks) -- and only applied to the rows that 134 # actually differ, instead of a per-row list.index() lookup inside 135 # the loop (quadratic in peak count for a large peak list). Matches 136 # peaks by m/z value rather than row position, same approach 137 # add_molecular_formula uses -- safe against any reordering between 138 # the dataframe and mass_spec_obj.mspeaks. Exact-match only, same as 139 # before. 140 mz_to_index = {mz: i for i, mz in enumerate(mass_spec_obj.mz_exp)} 141 142 for mz_exp, mz_cal in zip(mz_exp_col[differs], mz_cal_col[differs]): 143 ms_peak_index = mz_to_index.get(mz_exp) 144 if ms_peak_index is None: 145 continue 146 mass_spec_obj[ms_peak_index].mz_cal = mz_cal 147 148 def add_molecular_formula(self, mass_spec_obj, dataframe): 149 """ 150 Add molecular formula information to the mass spectrum object. 151 152 Parameters 153 ---------- 154 mass_spec_obj : MassSpecCentroid 155 The mass spectrum object to add the molecular formula to. 156 dataframe : pandas.DataFrame 157 The processed mass list data. 158 159 """ 160 161 # check if is coreMS file 162 if "Is Isotopologue" in dataframe: 163 # Reindex dataframe to row index to avoid issues with duplicated indexes (e.g. when multiple formula map to single mz_exp) 164 dataframe = dataframe.reset_index(drop=True) 165 166 mz_exp_df = dataframe[Labels.mz].astype(float) 167 formula_df = dataframe[ 168 dataframe.columns.intersection(Atoms.atoms_order) 169 ].copy() 170 # Convert to numeric first (pandas 3.x may infer str dtype for 171 # HDF5-sourced atom count columns); coerce handles b"nan" bytes too 172 formula_df = formula_df.apply(pd.to_numeric, errors="coerce").fillna(0) 173 174 ion_type_df = dataframe["Ion Type"] 175 # Formula assignment charge from export (not peak polarity) 176 ion_charge_df = dataframe["Ion Charge"] 177 is_isotopologue_df = dataframe["Is Isotopologue"] 178 if "Adduct" in dataframe: 179 adduct_df = dataframe["Adduct"] 180 else: 181 adduct_df = None 182 183 mass_spec_mz_exp_list = mass_spec_obj.mz_exp 184 185 for df_index, mz_exp in enumerate(mz_exp_df): 186 bad_mf = False 187 counts = 0 188 189 ms_peak_index = list(mass_spec_mz_exp_list).index(float(mz_exp)) 190 191 if "Is Isotopologue" in dataframe: 192 atoms = list(formula_df.columns.astype(str)) 193 counts = list(formula_df.iloc[df_index].astype(int)) 194 195 formula_dict = dict(zip(atoms, counts)) 196 197 # Drop any atoms with 0 counts 198 formula_dict = { 199 atom: formula_dict[atom] 200 for atom in formula_dict 201 if formula_dict[atom] > 0 202 } 203 204 if sum(counts) > 0: 205 # Prefer iloc for positional access (pandas 3 Series[] is label-based) 206 ion_type = str( 207 Labels.ion_type_translate.get(ion_type_df.iloc[df_index]) 208 ) 209 if adduct_df is not None: 210 adduct_atom = str(adduct_df.iloc[df_index]) 211 if adduct_atom == "None": 212 adduct_atom = None 213 else: 214 adduct_atom = None 215 216 # If not isotopologue, cast as MolecularFormula 217 if not bool(int(is_isotopologue_df.iloc[df_index])): 218 mfobj = MolecularFormula( 219 formula_dict, 220 int(ion_charge_df.iloc[df_index]), 221 mspeak_parent=mass_spec_obj[ms_peak_index], 222 ion_type=ion_type, 223 adduct_atom=adduct_atom, 224 ) 225 226 # if is isotopologue, recast as MolecularFormulaIsotopologue 227 if bool(int(is_isotopologue_df.iloc[df_index])): 228 # First make a MolecularFormula object for the parent so we can get probabilities etc 229 formula_list_parent = {} 230 for atom in formula_dict: 231 if atom in Atoms.isotopes.keys(): 232 formula_list_parent[atom] = formula_dict[atom] 233 else: 234 # remove any numbers from the atom name to cast as a mono-isotopic atom 235 atom_mono = atom.strip("0123456789") 236 if ( 237 atom_mono in Atoms.isotopes.keys() 238 and atom_mono in formula_list_parent.keys() 239 ): 240 formula_list_parent[atom_mono] = ( 241 formula_list_parent[atom_mono] + formula_dict[atom] 242 ) 243 elif atom_mono in Atoms.isotopes.keys(): 244 formula_list_parent[atom_mono] = formula_dict[atom] 245 else: 246 warnings.warn(f"Atom {atom} not in Atoms.atoms_order") 247 mono_index = int(dataframe.iloc[df_index]["Mono Isotopic Index"]) 248 mono_mfobj = MolecularFormula( 249 formula_list_parent, 250 int(ion_charge_df.iloc[df_index]), 251 mspeak_parent=mass_spec_obj[mono_index], 252 ion_type=ion_type, 253 adduct_atom=adduct_atom, 254 ) 255 256 # Next, generate isotopologues from the parent 257 isos = list( 258 mono_mfobj.isotopologues( 259 min_abundance=mass_spec_obj.abundance.min() * 0.01, 260 current_mono_abundance=mass_spec_obj[mono_index].abundance, 261 dynamic_range=mass_spec_obj.dynamic_range, 262 ) 263 ) 264 265 # Finally, find the isotopologue that matches the formula_dict 266 matched_isos = [] 267 for iso in isos: 268 # If match was already found, exit the loop 269 if len(matched_isos) > 0: 270 break 271 else: 272 # Check the atoms match 273 if set(iso.atoms) == set(formula_dict.keys()): 274 # Check the values of the atoms match 275 if all( 276 [ 277 iso[atom] == formula_dict[atom] 278 for atom in formula_dict 279 ] 280 ): 281 matched_isos.append(iso) 282 283 if len(matched_isos) == 0: 284 # FIXME: This should not occur see https://code.emsl.pnl.gov/mass-spectrometry/corems/-/issues/190 285 warnings.warn( 286 f"No isotopologue matched the formula_dict: {formula_dict}" 287 ) 288 bad_mf = True 289 else: 290 bad_mf = False 291 mfobj = matched_isos[0] 292 293 # Add the mono isotopic index, confidence score and isotopologue similarity 294 mfobj.mspeak_index_mono_isotopic = int( 295 dataframe.iloc[df_index]["Mono Isotopic Index"] 296 ) 297 if not bad_mf: 298 # Add the confidence score and isotopologue similarity and average MZ error score 299 if "m/z Error Score" in dataframe: 300 mfobj._mass_error_average_score = float( 301 dataframe.iloc[df_index]["m/z Error Score"] 302 ) 303 if "Confidence Score" in dataframe: 304 mfobj._confidence_score = float( 305 dataframe.iloc[df_index]["Confidence Score"] 306 ) 307 if "Isotopologue Similarity" in dataframe: 308 mfobj._isotopologue_similarity = float( 309 dataframe.iloc[df_index]["Isotopologue Similarity"] 310 ) 311 mass_spec_obj[ms_peak_index].add_molecular_formula(mfobj) 312 313 314class ReadMassList(MassListBaseClass): 315 """ 316 The ReadMassList object reads unprocessed mass list data types 317 and returns the mass spectrum object. 318 319 Parameters 320 ---------- 321 MassListBaseClass : class 322 The base class for reading mass list data types. 323 324 Methods 325 ------- 326 * get_mass_spectrum(polarity, scan=0, auto_process=True, loadSettings=True). Reads mass list data types and returns the mass spectrum object. 327 328 """ 329 330 def get_mass_spectrum( 331 self, 332 polarity: int, 333 scan: int = 0, 334 auto_process: bool = True, 335 loadSettings: bool = True, 336 ): 337 """ 338 Reads mass list data types and returns the mass spectrum object. 339 340 Parameters 341 ---------- 342 polarity : int 343 The polarity of the mass spectrum (+1 or -1). 344 scan : int, optional 345 The scan number of the mass spectrum (default is 0). 346 auto_process : bool, optional 347 Flag indicating whether to automatically process the mass spectrum (default is True). 348 loadSettings : bool, optional 349 Flag indicating whether to load settings for the mass spectrum (default is True). 350 351 Returns 352 ------- 353 mass_spec : MassSpecCentroid or MassSpecProfile 354 The mass spectrum object. 355 356 """ 357 358 # delimiter = " " or " " or "," or "\t" etc 359 360 if self.isCentroid: 361 dataframe = self.get_dataframe() 362 363 self.check_columns(dataframe.columns) 364 365 self.clean_data_frame(dataframe) 366 367 dataframe.rename(columns=self.parameters.header_translate, inplace=True) 368 369 output_parameters = self.get_output_parameters(polarity) 370 371 mass_spec = MassSpecCentroid( 372 dataframe.to_dict(orient="list"), 373 output_parameters, 374 auto_process=auto_process, 375 ) 376 377 if loadSettings: 378 self.load_settings(mass_spec, output_parameters) 379 380 return mass_spec 381 382 else: 383 dataframe = self.get_dataframe() 384 385 self.check_columns(dataframe.columns) 386 387 output_parameters = self.get_output_parameters(polarity) 388 389 self.clean_data_frame(dataframe) 390 391 dataframe.rename(columns=self.parameters.header_translate, inplace=True) 392 393 mass_spec = MassSpecProfile( 394 dataframe.to_dict(orient="list"), 395 output_parameters, 396 auto_process=auto_process, 397 ) 398 399 if loadSettings: 400 self.load_settings(mass_spec, output_parameters) 401 402 return mass_spec 403 404 405class ReadBrukerXMLList(MassListBaseClass): 406 """ 407 The ReadBrukerXMLList object reads Bruker XML objects 408 and returns the mass spectrum object. 409 See MassListBaseClass for details 410 411 Parameters 412 ---------- 413 MassListBaseClass : class 414 The base class for reading mass list data types and returning the mass spectrum object. 415 416 Methods 417 ------- 418 * get_mass_spectrum(polarity: bool = None, scan: int = 0, auto_process: bool = True, loadSettings: bool = True). Reads mass list data types and returns the mass spectrum object. 419 420 """ 421 422 def get_mass_spectrum( 423 self, 424 polarity: bool = None, 425 scan: int = 0, 426 auto_process: bool = True, 427 loadSettings: bool = True, 428 ): 429 """ 430 Reads mass list data types and returns the mass spectrum object. 431 432 Parameters 433 ---------- 434 polarity : bool, optional 435 The polarity of the mass spectrum. Can be +1 or -1. If not provided, it will be determined from the XML file. 436 scan : int, optional 437 The scan number of the mass spectrum. Default is 0. 438 auto_process : bool, optional 439 Whether to automatically process the mass spectrum. Default is True. 440 loadSettings : bool, optional 441 Whether to load the settings for the mass spectrum. Default is True. 442 443 Returns 444 ------- 445 mass_spec : MassSpecCentroid 446 The mass spectrum object representing the centroided mass spectrum. 447 """ 448 # delimiter = " " or " " or "," or "\t" etc 449 450 if polarity == None: 451 polarity = self.get_xml_polarity() 452 dataframe = self.get_dataframe() 453 454 self.check_columns(dataframe.columns) 455 456 self.clean_data_frame(dataframe) 457 458 dataframe.rename(columns=self.parameters.header_translate, inplace=True) 459 460 output_parameters = self.get_output_parameters(polarity) 461 462 mass_spec = MassSpecCentroid( 463 dataframe.to_dict(orient="list"), 464 output_parameters, 465 auto_process=auto_process, 466 ) 467 468 if loadSettings: 469 self.load_settings(mass_spec, output_parameters) 470 471 return mass_spec
18class ReadCoremsMasslist(MassListBaseClass): 19 """ 20 The ReadCoremsMasslist object reads processed mass list data types 21 and returns the mass spectrum obj with the molecular formula obj 22 23 **Only available for centroid mass spectrum type:** it will ignore the parameter **isCentroid** 24 Please see MassListBaseClass for more details 25 26 """ 27 28 def get_mass_spectrum( 29 self, loadSettings: bool = True, auto_process: bool = True 30 ) -> MassSpecCentroid: 31 """ 32 Get the mass spectrum object from the processed mass list data. 33 34 Parameters 35 ---------- 36 loadSettings : bool, optional 37 Whether to load the settings for the mass spectrum. Default is True. 38 auto_process : bool, optional 39 Whether to automatically process the mass spectrum on instantiation. 40 When False, molecular formulas are not attached; call 41 ``process_mass_spec`` and then ``add_molecular_formula`` on the 42 returned object. Default is True. 43 44 Returns 45 ------- 46 MassSpecCentroid 47 The mass spectrum object. 48 49 Raises 50 ------ 51 ValueError 52 If the input file is not a valid CoreMS file. 53 """ 54 55 dataframe = self.get_dataframe() 56 57 if not set( 58 ["H/C", "O/C", "Heteroatom Class", "Ion Type", "Is Isotopologue"] 59 ).issubset(dataframe.columns): 60 raise ValueError( 61 "%s it is not a valid CoreMS file" % str(self.file_location) 62 ) 63 64 self.check_columns(dataframe.columns) 65 66 dataframe.rename(columns=self.parameters.header_translate, inplace=True) 67 68 # "Ion Charge" is dual-purpose in CoreMS tables: spectrum/peak polarity 69 # for unassigned rows (±1), formula assignment charge when assigned 70 # (may be |z|>1). Spectrum polarity is only the sign. 71 # Use iloc for pandas 3 / CoW-safe indexing. 72 raw_charge = int(dataframe["Ion Charge"].iloc[0]) 73 if raw_charge == 0: 74 raise ValueError("Ion Charge column must be non-zero to derive polarity") 75 polarity = 1 if raw_charge > 0 else -1 76 77 output_parameters = self.get_output_parameters(polarity) 78 79 mass_spec_obj = MassSpecCentroid( 80 dataframe.to_dict(orient="list"), 81 output_parameters, 82 auto_process=auto_process, 83 ) 84 85 if loadSettings is True: 86 self.load_settings(mass_spec_obj, output_parameters) 87 88 if auto_process: 89 # Formulas first. add_molecular_formula matches the uncalibrated 90 # "m/z" column against mz_exp, which returns mz_cal once restored. 91 self.add_molecular_formula(mass_spec_obj, dataframe) 92 self.restore_peak_calibration(mass_spec_obj, dataframe) 93 94 return mass_spec_obj 95 96 def restore_peak_calibration(self, mass_spec_obj, dataframe): 97 """Restore each peak's ``mz_cal`` from the stored "Calibrated m/z" column. 98 99 The peak table always stores both the uncalibrated "m/z" and the 100 (possibly calibrated) "Calibrated m/z", but ``MassSpecCentroid`` is 101 built only from "m/z" -- so without this, a reloaded peak loses its 102 own calibration even when the spectrum it came from had been 103 calibrated. Only peaks whose "Calibrated m/z" actually differs from 104 "m/z" are touched; an unmatched or never-calibrated peak's ``mz_cal`` 105 is left as ``None``, same as before this method existed. 106 107 Parameters 108 ---------- 109 mass_spec_obj : MassSpecCentroid 110 The mass spectrum object whose peaks' ``mz_cal`` to restore. 111 dataframe : pandas.DataFrame 112 The processed mass list data, with column names already 113 translated via ``header_translate`` (same dataframe passed to 114 ``add_molecular_formula``). 115 """ 116 if "Calibrated m/z" not in dataframe.columns: 117 return 118 119 mz_exp_col = dataframe[Labels.mz].astype(float) 120 mz_cal_col = dataframe["Calibrated m/z"] 121 122 # A missing "Calibrated m/z" cell is NaN (pandas' representation of 123 # missing data), not None -- and NaN is truthy in Python, so letting 124 # it through would set mz_cal to NaN, and MSPeak.mz_exp 125 # (`self.mz_cal if self.mz_cal else self._mz_exp`) would then return 126 # NaN instead of correctly falling back to the uncalibrated value. 127 # pd.isna() catches it; `is None` would not. 128 present = ~pd.isna(mz_cal_col) 129 mz_cal_col = mz_cal_col.astype(float) 130 differs = present & (mz_cal_col != mz_exp_col) 131 if not differs.any(): 132 return 133 134 # Built once -- O(n_peaks) -- and only applied to the rows that 135 # actually differ, instead of a per-row list.index() lookup inside 136 # the loop (quadratic in peak count for a large peak list). Matches 137 # peaks by m/z value rather than row position, same approach 138 # add_molecular_formula uses -- safe against any reordering between 139 # the dataframe and mass_spec_obj.mspeaks. Exact-match only, same as 140 # before. 141 mz_to_index = {mz: i for i, mz in enumerate(mass_spec_obj.mz_exp)} 142 143 for mz_exp, mz_cal in zip(mz_exp_col[differs], mz_cal_col[differs]): 144 ms_peak_index = mz_to_index.get(mz_exp) 145 if ms_peak_index is None: 146 continue 147 mass_spec_obj[ms_peak_index].mz_cal = mz_cal 148 149 def add_molecular_formula(self, mass_spec_obj, dataframe): 150 """ 151 Add molecular formula information to the mass spectrum object. 152 153 Parameters 154 ---------- 155 mass_spec_obj : MassSpecCentroid 156 The mass spectrum object to add the molecular formula to. 157 dataframe : pandas.DataFrame 158 The processed mass list data. 159 160 """ 161 162 # check if is coreMS file 163 if "Is Isotopologue" in dataframe: 164 # Reindex dataframe to row index to avoid issues with duplicated indexes (e.g. when multiple formula map to single mz_exp) 165 dataframe = dataframe.reset_index(drop=True) 166 167 mz_exp_df = dataframe[Labels.mz].astype(float) 168 formula_df = dataframe[ 169 dataframe.columns.intersection(Atoms.atoms_order) 170 ].copy() 171 # Convert to numeric first (pandas 3.x may infer str dtype for 172 # HDF5-sourced atom count columns); coerce handles b"nan" bytes too 173 formula_df = formula_df.apply(pd.to_numeric, errors="coerce").fillna(0) 174 175 ion_type_df = dataframe["Ion Type"] 176 # Formula assignment charge from export (not peak polarity) 177 ion_charge_df = dataframe["Ion Charge"] 178 is_isotopologue_df = dataframe["Is Isotopologue"] 179 if "Adduct" in dataframe: 180 adduct_df = dataframe["Adduct"] 181 else: 182 adduct_df = None 183 184 mass_spec_mz_exp_list = mass_spec_obj.mz_exp 185 186 for df_index, mz_exp in enumerate(mz_exp_df): 187 bad_mf = False 188 counts = 0 189 190 ms_peak_index = list(mass_spec_mz_exp_list).index(float(mz_exp)) 191 192 if "Is Isotopologue" in dataframe: 193 atoms = list(formula_df.columns.astype(str)) 194 counts = list(formula_df.iloc[df_index].astype(int)) 195 196 formula_dict = dict(zip(atoms, counts)) 197 198 # Drop any atoms with 0 counts 199 formula_dict = { 200 atom: formula_dict[atom] 201 for atom in formula_dict 202 if formula_dict[atom] > 0 203 } 204 205 if sum(counts) > 0: 206 # Prefer iloc for positional access (pandas 3 Series[] is label-based) 207 ion_type = str( 208 Labels.ion_type_translate.get(ion_type_df.iloc[df_index]) 209 ) 210 if adduct_df is not None: 211 adduct_atom = str(adduct_df.iloc[df_index]) 212 if adduct_atom == "None": 213 adduct_atom = None 214 else: 215 adduct_atom = None 216 217 # If not isotopologue, cast as MolecularFormula 218 if not bool(int(is_isotopologue_df.iloc[df_index])): 219 mfobj = MolecularFormula( 220 formula_dict, 221 int(ion_charge_df.iloc[df_index]), 222 mspeak_parent=mass_spec_obj[ms_peak_index], 223 ion_type=ion_type, 224 adduct_atom=adduct_atom, 225 ) 226 227 # if is isotopologue, recast as MolecularFormulaIsotopologue 228 if bool(int(is_isotopologue_df.iloc[df_index])): 229 # First make a MolecularFormula object for the parent so we can get probabilities etc 230 formula_list_parent = {} 231 for atom in formula_dict: 232 if atom in Atoms.isotopes.keys(): 233 formula_list_parent[atom] = formula_dict[atom] 234 else: 235 # remove any numbers from the atom name to cast as a mono-isotopic atom 236 atom_mono = atom.strip("0123456789") 237 if ( 238 atom_mono in Atoms.isotopes.keys() 239 and atom_mono in formula_list_parent.keys() 240 ): 241 formula_list_parent[atom_mono] = ( 242 formula_list_parent[atom_mono] + formula_dict[atom] 243 ) 244 elif atom_mono in Atoms.isotopes.keys(): 245 formula_list_parent[atom_mono] = formula_dict[atom] 246 else: 247 warnings.warn(f"Atom {atom} not in Atoms.atoms_order") 248 mono_index = int(dataframe.iloc[df_index]["Mono Isotopic Index"]) 249 mono_mfobj = MolecularFormula( 250 formula_list_parent, 251 int(ion_charge_df.iloc[df_index]), 252 mspeak_parent=mass_spec_obj[mono_index], 253 ion_type=ion_type, 254 adduct_atom=adduct_atom, 255 ) 256 257 # Next, generate isotopologues from the parent 258 isos = list( 259 mono_mfobj.isotopologues( 260 min_abundance=mass_spec_obj.abundance.min() * 0.01, 261 current_mono_abundance=mass_spec_obj[mono_index].abundance, 262 dynamic_range=mass_spec_obj.dynamic_range, 263 ) 264 ) 265 266 # Finally, find the isotopologue that matches the formula_dict 267 matched_isos = [] 268 for iso in isos: 269 # If match was already found, exit the loop 270 if len(matched_isos) > 0: 271 break 272 else: 273 # Check the atoms match 274 if set(iso.atoms) == set(formula_dict.keys()): 275 # Check the values of the atoms match 276 if all( 277 [ 278 iso[atom] == formula_dict[atom] 279 for atom in formula_dict 280 ] 281 ): 282 matched_isos.append(iso) 283 284 if len(matched_isos) == 0: 285 # FIXME: This should not occur see https://code.emsl.pnl.gov/mass-spectrometry/corems/-/issues/190 286 warnings.warn( 287 f"No isotopologue matched the formula_dict: {formula_dict}" 288 ) 289 bad_mf = True 290 else: 291 bad_mf = False 292 mfobj = matched_isos[0] 293 294 # Add the mono isotopic index, confidence score and isotopologue similarity 295 mfobj.mspeak_index_mono_isotopic = int( 296 dataframe.iloc[df_index]["Mono Isotopic Index"] 297 ) 298 if not bad_mf: 299 # Add the confidence score and isotopologue similarity and average MZ error score 300 if "m/z Error Score" in dataframe: 301 mfobj._mass_error_average_score = float( 302 dataframe.iloc[df_index]["m/z Error Score"] 303 ) 304 if "Confidence Score" in dataframe: 305 mfobj._confidence_score = float( 306 dataframe.iloc[df_index]["Confidence Score"] 307 ) 308 if "Isotopologue Similarity" in dataframe: 309 mfobj._isotopologue_similarity = float( 310 dataframe.iloc[df_index]["Isotopologue Similarity"] 311 ) 312 mass_spec_obj[ms_peak_index].add_molecular_formula(mfobj)
The ReadCoremsMasslist object reads processed mass list data types and returns the mass spectrum obj with the molecular formula obj
Only available for centroid mass spectrum type: it will ignore the parameter isCentroid Please see MassListBaseClass for more details
def
get_mass_spectrum( self, loadSettings: bool = True, auto_process: bool = True) -> corems.mass_spectrum.factory.MassSpectrumClasses.MassSpecCentroid:
28 def get_mass_spectrum( 29 self, loadSettings: bool = True, auto_process: bool = True 30 ) -> MassSpecCentroid: 31 """ 32 Get the mass spectrum object from the processed mass list data. 33 34 Parameters 35 ---------- 36 loadSettings : bool, optional 37 Whether to load the settings for the mass spectrum. Default is True. 38 auto_process : bool, optional 39 Whether to automatically process the mass spectrum on instantiation. 40 When False, molecular formulas are not attached; call 41 ``process_mass_spec`` and then ``add_molecular_formula`` on the 42 returned object. Default is True. 43 44 Returns 45 ------- 46 MassSpecCentroid 47 The mass spectrum object. 48 49 Raises 50 ------ 51 ValueError 52 If the input file is not a valid CoreMS file. 53 """ 54 55 dataframe = self.get_dataframe() 56 57 if not set( 58 ["H/C", "O/C", "Heteroatom Class", "Ion Type", "Is Isotopologue"] 59 ).issubset(dataframe.columns): 60 raise ValueError( 61 "%s it is not a valid CoreMS file" % str(self.file_location) 62 ) 63 64 self.check_columns(dataframe.columns) 65 66 dataframe.rename(columns=self.parameters.header_translate, inplace=True) 67 68 # "Ion Charge" is dual-purpose in CoreMS tables: spectrum/peak polarity 69 # for unassigned rows (±1), formula assignment charge when assigned 70 # (may be |z|>1). Spectrum polarity is only the sign. 71 # Use iloc for pandas 3 / CoW-safe indexing. 72 raw_charge = int(dataframe["Ion Charge"].iloc[0]) 73 if raw_charge == 0: 74 raise ValueError("Ion Charge column must be non-zero to derive polarity") 75 polarity = 1 if raw_charge > 0 else -1 76 77 output_parameters = self.get_output_parameters(polarity) 78 79 mass_spec_obj = MassSpecCentroid( 80 dataframe.to_dict(orient="list"), 81 output_parameters, 82 auto_process=auto_process, 83 ) 84 85 if loadSettings is True: 86 self.load_settings(mass_spec_obj, output_parameters) 87 88 if auto_process: 89 # Formulas first. add_molecular_formula matches the uncalibrated 90 # "m/z" column against mz_exp, which returns mz_cal once restored. 91 self.add_molecular_formula(mass_spec_obj, dataframe) 92 self.restore_peak_calibration(mass_spec_obj, dataframe) 93 94 return mass_spec_obj
Get the mass spectrum object from the processed mass list data.
Parameters
- loadSettings (bool, optional): Whether to load the settings for the mass spectrum. Default is True.
- auto_process (bool, optional):
Whether to automatically process the mass spectrum on instantiation.
When False, molecular formulas are not attached; call
process_mass_specand thenadd_molecular_formulaon the returned object. Default is True.
Returns
- MassSpecCentroid: The mass spectrum object.
Raises
- ValueError: If the input file is not a valid CoreMS file.
def
restore_peak_calibration(self, mass_spec_obj, dataframe):
96 def restore_peak_calibration(self, mass_spec_obj, dataframe): 97 """Restore each peak's ``mz_cal`` from the stored "Calibrated m/z" column. 98 99 The peak table always stores both the uncalibrated "m/z" and the 100 (possibly calibrated) "Calibrated m/z", but ``MassSpecCentroid`` is 101 built only from "m/z" -- so without this, a reloaded peak loses its 102 own calibration even when the spectrum it came from had been 103 calibrated. Only peaks whose "Calibrated m/z" actually differs from 104 "m/z" are touched; an unmatched or never-calibrated peak's ``mz_cal`` 105 is left as ``None``, same as before this method existed. 106 107 Parameters 108 ---------- 109 mass_spec_obj : MassSpecCentroid 110 The mass spectrum object whose peaks' ``mz_cal`` to restore. 111 dataframe : pandas.DataFrame 112 The processed mass list data, with column names already 113 translated via ``header_translate`` (same dataframe passed to 114 ``add_molecular_formula``). 115 """ 116 if "Calibrated m/z" not in dataframe.columns: 117 return 118 119 mz_exp_col = dataframe[Labels.mz].astype(float) 120 mz_cal_col = dataframe["Calibrated m/z"] 121 122 # A missing "Calibrated m/z" cell is NaN (pandas' representation of 123 # missing data), not None -- and NaN is truthy in Python, so letting 124 # it through would set mz_cal to NaN, and MSPeak.mz_exp 125 # (`self.mz_cal if self.mz_cal else self._mz_exp`) would then return 126 # NaN instead of correctly falling back to the uncalibrated value. 127 # pd.isna() catches it; `is None` would not. 128 present = ~pd.isna(mz_cal_col) 129 mz_cal_col = mz_cal_col.astype(float) 130 differs = present & (mz_cal_col != mz_exp_col) 131 if not differs.any(): 132 return 133 134 # Built once -- O(n_peaks) -- and only applied to the rows that 135 # actually differ, instead of a per-row list.index() lookup inside 136 # the loop (quadratic in peak count for a large peak list). Matches 137 # peaks by m/z value rather than row position, same approach 138 # add_molecular_formula uses -- safe against any reordering between 139 # the dataframe and mass_spec_obj.mspeaks. Exact-match only, same as 140 # before. 141 mz_to_index = {mz: i for i, mz in enumerate(mass_spec_obj.mz_exp)} 142 143 for mz_exp, mz_cal in zip(mz_exp_col[differs], mz_cal_col[differs]): 144 ms_peak_index = mz_to_index.get(mz_exp) 145 if ms_peak_index is None: 146 continue 147 mass_spec_obj[ms_peak_index].mz_cal = mz_cal
Restore each peak's mz_cal from the stored "Calibrated m/z" column.
The peak table always stores both the uncalibrated "m/z" and the
(possibly calibrated) "Calibrated m/z", but MassSpecCentroid is
built only from "m/z" -- so without this, a reloaded peak loses its
own calibration even when the spectrum it came from had been
calibrated. Only peaks whose "Calibrated m/z" actually differs from
"m/z" are touched; an unmatched or never-calibrated peak's mz_cal
is left as None, same as before this method existed.
Parameters
- mass_spec_obj (MassSpecCentroid):
The mass spectrum object whose peaks'
mz_calto restore. - dataframe (pandas.DataFrame):
The processed mass list data, with column names already
translated via
header_translate(same dataframe passed toadd_molecular_formula).
def
add_molecular_formula(self, mass_spec_obj, dataframe):
149 def add_molecular_formula(self, mass_spec_obj, dataframe): 150 """ 151 Add molecular formula information to the mass spectrum object. 152 153 Parameters 154 ---------- 155 mass_spec_obj : MassSpecCentroid 156 The mass spectrum object to add the molecular formula to. 157 dataframe : pandas.DataFrame 158 The processed mass list data. 159 160 """ 161 162 # check if is coreMS file 163 if "Is Isotopologue" in dataframe: 164 # Reindex dataframe to row index to avoid issues with duplicated indexes (e.g. when multiple formula map to single mz_exp) 165 dataframe = dataframe.reset_index(drop=True) 166 167 mz_exp_df = dataframe[Labels.mz].astype(float) 168 formula_df = dataframe[ 169 dataframe.columns.intersection(Atoms.atoms_order) 170 ].copy() 171 # Convert to numeric first (pandas 3.x may infer str dtype for 172 # HDF5-sourced atom count columns); coerce handles b"nan" bytes too 173 formula_df = formula_df.apply(pd.to_numeric, errors="coerce").fillna(0) 174 175 ion_type_df = dataframe["Ion Type"] 176 # Formula assignment charge from export (not peak polarity) 177 ion_charge_df = dataframe["Ion Charge"] 178 is_isotopologue_df = dataframe["Is Isotopologue"] 179 if "Adduct" in dataframe: 180 adduct_df = dataframe["Adduct"] 181 else: 182 adduct_df = None 183 184 mass_spec_mz_exp_list = mass_spec_obj.mz_exp 185 186 for df_index, mz_exp in enumerate(mz_exp_df): 187 bad_mf = False 188 counts = 0 189 190 ms_peak_index = list(mass_spec_mz_exp_list).index(float(mz_exp)) 191 192 if "Is Isotopologue" in dataframe: 193 atoms = list(formula_df.columns.astype(str)) 194 counts = list(formula_df.iloc[df_index].astype(int)) 195 196 formula_dict = dict(zip(atoms, counts)) 197 198 # Drop any atoms with 0 counts 199 formula_dict = { 200 atom: formula_dict[atom] 201 for atom in formula_dict 202 if formula_dict[atom] > 0 203 } 204 205 if sum(counts) > 0: 206 # Prefer iloc for positional access (pandas 3 Series[] is label-based) 207 ion_type = str( 208 Labels.ion_type_translate.get(ion_type_df.iloc[df_index]) 209 ) 210 if adduct_df is not None: 211 adduct_atom = str(adduct_df.iloc[df_index]) 212 if adduct_atom == "None": 213 adduct_atom = None 214 else: 215 adduct_atom = None 216 217 # If not isotopologue, cast as MolecularFormula 218 if not bool(int(is_isotopologue_df.iloc[df_index])): 219 mfobj = MolecularFormula( 220 formula_dict, 221 int(ion_charge_df.iloc[df_index]), 222 mspeak_parent=mass_spec_obj[ms_peak_index], 223 ion_type=ion_type, 224 adduct_atom=adduct_atom, 225 ) 226 227 # if is isotopologue, recast as MolecularFormulaIsotopologue 228 if bool(int(is_isotopologue_df.iloc[df_index])): 229 # First make a MolecularFormula object for the parent so we can get probabilities etc 230 formula_list_parent = {} 231 for atom in formula_dict: 232 if atom in Atoms.isotopes.keys(): 233 formula_list_parent[atom] = formula_dict[atom] 234 else: 235 # remove any numbers from the atom name to cast as a mono-isotopic atom 236 atom_mono = atom.strip("0123456789") 237 if ( 238 atom_mono in Atoms.isotopes.keys() 239 and atom_mono in formula_list_parent.keys() 240 ): 241 formula_list_parent[atom_mono] = ( 242 formula_list_parent[atom_mono] + formula_dict[atom] 243 ) 244 elif atom_mono in Atoms.isotopes.keys(): 245 formula_list_parent[atom_mono] = formula_dict[atom] 246 else: 247 warnings.warn(f"Atom {atom} not in Atoms.atoms_order") 248 mono_index = int(dataframe.iloc[df_index]["Mono Isotopic Index"]) 249 mono_mfobj = MolecularFormula( 250 formula_list_parent, 251 int(ion_charge_df.iloc[df_index]), 252 mspeak_parent=mass_spec_obj[mono_index], 253 ion_type=ion_type, 254 adduct_atom=adduct_atom, 255 ) 256 257 # Next, generate isotopologues from the parent 258 isos = list( 259 mono_mfobj.isotopologues( 260 min_abundance=mass_spec_obj.abundance.min() * 0.01, 261 current_mono_abundance=mass_spec_obj[mono_index].abundance, 262 dynamic_range=mass_spec_obj.dynamic_range, 263 ) 264 ) 265 266 # Finally, find the isotopologue that matches the formula_dict 267 matched_isos = [] 268 for iso in isos: 269 # If match was already found, exit the loop 270 if len(matched_isos) > 0: 271 break 272 else: 273 # Check the atoms match 274 if set(iso.atoms) == set(formula_dict.keys()): 275 # Check the values of the atoms match 276 if all( 277 [ 278 iso[atom] == formula_dict[atom] 279 for atom in formula_dict 280 ] 281 ): 282 matched_isos.append(iso) 283 284 if len(matched_isos) == 0: 285 # FIXME: This should not occur see https://code.emsl.pnl.gov/mass-spectrometry/corems/-/issues/190 286 warnings.warn( 287 f"No isotopologue matched the formula_dict: {formula_dict}" 288 ) 289 bad_mf = True 290 else: 291 bad_mf = False 292 mfobj = matched_isos[0] 293 294 # Add the mono isotopic index, confidence score and isotopologue similarity 295 mfobj.mspeak_index_mono_isotopic = int( 296 dataframe.iloc[df_index]["Mono Isotopic Index"] 297 ) 298 if not bad_mf: 299 # Add the confidence score and isotopologue similarity and average MZ error score 300 if "m/z Error Score" in dataframe: 301 mfobj._mass_error_average_score = float( 302 dataframe.iloc[df_index]["m/z Error Score"] 303 ) 304 if "Confidence Score" in dataframe: 305 mfobj._confidence_score = float( 306 dataframe.iloc[df_index]["Confidence Score"] 307 ) 308 if "Isotopologue Similarity" in dataframe: 309 mfobj._isotopologue_similarity = float( 310 dataframe.iloc[df_index]["Isotopologue Similarity"] 311 ) 312 mass_spec_obj[ms_peak_index].add_molecular_formula(mfobj)
Add molecular formula information to the mass spectrum object.
Parameters
- mass_spec_obj (MassSpecCentroid): The mass spectrum object to add the molecular formula to.
- dataframe (pandas.DataFrame): The processed mass list data.
Inherited Members
- corems.mass_spectrum.input.baseClass.MassListBaseClass
- MassListBaseClass
- file_location
- header_lines
- isCentroid
- isThermoProfile
- headerless
- analyzer
- instrument_label
- sample_name
- parameters
- set_parameter_from_toml
- set_parameter_from_json
- data_type
- delimiter
- encoding_detector
- set_data_type
- get_dataframe
- load_settings
- get_output_parameters
- clean_data_frame
- check_columns
- read_xml_peaks
- get_xml_polarity
315class ReadMassList(MassListBaseClass): 316 """ 317 The ReadMassList object reads unprocessed mass list data types 318 and returns the mass spectrum object. 319 320 Parameters 321 ---------- 322 MassListBaseClass : class 323 The base class for reading mass list data types. 324 325 Methods 326 ------- 327 * get_mass_spectrum(polarity, scan=0, auto_process=True, loadSettings=True). Reads mass list data types and returns the mass spectrum object. 328 329 """ 330 331 def get_mass_spectrum( 332 self, 333 polarity: int, 334 scan: int = 0, 335 auto_process: bool = True, 336 loadSettings: bool = True, 337 ): 338 """ 339 Reads mass list data types and returns the mass spectrum object. 340 341 Parameters 342 ---------- 343 polarity : int 344 The polarity of the mass spectrum (+1 or -1). 345 scan : int, optional 346 The scan number of the mass spectrum (default is 0). 347 auto_process : bool, optional 348 Flag indicating whether to automatically process the mass spectrum (default is True). 349 loadSettings : bool, optional 350 Flag indicating whether to load settings for the mass spectrum (default is True). 351 352 Returns 353 ------- 354 mass_spec : MassSpecCentroid or MassSpecProfile 355 The mass spectrum object. 356 357 """ 358 359 # delimiter = " " or " " or "," or "\t" etc 360 361 if self.isCentroid: 362 dataframe = self.get_dataframe() 363 364 self.check_columns(dataframe.columns) 365 366 self.clean_data_frame(dataframe) 367 368 dataframe.rename(columns=self.parameters.header_translate, inplace=True) 369 370 output_parameters = self.get_output_parameters(polarity) 371 372 mass_spec = MassSpecCentroid( 373 dataframe.to_dict(orient="list"), 374 output_parameters, 375 auto_process=auto_process, 376 ) 377 378 if loadSettings: 379 self.load_settings(mass_spec, output_parameters) 380 381 return mass_spec 382 383 else: 384 dataframe = self.get_dataframe() 385 386 self.check_columns(dataframe.columns) 387 388 output_parameters = self.get_output_parameters(polarity) 389 390 self.clean_data_frame(dataframe) 391 392 dataframe.rename(columns=self.parameters.header_translate, inplace=True) 393 394 mass_spec = MassSpecProfile( 395 dataframe.to_dict(orient="list"), 396 output_parameters, 397 auto_process=auto_process, 398 ) 399 400 if loadSettings: 401 self.load_settings(mass_spec, output_parameters) 402 403 return mass_spec
The ReadMassList object reads unprocessed mass list data types and returns the mass spectrum object.
Parameters
- MassListBaseClass (class): The base class for reading mass list data types.
Methods
- get_mass_spectrum(polarity, scan=0, auto_process=True, loadSettings=True). Reads mass list data types and returns the mass spectrum object.
def
get_mass_spectrum( self, polarity: int, scan: int = 0, auto_process: bool = True, loadSettings: bool = True):
331 def get_mass_spectrum( 332 self, 333 polarity: int, 334 scan: int = 0, 335 auto_process: bool = True, 336 loadSettings: bool = True, 337 ): 338 """ 339 Reads mass list data types and returns the mass spectrum object. 340 341 Parameters 342 ---------- 343 polarity : int 344 The polarity of the mass spectrum (+1 or -1). 345 scan : int, optional 346 The scan number of the mass spectrum (default is 0). 347 auto_process : bool, optional 348 Flag indicating whether to automatically process the mass spectrum (default is True). 349 loadSettings : bool, optional 350 Flag indicating whether to load settings for the mass spectrum (default is True). 351 352 Returns 353 ------- 354 mass_spec : MassSpecCentroid or MassSpecProfile 355 The mass spectrum object. 356 357 """ 358 359 # delimiter = " " or " " or "," or "\t" etc 360 361 if self.isCentroid: 362 dataframe = self.get_dataframe() 363 364 self.check_columns(dataframe.columns) 365 366 self.clean_data_frame(dataframe) 367 368 dataframe.rename(columns=self.parameters.header_translate, inplace=True) 369 370 output_parameters = self.get_output_parameters(polarity) 371 372 mass_spec = MassSpecCentroid( 373 dataframe.to_dict(orient="list"), 374 output_parameters, 375 auto_process=auto_process, 376 ) 377 378 if loadSettings: 379 self.load_settings(mass_spec, output_parameters) 380 381 return mass_spec 382 383 else: 384 dataframe = self.get_dataframe() 385 386 self.check_columns(dataframe.columns) 387 388 output_parameters = self.get_output_parameters(polarity) 389 390 self.clean_data_frame(dataframe) 391 392 dataframe.rename(columns=self.parameters.header_translate, inplace=True) 393 394 mass_spec = MassSpecProfile( 395 dataframe.to_dict(orient="list"), 396 output_parameters, 397 auto_process=auto_process, 398 ) 399 400 if loadSettings: 401 self.load_settings(mass_spec, output_parameters) 402 403 return mass_spec
Reads mass list data types and returns the mass spectrum object.
Parameters
- polarity (int): The polarity of the mass spectrum (+1 or -1).
- scan (int, optional): The scan number of the mass spectrum (default is 0).
- auto_process (bool, optional): Flag indicating whether to automatically process the mass spectrum (default is True).
- loadSettings (bool, optional): Flag indicating whether to load settings for the mass spectrum (default is True).
Returns
- mass_spec (MassSpecCentroid or MassSpecProfile): The mass spectrum object.
Inherited Members
- corems.mass_spectrum.input.baseClass.MassListBaseClass
- MassListBaseClass
- file_location
- header_lines
- isCentroid
- isThermoProfile
- headerless
- analyzer
- instrument_label
- sample_name
- parameters
- set_parameter_from_toml
- set_parameter_from_json
- data_type
- delimiter
- encoding_detector
- set_data_type
- get_dataframe
- load_settings
- get_output_parameters
- clean_data_frame
- check_columns
- read_xml_peaks
- get_xml_polarity
406class ReadBrukerXMLList(MassListBaseClass): 407 """ 408 The ReadBrukerXMLList object reads Bruker XML objects 409 and returns the mass spectrum object. 410 See MassListBaseClass for details 411 412 Parameters 413 ---------- 414 MassListBaseClass : class 415 The base class for reading mass list data types and returning the mass spectrum object. 416 417 Methods 418 ------- 419 * get_mass_spectrum(polarity: bool = None, scan: int = 0, auto_process: bool = True, loadSettings: bool = True). Reads mass list data types and returns the mass spectrum object. 420 421 """ 422 423 def get_mass_spectrum( 424 self, 425 polarity: bool = None, 426 scan: int = 0, 427 auto_process: bool = True, 428 loadSettings: bool = True, 429 ): 430 """ 431 Reads mass list data types and returns the mass spectrum object. 432 433 Parameters 434 ---------- 435 polarity : bool, optional 436 The polarity of the mass spectrum. Can be +1 or -1. If not provided, it will be determined from the XML file. 437 scan : int, optional 438 The scan number of the mass spectrum. Default is 0. 439 auto_process : bool, optional 440 Whether to automatically process the mass spectrum. Default is True. 441 loadSettings : bool, optional 442 Whether to load the settings for the mass spectrum. Default is True. 443 444 Returns 445 ------- 446 mass_spec : MassSpecCentroid 447 The mass spectrum object representing the centroided mass spectrum. 448 """ 449 # delimiter = " " or " " or "," or "\t" etc 450 451 if polarity == None: 452 polarity = self.get_xml_polarity() 453 dataframe = self.get_dataframe() 454 455 self.check_columns(dataframe.columns) 456 457 self.clean_data_frame(dataframe) 458 459 dataframe.rename(columns=self.parameters.header_translate, inplace=True) 460 461 output_parameters = self.get_output_parameters(polarity) 462 463 mass_spec = MassSpecCentroid( 464 dataframe.to_dict(orient="list"), 465 output_parameters, 466 auto_process=auto_process, 467 ) 468 469 if loadSettings: 470 self.load_settings(mass_spec, output_parameters) 471 472 return mass_spec
The ReadBrukerXMLList object reads Bruker XML objects and returns the mass spectrum object. See MassListBaseClass for details
Parameters
- MassListBaseClass (class): The base class for reading mass list data types and returning the mass spectrum object.
Methods
- get_mass_spectrum(polarity: bool = None, scan: int = 0, auto_process: bool = True, loadSettings: bool = True). Reads mass list data types and returns the mass spectrum object.
def
get_mass_spectrum( self, polarity: bool = None, scan: int = 0, auto_process: bool = True, loadSettings: bool = True):
423 def get_mass_spectrum( 424 self, 425 polarity: bool = None, 426 scan: int = 0, 427 auto_process: bool = True, 428 loadSettings: bool = True, 429 ): 430 """ 431 Reads mass list data types and returns the mass spectrum object. 432 433 Parameters 434 ---------- 435 polarity : bool, optional 436 The polarity of the mass spectrum. Can be +1 or -1. If not provided, it will be determined from the XML file. 437 scan : int, optional 438 The scan number of the mass spectrum. Default is 0. 439 auto_process : bool, optional 440 Whether to automatically process the mass spectrum. Default is True. 441 loadSettings : bool, optional 442 Whether to load the settings for the mass spectrum. Default is True. 443 444 Returns 445 ------- 446 mass_spec : MassSpecCentroid 447 The mass spectrum object representing the centroided mass spectrum. 448 """ 449 # delimiter = " " or " " or "," or "\t" etc 450 451 if polarity == None: 452 polarity = self.get_xml_polarity() 453 dataframe = self.get_dataframe() 454 455 self.check_columns(dataframe.columns) 456 457 self.clean_data_frame(dataframe) 458 459 dataframe.rename(columns=self.parameters.header_translate, inplace=True) 460 461 output_parameters = self.get_output_parameters(polarity) 462 463 mass_spec = MassSpecCentroid( 464 dataframe.to_dict(orient="list"), 465 output_parameters, 466 auto_process=auto_process, 467 ) 468 469 if loadSettings: 470 self.load_settings(mass_spec, output_parameters) 471 472 return mass_spec
Reads mass list data types and returns the mass spectrum object.
Parameters
- polarity (bool, optional): The polarity of the mass spectrum. Can be +1 or -1. If not provided, it will be determined from the XML file.
- scan (int, optional): The scan number of the mass spectrum. Default is 0.
- auto_process (bool, optional): Whether to automatically process the mass spectrum. Default is True.
- loadSettings (bool, optional): Whether to load the settings for the mass spectrum. Default is True.
Returns
- mass_spec (MassSpecCentroid): The mass spectrum object representing the centroided mass spectrum.
Inherited Members
- corems.mass_spectrum.input.baseClass.MassListBaseClass
- MassListBaseClass
- file_location
- header_lines
- isCentroid
- isThermoProfile
- headerless
- analyzer
- instrument_label
- sample_name
- parameters
- set_parameter_from_toml
- set_parameter_from_json
- data_type
- delimiter
- encoding_detector
- set_data_type
- get_dataframe
- load_settings
- get_output_parameters
- clean_data_frame
- check_columns
- read_xml_peaks
- get_xml_polarity