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.warnings import RelaxWarning 
 33   
 34   
 35 -def read_seriestab(peak_list=None, file_data=None, int_col=None): 
 36      """Extract the intensity information from the NMRPipe SeriesTab peak intensity file. 
 37   
 38      @keyword peak_list: The peak list object to place all data into. 
 39      @type peak_list:    lib.spectrum.objects.Peak_list instance 
 40      @keyword file_data: The data extracted from the file converted into a list of lists. 
 41      @type file_data:    list of lists of str 
 42      @keyword int_col:  The column which to multiply the peak intensity data (used by the SeriesTab intensity file format). 
 43      @type int_col:     int 
 44      @raises RelaxError: When the expected peak intensity is not a float. 
 45      """ 
 46   
 47      # Set start variables. 
 48      modeline = False 
 49      mode = False 
 50      varsline = False 
 51      header = False 
 52   
 53      # Loop over lines, to extract variables and find header size. 
 54      line_nr = 0 
 55      for line in file_data: 
 56          if len(line) > 0: 
 57              if line[0] == 'REMARK' and line[1] == 'Mode:': 
 58                  modeline = line[2:] 
 59                  mode = modeline[0] 
 60              elif line[0] == 'VARS': 
 61                  varsline = line[1:] 
 62              elif line[0] == '1': 
 63                  header = line_nr 
 64                  break 
 65          line_nr += 1 
 66   
 67      # Raise RelaxError, if the MODE is not found. 
 68      if not (modeline and mode): 
 69          raise RelaxError("MODE not detected. Expecting line 2:\nREMARK Mode: Summation") 
 70   
 71      # Raise RelaxError, if the VARS line is not found. 
 72      if not (varsline): 
 73          raise RelaxError("VARS not detected. Expecting line 8:\nVARS INDEX X_AXIS Y_AXIS X_PPM Y_PPM VOL ASS Z_A0") 
 74   
 75      # Raise RelaxError, if the header size is not found. 
 76      if not header: 
 77          raise RelaxError("'1' not detected in start of line. Cannot determine header size.") 
 78   
 79      # Find index of assignment ASS. 
 80      ass_i = varsline.index('ASS') 
 81   
 82      # Chemical shifts preparation. 
 83      w1_col = None 
 84      w2_col = None 
 85   
 86      # Find index of chemical shift Y_PPM which in sparky is w1. 
 87      w1_col = varsline.index('Y_PPM') 
 88   
 89      # Find index of chemical shift X_PPM which in sparky is w2. 
 90      w2_col = varsline.index('X_PPM') 
 91   
 92      # Make a regular search for Z_A entries. 
 93      Z_A = re.compile("Z_A*") 
 94      spectra = list(filter(Z_A.search, varsline)) 
 95   
 96      # Find index of Z_A entries. 
 97      spectra_i = [] 
 98      for y in spectra: 
 99          spectra_i.append(varsline.index(y)) 
100   
101      # Remove the header. 
102      file_data = file_data[header:] 
103   
104      # Loop over the file data. 
105      for line in file_data: 
106          # Skip non-assigned peaks. 
107          if line[ass_i] == '?-?': 
108              continue 
109   
110          # First split by the 2D separator. 
111          assign1, assign2 = re.split('-', line[ass_i]) 
112   
113          # The assignment of the first dimension. 
114          row1 = re.split('([a-zA-Z]+)', assign1) 
115          name1 = row1[-2] + row1[-1] 
116   
117          # The assignment of the second dimension. 
118          row2 = re.split('([a-zA-Z]+)', assign2) 
119          name2 = row2[-2] + row2[-1] 
120   
121          # Get the residue number for dimension 1. 
122          got_res_num1 = True 
123          try: 
124              res_num1 = int(row1[-3]) 
125          except: 
126              got_res_num1 = False 
127              raise RelaxError("Improperly formatted NMRPipe SeriesTab file, cannot process the residue number for dimension 1 in assignment: %s." % line[0]) 
128   
129          # Get the residue number for dimension 2. 
130          try: 
131              res_num2 = int(row2[-3]) 
132          except: 
133              # We cannot always expect dimension 2 to have residue number. 
134              if got_res_num1: 
135                  res_num2 = res_num1 
136              else: 
137                  res_num2 = None 
138                  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))) 
139   
140          # The residue name for dimension 1. 
141          got_res_name1 = True 
142          try: 
143              res_name1 = row1[-4] 
144          except: 
145              got_res_name1 = False 
146              res_name1 = None 
147              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))) 
148   
149          # The residue name for dimension 2. 
150          try: 
151              res_name2 = row2[-4] 
152          except: 
153              # We cannot always expect dimension 2 to have residue name. 
154              if got_res_name1: 
155                  res_name2 = res_name1 
156              else: 
157                  res_name2 = None 
158                  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))) 
159   
160          # Get the intensities. 
161          try: 
162              # Loop over the spectra. 
163              intensities = [] 
164              for i in range(len(spectra)): 
165                  # The intensity is given by column multiplication. 
166                  intensities.append(float(line[spectra_i[i]])*float(line[5])) 
167   
168          # Bad data. 
169          except ValueError: 
170              raise RelaxError("The peak intensity value %s from the line %s is invalid." % (intensity, line)) 
171   
172          # Chemical shifts. 
173          w1 = None 
174          w2 = None 
175          if w1_col != None: 
176              try: 
177                  w1 = float(line[w1_col]) 
178              except ValueError: 
179                  raise RelaxError("The chemical shift from the line %s is invalid." % line) 
180          if w2_col != None: 
181              try: 
182                  w2 = float(line[w2_col]) 
183              except ValueError: 
184                  raise RelaxError("The chemical shift from the line %s is invalid." % line) 
185   
186          # Add the assignment to the peak list object. 
187          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) 
188