Source Code for Module generic_fns.bruker

  1  ############################################################################### 
  2  #                                                                             # 
  3  # Copyright (C) 2011-2012 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 generic_fns import pipes 
 30  from generic_fns import value 
 31  from generic_fns.exp_info import software_select 
 32  from generic_fns.mol_res_spin import exists_mol_res_spin_data, name_spin, set_spin_isotope, spin_loop 
 33  from generic_fns.relax_data import pack_data, peak_intensity_type 
 34  from relax_errors import RelaxError, RelaxNoSequenceError 
 35  from relax_io import open_read_file 
 36  from physical_constants import element_from_isotope 
 37   
 38   
 39 -def convert_relax_data(data): 
 40      """Determine the relaxation data from the given DC data. 
 41   
 42      @param data:    The list of Tx, Tx error, and scaling factor for a given residue from the DC file. 
 43      @type data:     list of str 
 44      """ 
 45   
 46      # Convert the value from Tx to Rx. 
 47      rx = 1.0 / float(data[0]) 
 48   
 49      # Remove the scaling. 
 50      rx_err = float(data[1]) / float(data[2]) 
 51   
 52      # Convert the Tx error to an Rx error. 
 53      rx_err = rx**2 * rx_err 
 54   
 55      # Return the value and error. 
 56      return rx, rx_err 
 57   
 58   
 59 -def get_res_num(data): 
 60      """Determine the residue number from the given DC data. 
 61   
 62      @param data:    The list of residue info, split by whitespace, from the DC file. 
 63      @type data:     list of str 
 64      """ 
 65   
 66      # Init. 
 67      res_num = None 
 68   
 69      # Split the data. 
 70      row = split('([0-9]+)', data) 
 71   
 72      # Loop over the new list. 
 73      for j in range(len(row)): 
 74          try: 
 75              res_num = int(row[j]) 
 76          except ValueError: 
 77              pass 
 78   
 79      # Return the value. 
 80      return ":%s" % res_num 
 81   
 82   
 83 -def read(ri_id=None, file=None, dir=None): 
 84      """Read the DC data file and place all the data into the relax data store. 
 85   
 86      @keyword ri_id: The relaxation data ID string. 
 87      @type ri_id:    str 
 88      @keyword file:  The name of the file to open. 
 89      @type file:     str 
 90      @keyword dir:   The directory containing the file (defaults to the current directory if None). 
 91      @type dir:      str or None 
 92      """ 
 93   
 94      # Test if the current pipe exists. 
 95      pipes.test() 
 96   
 97      # Test if sequence data is loaded. 
 98      if not exists_mol_res_spin_data(): 
 99          raise RelaxNoSequenceError 
100   
101      # Extract the data from the file. 
102      file_handle = open_read_file(file, dir) 
103      lines = file_handle.readlines() 
104      file_handle.close() 
105   
106      # Init. 
107      values = [] 
108      errors = [] 
109      res_nums = [] 
110      int_type = None 
111   
112      # Loop over the data. 
113      in_ri_data = False 
114      for line in lines: 
115          # Split the line. 
116          row = split("\t", line) 
117   
118          # Strip the rubbish. 
119          for j in range(len(row)): 
120              row[j] = row[j].strip() 
121   
122          # Empty line. 
123          if len(row) == 0: 
124              continue 
125   
126          # The DC version. 
127          if row[0] == 'generated by:': 
128              version = row[1] 
129   
130          # Check for bad errors. 
131          if row[0] == 'Systematic error estimation of data:': 
132              # Badness. 
133              if row[1] == 'worst case per peak scenario': 
134                  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\".") 
135   
136          # The data type. 
137          if row[0] == 'Project:': 
138              if search('T1', row[1]): 
139                  ri_type = 'R1' 
140              elif search('T2', row[1]): 
141                  ri_type = 'R2' 
142              elif search('NOE', row[1]): 
143                  ri_type = 'NOE' 
144   
145          # Get the frequency, converting to Hz. 
146          elif row[0] == 'Proton frequency[MHz]:': 
147              frq = float(row[1]) * 1e6 
148   
149          # Inside the relaxation data section. 
150          elif row[0] == 'SECTION:' and row[1] == 'results': 
151              in_ri_data = True 
152   
153          # The relaxation data. 
154          elif in_ri_data: 
155              # Skip the header. 
156              if row[0] == 'Peak name': 
157                  # Catch old PDC files (to fix https://web.archive.org/web/https://gna.org/bugs/?20152). 
158                  pdc_file = False 
159                  if ri_type == 'R1' and not search('R1', line): 
160                      pdc_file = True 
161                  elif ri_type == 'R2' and not search('R2', line): 
162                      pdc_file = True 
163                  if pdc_file: 
164                      raise RelaxError("The old Protein Dynamics Center (PDC) files are not supported") 
165   
166                  # Skip. 
167                  continue 
168   
169              # The residue info. 
170              res_nums.append(get_res_num(row[0])) 
171   
172              # Get the relaxation data. 
173              if ri_type != 'NOE': 
174                  #rx, rx_err = convert_relax_data(row[3:]) 
175                  rx = float(row[-2]) 
176                  rx_err = float(row[-1]) 
177              else: 
178                  rx = float(row[-3]) 
179                  rx_err = float(row[-2]) 
180   
181              # Append the data. 
182              values.append(rx) 
183              errors.append(rx_err) 
184   
185          # The temperature. 
186          elif row[0] == 'Temperature (K):': 
187              # Set the value (not implemented yet). 
188              pass 
189   
190          # The labelling. 
191          elif row[0] == 'Labelling:': 
192              # Store the isotope for later use. 
193              isotope = row[1] 
194   
195              # Set the isotope value. 
196              set_spin_isotope(isotope=isotope, force=None) 
197   
198              # Name the spins. 
199              name = split('([A-Z]+)', row[1])[1] 
200              name_spin(name=name, force=None) 
201   
202          # The integration method. 
203          elif row[0] == 'Used integrals:': 
204              # Peak heights. 
205              if row[1] == 'peak intensities': 
206                  int_type = 'height' 
207   
208              # Peak volumes: 
209              if row[1] == 'area integral': 
210                  int_type = 'volume' 
211   
212      # Modify the residue numbers by adding the heteronucleus name. 
213      atom_name = element_from_isotope(isotope) 
214      for i in range(len(res_nums)): 
215          res_nums[i] += '@' + atom_name 
216   
217      # Pack the data. 
218      pack_data(ri_id, ri_type, frq, values, errors, spin_ids=res_nums) 
219   
220      # Set the integration method. 
221      peak_intensity_type(ri_id=ri_id, type=int_type) 
222   
223      # Set the DC as used software. 
224      software_select('Bruker DC', version=version) 
225