Source Code for Module lib.spectrum.nmrpipe

  1  ############################################################################### 
  2  #                                                                             # 
  3  # Copyright (C) 2013 Troels E. Linnet                                         # 
  4  #                                                                             # 
  5  # This file is part of the program relax (http://www.nmr-relax.com).          # 
  6  #                                                                             # 
  7  # This program is free software: you can redistribute it and/or modify        # 
  8  # it under the terms of the GNU General Public License as published by        # 
  9  # the Free Software Foundation, either version 3 of the License, or           # 
 10  # (at your option) any later version.                                         # 
 11  #                                                                             # 
 12  # This program is distributed in the hope that it will be useful,             # 
 13  # but WITHOUT ANY WARRANTY; without even the implied warranty of              # 
 14  # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the               # 
 15  # GNU General Public License for more details.                                # 
 16  #                                                                             # 
 17  # You should have received a copy of the GNU General Public License           # 
 18  # along with this program.  If not, see <http://www.gnu.org/licenses/>.       # 
 19  #                                                                             # 
 20  ############################################################################### 
 21   
 22  # Module docstring. 
 23  """Module containing functions for handling NMRPipe SeriesTab files.""" 
 24   
 25   
 26  # Python module imports. 
 27  import re 
 28  from warnings import warn 
 29   
 30  # relax module imports. 
 31  from lib.errors import RelaxError 
 32  from lib.io import open_write_file, strip 
 33  from lib.warnings import RelaxWarning 
 34   
 35   
 36 -def read_seriestab(peak_list=None, file_data=None, int_col=None): 
 37      """Extract the intensity information from the NMRPipe SeriesTab peak intensity file. 
 38   
 39      @keyword peak_list: The peak list object to place all data into. 
 40      @type peak_list:    lib.spectrum.objects.Peak_list instance 
 41      @keyword file_data: The data extracted from the file converted into a list of lists. 
 42      @type file_data:    list of lists of str 
 43      @keyword int_col:  The column which to multiply the peak intensity data (used by the SeriesTab intensity file format). 
 44      @type int_col:     int 
 45      @raises RelaxError: When the expected peak intensity is not a float. 
 46      """ 
 47   
 48      # Set start variables. 
 49      modeline = False 
 50      mode = False 
 51      varsline = False 
 52      header = False 
 53   
 54      # Loop over lines, to extract variables and find header size. 
 55      line_nr = 0 
 56      for line in file_data: 
 57          if len(line) > 0: 
 58              if line[0] == 'REMARK' and line[1] == 'Mode:': 
 59                  modeline = line[2:] 
 60                  mode = modeline[0] 
 61              elif line[0] == 'VARS': 
 62                  varsline = line[1:] 
 63              elif line[0] == '1': 
 64                  header = line_nr 
 65                  break 
 66          line_nr += 1 
 67   
 68      # Raise RelaxError, if the MODE is not found. 
 69      if not (modeline and mode): 
 70          raise RelaxError("MODE not detected. Expecting line 2:\nREMARK Mode: Summation") 
 71   
 72      # Raise RelaxError, if the VARS line is not found. 
 73      if not (varsline): 
 74          raise RelaxError("VARS not detected. Expecting line 8:\nVARS INDEX X_AXIS Y_AXIS X_PPM Y_PPM VOL ASS Z_A0") 
 75   
 76      # Raise RelaxError, if the header size is not found. 
 77      if not header: 
 78          raise RelaxError("'1' not detected in start of line. Cannot determine header size.") 
 79   
 80      # Find index of assignment ASS. 
 81      ass_i = varsline.index('ASS') 
 82   
 83      # Chemical shifts preparation. 
 84      w1_col = None 
 85      w2_col = None 
 86   
 87      # Find index of chemical shift Y_PPM which in sparky is w1. 
 88      w1_col = varsline.index('Y_PPM') 
 89   
 90      # Find index of chemical shift X_PPM which in sparky is w2. 
 91      w2_col = varsline.index('X_PPM') 
 92   
 93      # Make a regular search for Z_A entries. 
 94      Z_A = re.compile("Z_A*") 
 95      spectra = list(filter(Z_A.search, varsline)) 
 96   
 97      # Find index of Z_A entries. 
 98      spectra_i = [] 
 99      for y in spectra: 
100          spectra_i.append(varsline.index(y)) 
101   
102      # Remove the header. 
103      file_data = file_data[header:] 
104   
105      # Loop over the file data. 
106      for line in file_data: 
107          # Skip non-assigned peaks. 
108          if line[ass_i] == '?-?': 
109              continue 
110   
111          # First split by the 2D separator. 
112          assign1, assign2 = re.split('-', line[ass_i]) 
113   
114          # The assignment of the first dimension. 
115          row1 = re.split('([a-zA-Z]+)', assign1) 
116          name1 = row1[-2] + row1[-1] 
117   
118          # The assignment of the second dimension. 
119          row2 = re.split('([a-zA-Z]+)', assign2) 
120          name2 = row2[-2] + row2[-1] 
121   
122          # Get the residue number for dimension 1. 
123          got_res_num1 = True 
124          try: 
125              res_num1 = int(row1[-3]) 
126          except: 
127              got_res_num1 = False 
128              raise RelaxError("Improperly formatted NMRPipe SeriesTab file, cannot process the residue number for dimension 1 in assignment: %s." % line[0]) 
129   
130          # Get the residue number for dimension 2. 
131          try: 
132              res_num2 = int(row2[-3]) 
133          except: 
134              # We cannot always expect dimension 2 to have residue number. 
135              if got_res_num1: 
136                  res_num2 = res_num1 
137              else: 
138                  res_num2 = None 
139                  warn(RelaxWarning("Improperly formatted NMRPipe SeriesTab file, cannot process the residue number for dimension 2 in assignment: %s. Setting residue number to %s." % (line[0], res_num2))) 
140   
141          # The residue name for dimension 1. 
142          got_res_name1 = True 
143          try: 
144              res_name1 = row1[-4] 
145          except: 
146              got_res_name1 = False 
147              res_name1 = None 
148              warn(RelaxWarning("Improperly formatted NMRPipe SeriesTab file, cannot process the residue name for dimension 1 in assignment: %s. Setting residue name to %s." % (line[0], res_name1))) 
149   
150          # The residue name for dimension 2. 
151          try: 
152              res_name2 = row2[-4] 
153          except: 
154              # We cannot always expect dimension 2 to have residue name. 
155              if got_res_name1: 
156                  res_name2 = res_name1 
157              else: 
158                  res_name2 = None 
159                  warn(RelaxWarning("Improperly formatted NMRPipe SeriesTab file, cannot process the residue name for dimension 2 in assignment: %s. Setting residue name to %s." % (line[0], res_name2))) 
160   
161          # Get the intensities. 
162          try: 
163              # Loop over the spectra. 
164              intensities = [] 
165              for i in range(len(spectra)): 
166                  # The intensity is given by column multiplication. 
167                  intensities.append(float(line[spectra_i[i]])*float(line[5])) 
168   
169          # Bad data. 
170          except ValueError: 
171              raise RelaxError("The peak intensity value %s from the line %s is invalid." % (intensity, line)) 
172   
173          # Chemical shifts. 
174          w1 = None 
175          w2 = None 
176          if w1_col != None: 
177              try: 
178                  w1 = float(line[w1_col]) 
179              except ValueError: 
180                  raise RelaxError("The chemical shift from the line %s is invalid." % line) 
181          if w2_col != None: 
182              try: 
183                  w2 = float(line[w2_col]) 
184              except ValueError: 
185                  raise RelaxError("The chemical shift from the line %s is invalid." % line) 
186   
187          # Add the assignment to the peak list object. 
188          peak_list.add(res_nums=[res_num1, res_num2], res_names=[res_name1, res_name2], spin_names=[name1, name2], shifts=[w1, w2], intensity=intensities, intensity_name=spectra) 
189