lib.spectrum.peak

1 ############################################################################### 2 # # 3 # Copyright (C) 2004-2013 Edward d'Auvergne # 4 # Copyright (C) 2008 Sebastien Morin # 5 # Copyright (C) 2013 Troels E. Linnet # 6 # # 7 # This file is part of the program relax (http://www.nmr-relax.com). # 8 # # 9 # This program is free software: you can redistribute it and/or modify # 10 # it under the terms of the GNU General Public License as published by # 11 # the Free Software Foundation, either version 3 of the License, or # 12 # (at your option) any later version. # 13 # # 14 # This program is distributed in the hope that it will be useful, # 15 # but WITHOUT ANY WARRANTY; without even the implied warranty of # 16 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # 17 # GNU General Public License for more details. # 18 # # 19 # You should have received a copy of the GNU General Public License # 20 # along with this program. If not, see <http://www.gnu.org/licenses/>. # 21 # # 22 ############################################################################### 23 24 # Module docstring. 25 """Module containing functions for the handling of peak intensities.""" 26 27 28 # Python module imports. 29 import sys 30 from warnings import warn 31 32 # relax module imports. 33 from lib.errors import RelaxError 34 from lib.io import extract_data, read_spin_data, strip, write_data 35 from lib.spectrum import nmrpipe, nmrview, sparky, xeasy 36 from lib.spectrum.objects import Peak_list 37 from lib.warnings import RelaxWarning, RelaxNoSpinWarning 38 from pipe_control.mol_res_spin import generate_spin_id_unique, return_spin 39 40

41 -def autodetect_format(file_data):

42 """Automatically detect the format of the peak list. 43 44 @param file_data: The processed results file data. 45 @type file_data: list of lists of str 46 """ 47 48 # The first header line. 49 for line in file_data: 50 if line != []: 51 break 52 53 # Sparky format. 54 if line[0] == 'Assignment': 55 return 'sparky' 56 57 # NMRView format. 58 if line == ['label', 'dataset', 'sw', 'sf']: 59 return 'nmrview' 60 61 # NMRPipe SeriesTab. 62 if line[0] == 'REMARK' and line[1] == 'SeriesTab': 63 return 'seriestab' 64 65 # XEasy format. 66 if line == ['No.', 'Color', 'w1', 'w2', 'ass.', 'in', 'w1', 'ass.', 'in', 'w2', 'Volume', 'Vol.', 'Err.', 'Method', 'Comment']: 67 return 'xeasy' 68 69 # Assume a generic format. 70 return 'generic'

71 72

73 -def intensity_generic(peak_list=None, file_data=None, spin_id_col=None, mol_name_col=None, res_num_col=None, res_name_col=None, spin_num_col=None, spin_name_col=None, data_col=None, sep=None, spin_id=None):

74 """Extract the peak intensity information from the generic column formatted peak list. 75 76 @keyword peak_list: The peak list object to place all data into. 77 @type peak_list: lib.spectrum.objects.Peak_list instance 78 @keyword file_data: The data extracted from the file converted into a list of lists. 79 @type file_data: list of lists of str 80 @keyword spin_id_col: The column containing the spin ID strings (used by the generic intensity file format). If supplied, the mol_name_col, res_name_col, res_num_col, spin_name_col, and spin_num_col arguments must be none. @type spin_id_col: int or None @keyword mol_name_col: The column containing the molecule name information (used by the generic intensity file format). If supplied, spin_id_col must be None. 81 @type mol_name_col: int or None 82 @keyword res_name_col: The column containing the residue name information (used by the generic intensity file format). If supplied, spin_id_col must be None. 83 @type res_name_col: int or None 84 @keyword res_num_col: The column containing the residue number information (used by the generic intensity file format). If supplied, spin_id_col must be None. 85 @type res_num_col: int or None 86 @keyword spin_name_col: The column containing the spin name information (used by the generic intensity file format). If supplied, spin_id_col must be None. 87 @type spin_name_col: int or None 88 @keyword spin_num_col: The column containing the spin number information (used by the generic intensity file format). If supplied, spin_id_col must be None. 89 @type spin_num_col: int or None 90 @keyword data_col: The column containing the peak intensities. 91 @type data_col: int or list of int 92 @keyword sep: The column separator which, if None, defaults to whitespace. 93 @type sep: str or None 94 @keyword spin_id: The spin ID string used to restrict data loading to a subset of all spins. 95 @type spin_id: None or str 96 @raises RelaxError: When the expected peak intensity is not a float. 97 """ 98 99 # Check the intensity column argument. 100 if data_col == None: 101 raise RelaxError("The data column argument has not been supplied.") 102 103 # Strip the data. 104 file_data = strip(file_data) 105 106 # Convert the the data_col argument to a list if needed. 107 if not isinstance(data_col, list): 108 data_col = [data_col] 109 110 # Loop over the file data. 111 for line in file_data: 112 # Loop over the intensity columns, storing the data. 113 intensity = [] 114 for i in range(len(data_col)): 115 # Extract the data for the single line (loop of a single element). 116 for values in read_spin_data(file_data=[line], spin_id_col=spin_id_col, mol_name_col=mol_name_col, res_num_col=res_num_col, res_name_col=res_name_col, spin_num_col=spin_num_col, spin_name_col=spin_name_col, data_col=data_col[i], sep=sep, spin_id=spin_id): 117 # Check the values. 118 if len(values) != 6: 119 raise RelaxError("The molecule name, residue number and name, spin number and name, and value columns could not be found in the data %s." % repr(values)) 120 121 # Unpack. 122 mol_name, res_num, res_name, spin_num, spin_name, value = values 123 124 # Store the intensity. 125 intensity.append(value) 126 127 # Add the assignment to the peak list object. 128 peak_list.add(mol_names=[mol_name, mol_name], res_nums=[res_num, res_num], res_names=[res_name, res_name], spin_nums=[spin_num, spin_num], spin_names=[spin_name, spin_name], intensity=intensity)

129 130

131 -def read_peak_list(file=None, dir=None, int_col=None, spin_id_col=None, mol_name_col=None, res_num_col=None, res_name_col=None, spin_num_col=None, spin_name_col=None, sep=None, spin_id=None):

132 """Read the peak intensity data. 133 134 @keyword file: The name of the file containing the peak intensities. 135 @type file: str 136 @keyword dir: The directory where the file is located. 137 @type dir: str 138 @keyword int_col: The column containing the peak intensity data. If set to None, the auto-detection of intensity data will be attempted. 139 @type int_col: None or int 140 @keyword spin_id_col: The column containing the spin ID strings (used by the generic intensity file format). If supplied, the mol_name_col, res_name_col, res_num_col, spin_name_col, and spin_num_col arguments must be none. 141 @type spin_id_col: int or None 142 @keyword mol_name_col: The column containing the molecule name information (used by the generic intensity file format). If supplied, spin_id_col must be None. 143 @type mol_name_col: int or None 144 @keyword res_name_col: The column containing the residue name information (used by the generic intensity file format). If supplied, spin_id_col must be None. 145 @type res_name_col: int or None 146 @keyword res_num_col: The column containing the residue number information (used by the generic intensity file format). If supplied, spin_id_col must be None. 147 @type res_num_col: int or None 148 @keyword spin_name_col: The column containing the spin name information (used by the generic intensity file format). If supplied, spin_id_col must be None. 149 @type spin_name_col: int or None 150 @keyword spin_num_col: The column containing the spin number information (used by the generic intensity file format). If supplied, spin_id_col must be None. 151 @type spin_num_col: int or None 152 @keyword sep: The column separator which, if None, defaults to whitespace. 153 @type sep: str or None 154 @keyword spin_id: The spin ID string used to restrict data loading to a subset of all spins. 155 @type spin_id: None or str 156 @return: The peak list object containing all relevant data in the peak list. 157 @rtype: lib.spectrum.objects.Peak_list instance 158 """ 159 160 # Extract the data from the file. 161 file_data = extract_data(file, dir, sep=sep) 162 163 # Initialise the peak list object. 164 peak_list = Peak_list() 165 166 # Automatic format detection. 167 format = autodetect_format(file_data) 168 169 # Generic. 170 if format == 'generic': 171 # Print out. 172 print("Generic formatted data file.\n") 173 174 # Extract the data. 175 intensity_generic(peak_list=peak_list, file_data=file_data, spin_id_col=spin_id_col, mol_name_col=mol_name_col, res_num_col=res_num_col, res_name_col=res_name_col, spin_num_col=spin_num_col, spin_name_col=spin_name_col, data_col=int_col, sep=sep, spin_id=spin_id) 176 177 # NMRView. 178 elif format == 'nmrview': 179 # Print out. 180 print("NMRView formatted data file.\n") 181 182 # Extract the data. 183 nmrview.read_list(peak_list=peak_list, file_data=file_data) 184 185 # NMRPipe SeriesTab. 186 elif format == 'seriestab': 187 # Print out. 188 print("NMRPipe SeriesTab formatted data file.\n") 189 190 # Extract the data. 191 nmrpipe.read_seriestab(peak_list=peak_list, file_data=file_data, int_col=int_col) 192 193 # Sparky. 194 elif format == 'sparky': 195 # Print out. 196 print("Sparky formatted data file.\n") 197 198 # Extract the data. 199 sparky.read_list(peak_list=peak_list, file_data=file_data) 200 201 # XEasy. 202 elif format == 'xeasy': 203 # Print out. 204 print("XEasy formatted data file.\n") 205 206 # Extract the data. 207 xeasy.read_list(peak_list=peak_list, file_data=file_data, int_col=int_col) 208 209 # Return the peak list object. 210 return peak_list

211

Source Code for Module lib.spectrum.peak_list