Source Code for Module lib.software.bruker_dc

  1  ############################################################################### 
  2  #                                                                             # 
  3  # Copyright (C) 2011-2014 Edward d'Auvergne                                   # 
  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 for the reading of Bruker Dynamics Centre (DC) files.""" 
 24   
 25  # Python module imports. 
 26  from re import search, split 
 27   
 28  # relax module imports. 
 29  from lib.errors import RelaxError 
 30  from lib.io import open_read_file 
 31   
 32   
 33 -def convert_relax_data(data): 
 34      """Determine the relaxation data from the given DC data. 
 35   
 36      @param data:    The list of Tx, Tx error, and scaling factor for a given residue from the DC file. 
 37      @type data:     list of str 
 38      """ 
 39   
 40      # Convert the value from Tx to Rx. 
 41      rx = 1.0 / float(data[0]) 
 42   
 43      # Remove the scaling. 
 44      rx_err = float(data[1]) / float(data[2]) 
 45   
 46      # Convert the Tx error to an Rx error. 
 47      rx_err = rx**2 * rx_err 
 48   
 49      # Return the value and error. 
 50      return rx, rx_err 
 51   
 52   
 53 -def get_res_num(data): 
 54      """Determine the residue number from the given DC data. 
 55   
 56      @param data:    The list of residue info, split by whitespace, from the DC file. 
 57      @type data:     list of str 
 58      """ 
 59   
 60      # Init. 
 61      res_num = None 
 62   
 63      # Split the data. 
 64      row = split('([0-9]+)', data) 
 65   
 66      # Loop over the new list. 
 67      for j in range(len(row)): 
 68          try: 
 69              res_num = int(row[j]) 
 70          except ValueError: 
 71              pass 
 72   
 73      # Return the value. 
 74      return ":%s" % res_num 
 75   
 76   
 77 -def parse_file(file=None, dir=None): 
 78      """Parse the DC data file and return the extracted data. 
 79   
 80      @keyword file:  The name of the file to open. 
 81      @type file:     str 
 82      @keyword dir:   The directory containing the file (defaults to the current directory if None). 
 83      @type dir:      str or None 
 84      @return:        The data from the Bruker Dynamics Centre file.  This includes the values, the errors, the residue numbers, the integration type, the field strength frequency, the relaxation data type, the isotope, the spin name, and the BDC version number. 
 85      @rtype:         list of float, list of float, list of int, str, float, str, str, str, str 
 86      """ 
 87   
 88      # Extract the data from the file. 
 89      file_handle = open_read_file(file, dir) 
 90      lines = file_handle.readlines() 
 91      file_handle.close() 
 92   
 93      # Init. 
 94      values = [] 
 95      errors = [] 
 96      res_nums = [] 
 97      int_type = None 
 98      isotope = None 
 99      spin_name = None 
100   
101      # Loop over the data. 
102      in_ri_data = False 
103      for line in lines: 
104          # Split the line. 
105          row = split("\t", line) 
106   
107          # Strip the rubbish. 
108          for j in range(len(row)): 
109              row[j] = row[j].strip() 
110   
111          # Skip empty lines. 
112          if len(row) == 0 or row == ['']: 
113              continue 
114   
115          # The DC version. 
116          if row[0] == 'generated by:': 
117              version = row[1] 
118   
119          # Check for bad errors. 
120          if row[0] == 'Systematic error estimation of data:': 
121              # Badness. 
122              if row[1] == 'worst case per peak scenario': 
123                  raise RelaxError("The errors estimation method \"worst case per peak scenario\" is not suitable for model-free analysis.  Please go back to the DC and switch to \"average variance calculation\".") 
124   
125          # The data type. 
126          if row[0] == 'Project:': 
127              if search('T1', row[1]): 
128                  ri_type = 'R1' 
129              elif search('T2', row[1]): 
130                  ri_type = 'R2' 
131              elif search('NOE', row[1]): 
132                  ri_type = 'NOE' 
133   
134          # Get the frequency, converting to Hz. 
135          elif row[0] == 'Proton frequency[MHz]:': 
136              frq = float(row[1]) * 1e6 
137   
138          # Inside the relaxation data section. 
139          elif row[0] == 'SECTION:' and row[1] == 'results': 
140              in_ri_data = True 
141   
142          # The relaxation data. 
143          elif in_ri_data: 
144              # Skip the header. 
145              if row[0] == 'Peak name': 
146                  # Catch old PDC files (to fix https://web.archive.org/web/https://gna.org/bugs/?20152). 
147                  pdc_file = False 
148                  if ri_type == 'R1' and not search('R1', line): 
149                      pdc_file = True 
150                  elif ri_type == 'R2' and not search('R2', line): 
151                      pdc_file = True 
152                  if pdc_file: 
153                      raise RelaxError("The old Protein Dynamics Center (PDC) files are not supported") 
154   
155                  # Skip. 
156                  continue 
157   
158              # The residue info. 
159              res_nums.append(get_res_num(row[0])) 
160   
161              # Get the relaxation data. 
162              if ri_type != 'NOE': 
163                  #rx, rx_err = convert_relax_data(row[3:]) 
164                  rx = float(row[-2]) 
165                  rx_err = float(row[-1]) 
166              else: 
167                  rx = float(row[-3]) 
168                  rx_err = float(row[-2]) 
169   
170              # Append the data. 
171              values.append(rx) 
172              errors.append(rx_err) 
173   
174          # The temperature. 
175          elif row[0] == 'Temperature (K):': 
176              # Set the value (not implemented yet). 
177              pass 
178   
179          # The labelling. 
180          elif row[0] == 'Labelling:': 
181              # Store the isotope for later use. 
182              isotope = row[1] 
183   
184              # Name the spins. 
185              spin_name = split('([A-Z]+)', row[1])[1] 
186   
187          # The integration method. 
188          elif row[0] == 'Used integrals:': 
189              # Peak heights. 
190              if row[1] == 'peak intensities': 
191                  int_type = 'height' 
192   
193              # Peak volumes: 
194              if row[1] == 'area integral': 
195                  int_type = 'volume' 
196   
197      # Return the data. 
198      return values, errors, res_nums, int_type, frq, ri_type, spin_name, isotope, version 
199