def run(data_path, grid_search_path, ensemble_output_path, score_output_path,
number_of_partitions, number_of_iterations, best_proportion,
used_proportion):
# Read partitioned input data
data = read_partitioned_data(data_path, number_of_iterations,
number_of_partitions)
# Read true values from the partitioned data set
true_values = get_true_values(data)
# Read the grid search results as input data
results = read_data(grid_search_path)
# Construct the ensemble based on the results of the grid search and the
# proportion parameters passed to this script
ensemble = construct_ensemble(results, best_proportion, used_proportion)
# Retrieve the classification results from the ensemble based on a
# popularity vote
predicted_values = ensemble_vote(ensemble)
# Score the classification results of the ensemble against the true values
result = Result()
result.add_values(true_values, predicted_values)
result.calculate()
# Output the ensemble into the specified file
write_data(ensemble_output_path, ensemble)
# Output the ensemble score into the specified file
write_data(score_output_path, result)
def write(align_id=None, file=None, dir=None, bc=False, force=False):
"""Display the RDC data corresponding to the alignment ID.
@keyword align_id: The alignment tensor ID string.
@type align_id: str
@keyword file: The file name or object to write to.
@type file: str or file object
@keyword dir: The name of the directory to place the file into (defaults to the current directory).
@type dir: str
@keyword bc: The back-calculation flag which if True will cause the back-calculated rather than measured data to be written.
@type bc: bool
@keyword force: A flag which if True will cause any pre-existing file to be overwritten.
@type force: bool
"""
# Check the pipe setup.
check_pipe_setup(sequence=True, rdc_id=align_id, rdc=True)
# Open the file for writing.
file = open_write_file(file, dir, force)
# Loop over the interatomic data containers and collect the data.
data = []
for interatom in interatomic_loop():
# Skip deselected containers.
if not interatom.select:
continue
# Skip containers with no RDCs.
if not bc and (not hasattr(interatom, 'rdc') or align_id not in interatom.rdc.keys()):
continue
elif bc and (not hasattr(interatom, 'rdc_bc') or align_id not in interatom.rdc_bc.keys()):
continue
# Append the spin data.
data.append([])
data[-1].append(interatom.spin_id1)
data[-1].append(interatom.spin_id2)
# Handle the missing rdc_data_types variable.
data_type = None
if hasattr(interatom, 'rdc_data_types'):
data_type = interatom.rdc_data_types[align_id]
# The value.
if bc:
data[-1].append(repr(convert(interatom.rdc_bc[align_id], data_type, align_id)))
else:
data[-1].append(repr(convert(interatom.rdc[align_id], data_type, align_id)))
# The error.
if hasattr(interatom, 'rdc_err') and align_id in interatom.rdc_err.keys():
data[-1].append(repr(convert(interatom.rdc_err[align_id], data_type, align_id)))
else:
data[-1].append(repr(None))
# Write out.
write_data(out=file, headings=["Spin_ID1", "Spin_ID2", "RDCs", "RDC_error"], data=data)
def run(input_path, output_path):
# Read the results as input data
results = read_data(input_path)
# Retrieve the best result
best_result = sorted(results, key=lambda k: k.average_f1(),
reverse=True)[0]
# Output the score into the specified file
write_data(output_path, best_result)
def create_par_chi2(self, file_prefix, par_chi2_vals):
"""Function for creating file with parameters and the chi2 value."""
# Print out.
print("\nCreating the file with parameters and the chi2 value.")
# Open the file.
par_file = open_write_file(file_name=file_prefix + '.par',
dir=self.dir,
force=True)
# Copy the nested list to sort it.
par_chi2_vals_sort = deepcopy(par_chi2_vals)
# Then sort the value.
par_chi2_vals_sort.sort(key=lambda values: values[4])
# Collect the data structure, which is a list of list of strings.
data = []
for i, line in enumerate(par_chi2_vals):
line_sort = par_chi2_vals_sort[i]
# Convert values to strings.
line_str = ["%3.5f" % j for j in line]
line_sort_str = ["%3.5f" % j for j in line_sort]
# Convert the index from float to index.
line_str[0] = "%i" % line[0]
line_sort_str[0] = "%i" % line_sort[0]
# Merge the two lists and append to data.
data_list = line_str + line_sort_str
data.append(data_list)
# Make the headings.
headings = ['i'] + self.params + ['chi2']
headings += headings
# Add "_sort" to headings.
headings[5] = headings[5] + "_sort"
headings[6] = headings[6] + "_sort"
headings[7] = headings[7] + "_sort"
headings[8] = headings[8] + "_sort"
headings[9] = headings[9] + "_sort"
# Write the parameters and chi2 values to file.
write_data(out=par_file, headings=headings, data=data)
# Close the file.
par_file.close()
def show_apod_rmsd_to_file(file_name=None, dir=None, path_to_command='showApod', outdir=None, force=False):
"""Extract showApod 'Noise Std Dev' from showApod, and write to file with same filename and ending '.rmsd'
@keyword file: The filename of the NMRPipe fourier transformed file.
@type file: str
@keyword dir: The directory where the file is located.
@type dir: str
@keyword path_to_command: If showApod not in PATH, then specify absolute path as: /path/to/showApod
@type path_to_command: str
@keyword outdir: The directory where to write the file. If 'None', then write in same directory.
@type outdir: str
@param force: Boolean argument which if True causes the file to be overwritten if it already exists.
@type force: bool
@return: Write the 'Noise Std Dev' from showApod to a file with same file filename, with ending '.rmsd'. This will be a file path.
@rtype: str
"""
# Call extract function.
apod_rmsd = show_apod_rmsd(file_name=file_name, dir=dir, path_to_command=path_to_command)
# Get the filename striped of extension details.
file_name_root = file_root(file_name)
# Define extension.
extension = ".rmsd"
# Define file name for writing.
file_name_out = file_name_root + extension
# Define folder to write to.
if outdir == None:
write_outdir = dir
else:
write_outdir = outdir
# Open file for writing,
wfile, wfile_path = open_write_file(file_name=file_name_out, dir=write_outdir, force=force, verbosity=1, return_path=True)
# Write to file.
out_write_data = [['%s'%apod_rmsd]]
# Write data
write_data(out=wfile, headings=None, data=out_write_data, sep=None)
# Close file.
wfile.close()
# Return path to file.
return wfile_path
def set_dist(spin_id1=None, spin_id2=None, ave_dist=None, unit='meter'):
"""Set up the magnetic dipole-dipole interaction.
@keyword spin_id1: The spin identifier string of the first spin of the pair.
@type spin_id1: str
@keyword spin_id2: The spin identifier string of the second spin of the pair.
@type spin_id2: str
@keyword ave_dist: The r^-3 averaged interatomic distance.
@type ave_dist: float
@keyword unit: The measurement unit. This can be either 'meter' or 'Angstrom'.
@type unit: str
"""
# Check the units.
if unit not in ['meter', 'Angstrom']:
raise RelaxError("The measurement unit of '%s' must be one of 'meter' or 'Angstrom'." % unit)
# Unit conversion.
if unit == 'Angstrom':
ave_dist = ave_dist * 1e-10
# Generate the selection objects.
sel_obj1 = Selection(spin_id1)
sel_obj2 = Selection(spin_id2)
# Loop over the interatomic containers.
data = []
for interatom in interatomic_loop():
# Get the spin info.
mol_name1, res_num1, res_name1, spin1 = return_spin(spin_hash=interatom._spin_hash1, full_info=True)
mol_name2, res_num2, res_name2, spin2 = return_spin(spin_hash=interatom._spin_hash2, full_info=True)
# No match, either way.
if not (sel_obj1.contains_spin(spin_num=spin1.num, spin_name=spin1.name, res_num=res_num1, res_name=res_name1, mol=mol_name1) and sel_obj2.contains_spin(spin_num=spin2.num, spin_name=spin2.name, res_num=res_num2, res_name=res_name2, mol=mol_name2)) and not (sel_obj2.contains_spin(spin_num=spin1.num, spin_name=spin1.name, res_num=res_num1, res_name=res_name1, mol=mol_name1) and sel_obj1.contains_spin(spin_num=spin2.num, spin_name=spin2.name, res_num=res_num2, res_name=res_name2, mol=mol_name2)):
continue
# Store the averaged distance.
interatom.r = ave_dist
# Store the data for the printout.
data.append([repr(interatom.spin_id1), repr(interatom.spin_id2), repr(ave_dist)])
# No data, so fail!
if not len(data):
raise RelaxError("No data could be set.")
# Print out.
print("The following averaged distances have been set:\n")
write_data(out=sys.stdout, headings=["Spin_ID_1", "Spin_ID_2", "Ave_distance(meters)"], data=data)
def show_apod_rmsd_to_file(file_name=None, dir=None, path_to_command='showApod', outdir=None, force=False):
"""Extract showApod 'Noise Std Dev' from showApod, and write to file with same filename and ending '.rmsd'
@keyword file: The filename of the NMRPipe fourier transformed file.
@type file: str
@keyword dir: The directory where the file is located.
@type dir: str
@keyword path_to_command: If showApod not in PATH, then specify absolute path as: /path/to/showApod
@type path_to_command: str
@keyword outdir: The directory where to write the file. If 'None', then write in same directory.
@type outdir: str
@param force: Boolean argument which if True causes the file to be overwritten if it already exists.
@type force: bool
@return: Write the 'Noise Std Dev' from showApod to a file with same file filename, with ending '.rmsd'. This will be a file path.
@rtype: str
"""
# Call extract function.
apod_rmsd = show_apod_rmsd(file_name=file_name, dir=dir, path_to_command=path_to_command)
# Get the filename striped of extension details.
file_name_root = file_root(file_name)
# Define extension.
extension = ".rmsd"
# Define file name for writing.
file_name_out = file_name_root + extension
# Define folder to write to.
if outdir == None:
write_outdir = dir
else:
write_outdir = outdir
# Open file for writing,
wfile, wfile_path = open_write_file(file_name=file_name_out, dir=write_outdir, force=force, verbosity=1, return_path=True)
# Write to file.
out_write_data = [['%s'%apod_rmsd]]
# Write data
write_data(out=wfile, headings=None, data=out_write_data, sep=None)
# Close file.
wfile.close()
# Return path to file.
return wfile_path
def set_dist(spin_id1=None, spin_id2=None, ave_dist=None, unit='meter'):
"""Set up the magnetic dipole-dipole interaction.
@keyword spin_id1: The spin identifier string of the first spin of the pair.
@type spin_id1: str
@keyword spin_id2: The spin identifier string of the second spin of the pair.
@type spin_id2: str
@keyword ave_dist: The r^-3 averaged interatomic distance.
@type ave_dist: float
@keyword unit: The measurement unit. This can be either 'meter' or 'Angstrom'.
@type unit: str
"""
# Check the units.
if unit not in ['meter', 'Angstrom']:
raise RelaxError("The measurement unit of '%s' must be one of 'meter' or 'Angstrom'." % unit)
# Unit conversion.
if unit == 'Angstrom':
ave_dist = ave_dist * 1e-10
# Generate the selection objects.
sel_obj1 = Selection(spin_id1)
sel_obj2 = Selection(spin_id2)
# Loop over the interatomic containers.
data = []
for interatom in interatomic_loop():
# Get the spin info.
mol_name1, res_num1, res_name1, spin1 = return_spin(interatom.spin_id1, full_info=True)
mol_name2, res_num2, res_name2, spin2 = return_spin(interatom.spin_id2, full_info=True)
# No match, either way.
if not (sel_obj1.contains_spin(spin_num=spin1.num, spin_name=spin1.name, res_num=res_num1, res_name=res_name1, mol=mol_name1) and sel_obj2.contains_spin(spin_num=spin2.num, spin_name=spin2.name, res_num=res_num2, res_name=res_name2, mol=mol_name2)) and not (sel_obj2.contains_spin(spin_num=spin1.num, spin_name=spin1.name, res_num=res_num1, res_name=res_name1, mol=mol_name1) and sel_obj1.contains_spin(spin_num=spin2.num, spin_name=spin2.name, res_num=res_num2, res_name=res_name2, mol=mol_name2)):
continue
# Store the averaged distance.
interatom.r = ave_dist
# Store the data for the printout.
data.append([repr(interatom.spin_id1), repr(interatom.spin_id2), repr(ave_dist)])
# No data, so fail!
if not len(data):
raise RelaxError("No data could be set.")
# Print out.
print("The following averaged distances have been set:\n")
write_data(out=sys.stdout, headings=["Spin_ID_1", "Spin_ID_2", "Ave_distance(meters)"], data=data)
def create_par_chi2(self, file_prefix, par_chi2_vals):
"""Function for creating file with parameters and the chi2 value."""
# Print out.
print("\nCreating the file with parameters and the chi2 value.")
# Open the file.
par_file = open_write_file(file_name=file_prefix+'.par', dir=self.dir, force=True)
# Copy the nested list to sort it.
par_chi2_vals_sort = deepcopy(par_chi2_vals)
# Then sort the value.
par_chi2_vals_sort.sort(key=lambda values: values[4])
# Collect the data structure, which is a list of list of strings.
data = []
for i, line in enumerate(par_chi2_vals):
line_sort = par_chi2_vals_sort[i]
# Convert values to strings.
line_str = ["%3.5f"%j for j in line]
line_sort_str = ["%3.5f"%j for j in line_sort]
# Convert the index from float to index.
line_str[0] = "%i" % line[0]
line_sort_str[0] = "%i" % line_sort[0]
# Merge the two lists and append to data.
data_list = line_str + line_sort_str
data.append(data_list)
# Make the headings.
headings = ['i'] + self.params + ['chi2']
headings += headings
# Add "_sort" to headings.
headings[5] = headings[5] + "_sort"
headings[6] = headings[6] + "_sort"
headings[7] = headings[7] + "_sort"
headings[8] = headings[8] + "_sort"
headings[9] = headings[9] + "_sort"
# Write the parameters and chi2 values to file.
write_data(out=par_file, headings=headings, data=data)
# Close the file.
par_file.close()
def run(input_path, output_path, number_of_partitions, number_of_iterations,
number_of_trials):
# Read partitioned input data
data = read_partitioned_data(input_path, number_of_iterations,
number_of_partitions)
# Define classification models and their corresponding parameters
models = {
'svm': {
'C': (int, (5, 15)),
'decision_function_shape': (tuple, ('ovo', 'ovr', None))
},
'random_forest': {
'max_features': (int, (5, 15)),
'class_weight': (tuple, ('balanced', 'balanced_subsample'))
}
}
# Initialise the grid search result list
results = []
# If the number of trials is set, use grid search.
if number_of_trials:
# Iterate trough each classification model defined.
for algorithm, parameter_model in models.items():
# Perform grid search and append the results to the complete result
# list
results += grid_search(data, algorithm, parameter_model,
number_of_trials)
# If the number of trials is not set, use regular classification.
else:
# Iterate through each algorithm defined.
for algorithm in models.keys():
# Perform classification and append the results to the complete
# result list
results.append(classify(data,
classifier_from_algorithm[algorithm]))
# Output the grid search results into the specified file
write_data(output_path, results)
def write(file=None, dir=None, force=False):
"""Write the J coupling data to file.
@keyword file: The file name or object to write to.
@type file: str or file object
@keyword dir: The name of the directory to place the file into (defaults to the current directory).
@type dir: str
@keyword force: A flag which if True will cause any pre-existing file to be overwritten.
@type force: bool
"""
# Check the pipe setup.
check_pipe_setup(sequence=True, j=True)
# Open the file for writing.
file = open_write_file(file, dir, force)
# Loop over the interatomic data containers and collect the data.
data = []
for interatom in interatomic_loop():
# Skip deselected containers.
if not interatom.select:
continue
# Skip containers with no J coupling.
if not hasattr(interatom, 'j_coupling'):
continue
# Append the spin data.
data.append([])
data[-1].append(interatom.spin_id1)
data[-1].append(interatom.spin_id2)
# The value.
data[-1].append(repr(interatom.j_coupling))
# The error.
if hasattr(interatom, 'j_coupling_err'):
data[-1].append(repr(interatom.j_coupling_err))
else:
data[-1].append(repr(None))
# Write out.
write_data(out=file, headings=["Spin_ID1", "Spin_ID2", "J coupling", "J coupling"], data=data)
def write(file=None, dir=None, force=False):
"""Write the J coupling data to file.
@keyword file: The file name or object to write to.
@type file: str or file object
@keyword dir: The name of the directory to place the file into (defaults to the current directory).
@type dir: str
@keyword force: A flag which if True will cause any pre-existing file to be overwritten.
@type force: bool
"""
# Check the pipe setup.
check_pipe_setup(sequence=True, j=True)
# Open the file for writing.
file = open_write_file(file, dir, force)
# Loop over the interatomic data containers and collect the data.
data = []
for interatom in interatomic_loop():
# Skip deselected containers.
if not interatom.select:
continue
# Skip containers with no J coupling.
if not hasattr(interatom, 'j_coupling'):
continue
# Append the spin data.
data.append([])
data[-1].append(interatom.spin_id1)
data[-1].append(interatom.spin_id2)
# The value.
data[-1].append(repr(interatom.j_coupling))
# The error.
if hasattr(interatom, 'j_coupling_err'):
data[-1].append(repr(interatom.j_coupling_err))
else:
data[-1].append(repr(None))
# Write out.
write_data(out=file, headings=["Spin_ID1", "Spin_ID2", "J coupling", "J coupling"], data=data)
def aic():
"""Calculate and store Akaike's Information Criterion (AIC) for each model."""
# Checks.
check_pipe()
# The specific analysis API object.
api = return_api()
# Calculate the chi2.
print(
"Calculating the chi-squared value for the current parameter values.")
api.calculate()
# Loop over the base models.
print("\nStoring the model statistics.")
for model_info in api.model_loop():
# Title printout.
api.print_model_title(model_info=model_info)
# Get the model statistics.
k, n, chi2 = api.model_statistics(model_info=model_info)
# Calculate the AIC value.
aic = chi2 + 2.0 * k
# The model container.
container = api.get_model_container(model_info=model_info)
# Store the statistics.
container.chi2 = chi2
container.num_params = k
container.aic = aic
# Statistics printout.
data = [["Chi-squared value:", "%20f" % chi2],
["Number of parameters (k):",
"%20i" % k],
["Akaike's Information Criterion (AIC):",
"%20f" % aic]]
write_data(out=sys.stdout, data=data)
def display(sort=False, rev=False):
"""Print the details of all the data pipes."""
# Acquire the pipe lock, and make sure it is finally released.
status.pipe_lock.acquire(sys._getframe().f_code.co_name)
try:
# Loop over the data pipes.
pipe_names = []
for pipe_name_i in ds:
pipe_names.append(pipe_name_i)
if sort:
pipe_names = sort_filenames(filenames=pipe_names, rev=rev)
data = []
for pipe_name in pipe_names:
# The current data pipe.
current = ''
if pipe_name == cdp_name():
current = '*'
# Store the data for the print out.
data.append([
repr(pipe_name),
get_type(pipe_name),
repr(get_bundle(pipe_name)), current
])
# Release the lock.
finally:
status.pipe_lock.release(sys._getframe().f_code.co_name)
# Print out.
write_data(
out=sys.stdout,
headings=["Data pipe name", "Data pipe type", "Bundle", "Current"],
data=data)
# Return data
return data
def aic():
"""Calculate and store Akaike's Information Criterion (AIC) for each model."""
# Checks.
check_pipe()
# The specific analysis API object.
api = return_api()
# Calculate the chi2.
print("Calculating the chi-squared value for the current parameter values.")
api.calculate()
# Loop over the base models.
print("\nStoring the model statistics.")
for model_info in api.model_loop():
# Title printout.
api.print_model_title(model_info=model_info)
# Get the model statistics.
k, n, chi2 = api.model_statistics(model_info=model_info)
# Calculate the AIC value.
aic = chi2 + 2.0*k
# The model container.
container = api.get_model_container(model_info=model_info)
# Store the statistics.
container.chi2 = chi2
container.num_params = k
container.aic = aic
# Statistics printout.
data = [
["Chi-squared value:", "%20f" % chi2],
["Number of parameters (k):", "%20i" % k],
["Akaike's Information Criterion (AIC):", "%20f" % aic]
]
write_data(out=sys.stdout, data=data)
def run(input_path, output_path, classes):
# Read the input data set from the specified input path
input_data = read_data(input_path)
# Change the list of classes to a set
classes = set(classes)
# Construct the output data set, filtering to only have the selected classes
output_data = {
'subjects': input_data['subjects'],
'areas': input_data['areas'],
'image_category': [],
'neural_responses': []
}
for i in range(len(input_data['image_category'])):
if input_data['image_category'][i] in classes:
for field in ['image_category', 'neural_responses']:
output_data[field].append(input_data[field][i])
# Write the output data set to the specified output path
write_data(output_path, output_data)
def display():
"""Print the details of all the data pipes."""
# Acquire the pipe lock, and make sure it is finally released.
status.pipe_lock.acquire(sys._getframe().f_code.co_name)
try:
# Loop over the data pipes.
data = []
for pipe_name in ds:
# The current data pipe.
current = ''
if pipe_name == cdp_name():
current = '*'
# Store the data for the print out.
data.append([repr(pipe_name), get_type(pipe_name), repr(get_bundle(pipe_name)), current])
# Release the lock.
finally:
status.pipe_lock.release(sys._getframe().f_code.co_name)
# Print out.
write_data(out=sys.stdout, headings=["Data pipe name", "Data pipe type", "Bundle", "Current"], data=data)
def model_statistics():
"""Calculate and store the model statistics."""
# Checks.
check_pipe()
# The specific analysis API object.
api = return_api()
# Calculate the chi2.
print("Calculating the chi-squared value for the current parameter values.")
api.calculate()
# Loop over the base models.
print("\nStoring the model statistics.")
for model_info in api.model_loop():
# Title printout.
api.print_model_title(model_info=model_info)
# Get the model statistics.
k, n, chi2 = api.model_statistics(model_info=model_info)
# The model container.
container = api.get_model_container(model_info=model_info)
# Store the values.
container.chi2 = chi2
container.num_params = k
container.num_data_points = n
# Statistics printout.
data = [
['Chi-squared value:', "%20f" % chi2],
['Number of parameters (k):', "%20i" % k],
['Number of data points (n):', "%20i" % n]
]
write_data(out=sys.stdout, data=data)
def model_statistics():
"""Calculate and store the model statistics."""
# Checks.
check_pipe()
# The specific analysis API object.
api = return_api()
# Calculate the chi2.
print(
"Calculating the chi-squared value for the current parameter values.")
api.calculate()
# Loop over the base models.
print("\nStoring the model statistics.")
for model_info in api.model_loop():
# Title printout.
api.print_model_title(model_info=model_info)
# Get the model statistics.
k, n, chi2 = api.model_statistics(model_info=model_info)
# The model container.
container = api.get_model_container(model_info=model_info)
# Store the values.
container.chi2 = chi2
container.num_params = k
container.num_data_points = n
# Statistics printout.
data = [['Chi-squared value:', "%20f" % chi2],
['Number of parameters (k):',
"%20i" % k], ['Number of data points (n):',
"%20i" % n]]
write_data(out=sys.stdout, data=data)
def run(raw_input_path, output_path_recall, output_path_precision,
output_path_f1, time_windows, frequency_bands):
# Convert time windows to integers
time_windows = [int(time_window) for time_window in time_windows]
# Initialise the integrated score data dictionaries
integrated_recall = {}
integrated_precision = {}
integrated_f1 = {}
for time_window in time_windows:
integrated_recall[time_window] = {}
integrated_precision[time_window] = {}
integrated_f1[time_window] = {}
for time_window in time_windows:
for frequency_band in frequency_bands:
integrated_recall[time_window][frequency_band] = None
integrated_precision[time_window][frequency_band] = None
integrated_f1[time_window][frequency_band] = None
# Read F1-scores from the input files into the integrated data dictionary
# Iterate through each time window and frequency band pair
for time_window in time_windows:
for frequency_band in frequency_bands:
# Construct the input file path
input_path = raw_input_path.replace('TIMEWINDOW', str(time_window))\
.replace('FREQUENCYBAND', frequency_band)
# Read the input file
input_data = read_data(input_path)
# Add the F1-score received from the data into the integrated data
# dictionary
integrated_recall[time_window][
frequency_band] = input_data.average_recall()
integrated_precision[time_window][
frequency_band] = input_data.average_precision()
integrated_f1[time_window][frequency_band] = input_data.average_f1(
)
# Output the integrated scores into the specified files
write_data(output_path_recall, integrated_recall)
write_data(output_path_precision, integrated_precision)
write_data(output_path_f1, integrated_f1)
def run(input_path, output_path, cv_amount, use_even_distribution):
# Read the data set
data = read_data(input_path)
# Find the number of images in the data set
number_of_images = len(data['image_category'])
# Find all image classes in the data set
classes = sorted(set(data['image_category']))
# Initialise the list of partitioned indices
partitioned_indices = [[] for i in range(cv_amount)]
# If even distribution is set to be used, partition data within each class
# separately and merge the resulting partitions into the partitioned
# indices list, so the image class distribution in each partition would be
# roughly the same.
if use_even_distribution:
# Construct a list of image indices corresponding to each image class
indices = {}
for image_class in classes:
indices[image_class] = []
for i in range(number_of_images):
indices[data['image_category'][i]].append(i)
# Randomly split each of these lists into k nearly equal parts, and
# merge them by partitions
for image_class in classes:
# Partition the indices list for the current image class into k
# nearly equal parts
partitions_list = partition_list(indices[image_class], cv_amount)
# Shuffle the partition list to ensure that cumulative partitions
# after merging by partitions are roughly of equal size
shuffle(partitions_list)
# Merge the partitioned indices list for the current image class
# into the general partitioned indices list by partitions
for i in range(cv_amount):
partitioned_indices[i] += partitions_list[i]
# If even distribution is not set to be used, partition data randomly.
else:
# Partition the indices list into k nearly equal parts
partitioned_indices = partition_list(range(number_of_images),
cv_amount)
# Sort all of the partitions
for partition in partitioned_indices:
partition.sort()
# Partition data
partitions = []
for i in range(cv_amount):
partitions.append({
'subjects':
data['subjects'],
'areas':
data['areas'],
'image_category':
[data['image_category'][j] for j in partitioned_indices[i]],
'neural_responses':
[data['neural_responses'][j] for j in partitioned_indices[i]]
})
# Save partitioned data
for i in range(cv_amount):
write_data(add_suffix_to_path(output_path, '-', i + 1), partitions[i])
#print(k_stat, n_stat, chi2, "point is %s=%3.3f, %s=%3.3f"% (params[0], values[0], params[1], values[1]))
# Progress incrementation and printout.
percent = percent + percent_inc
print(
"%-10s%8.3f%-8s%-8g" %
("Progress:", percent, "%, " + repr(values) + ", f(x): ", chi2))
# Append to data.
data.append(["%3.3f" % values[0], "%3.3f" % values[1], "%3.3f" % chi2])
# Save all values of chi2. To help find reasonale level for the Innermost, Inner, Middle and Outer Isosurface.
all_chi.append(chi2)
# Increment the value of the second parameter.
values[1] = values[1] + step_size[1]
# Increment the value of the first parameter.
values[0] = values[0] + step_size[0]
print("\nMin cluster point %s=%3.3f, %s=%3.3f, with chi2=%3.3f" %
(params[0], pcm[0], params[1], pcm[1], pre_chi2))
# Open file
file_name = '1_create_surface_data_S65_dw_r2a_FT128.txt'
surface_file = open_write_file(file_name=file_name, dir=None, force=True)
write_data(out=surface_file, headings=headings, data=data)
# Close file
surface_file.close()
def read(file=None, dir=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, verbose=True):
"""Read the peak intensity data.
@keyword file: The name of the file containing the peak intensities.
@type file: str
@keyword dir: The directory where the file is located.
@type dir: str
@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.
@type mol_name_col: int or None
@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.
@type res_name_col: int or None
@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.
@type res_num_col: int or None
@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.
@type spin_name_col: int or None
@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.
@type spin_num_col: int or None
@keyword sep: The column separator which, if None, defaults to whitespace.
@type sep: str or None
@keyword spin_id: The spin ID string used to restrict data loading to a subset of all spins. If 'auto' is provided for a NMRPipe seriesTab formatted file, the ID's are auto generated in form of Z_Ai.
@type spin_id: None or str
@keyword verbose: A flag which if True will cause all chemical shift data loaded to be printed out.
@type verbose: bool
"""
# Test if the current data pipe exists.
check_pipe()
# Test if sequence data is loaded.
if not exists_mol_res_spin_data():
raise RelaxNoSequenceError
# Check the file name.
if file == None:
raise RelaxError("The file name must be supplied.")
# Read the peak list data.
peak_list = read_peak_list(file=file, dir=dir, 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, sep=sep, spin_id=spin_id)
# Loop over the assignments.
data = []
data_flag = False
for assign in peak_list:
# Loop over the dimensions of the peak list.
for i in range(peak_list.dimensionality):
# Generate the spin_id.
spin_id = generate_spin_id_unique(res_num=assign.res_nums[i], spin_name=assign.spin_names[i])
# Get the spin container.
spin = return_spin(spin_id)
if not spin:
warn(RelaxNoSpinWarning(spin_id))
continue
# Skip deselected spins.
if not spin.select:
continue
# Store the shift.
spin.chemical_shift = assign.shifts[i]
# Switch the flag.
data_flag = True
# Append the data for printing out.
data.append([spin_id, repr(spin.chemical_shift)])
# No data.
if not data_flag:
raise RelaxError("No chemical shifts could be loaded from the peak list")
# Print out.
if verbose:
print("\nThe following chemical shifts have been loaded into the relax data store:\n")
write_data(out=sys.stdout, headings=["Spin_ID", "Chemical shift"], data=data)
def read_dist(file=None, dir=None, unit='meter', spin_id1_col=None, spin_id2_col=None, data_col=None, sep=None):
"""Set up the magnetic dipole-dipole interaction.
@keyword file: The name of the file to open.
@type file: str
@keyword dir: The directory containing the file (defaults to the current directory if None).
@type dir: str or None
@keyword unit: The measurement unit. This can be either 'meter' or 'Angstrom'.
@type unit: str
@keyword spin_id1_col: The column containing the spin ID strings of the first spin.
@type spin_id1_col: int
@keyword spin_id2_col: The column containing the spin ID strings of the second spin.
@type spin_id2_col: int
@keyword data_col: The column containing the averaged distances in meters.
@type data_col: int or None
@keyword sep: The column separator which, if None, defaults to whitespace.
@type sep: str or None
"""
# Check the units.
if unit not in ['meter', 'Angstrom']:
raise RelaxError("The measurement unit of '%s' must be one of 'meter' or 'Angstrom'." % unit)
# Test if the current data pipe exists.
pipes.test()
# Test if sequence data exists.
if not exists_mol_res_spin_data():
raise RelaxNoSequenceError
# Extract the data from the file, and clean it up.
file_data = extract_data(file, dir, sep=sep)
file_data = strip(file_data, comments=True)
# Loop over the RDC data.
data = []
for line in file_data:
# Invalid columns.
if spin_id1_col > len(line):
warn(RelaxWarning("The data %s is invalid, no first spin ID column can be found." % line))
continue
if spin_id2_col > len(line):
warn(RelaxWarning("The data %s is invalid, no second spin ID column can be found." % line))
continue
if data_col and data_col > len(line):
warn(RelaxWarning("The data %s is invalid, no data column can be found." % line))
continue
# Unpack.
spin_id1 = line[spin_id1_col-1]
spin_id2 = line[spin_id2_col-1]
ave_dist = None
if data_col:
ave_dist = line[data_col-1]
# Convert and check the value.
if ave_dist != None:
try:
ave_dist = float(ave_dist)
except ValueError:
warn(RelaxWarning("The averaged distance of '%s' from the line %s is invalid." % (ave_dist, line)))
continue
# Unit conversion.
if unit == 'Angstrom':
ave_dist = ave_dist * 1e-10
# Get the interatomic data container.
interatom = return_interatom(spin_id1, spin_id2)
# No container found, so create it.
if interatom == None:
interatom = create_interatom(spin_id1=spin_id1, spin_id2=spin_id2, verbose=True)
# Store the averaged distance.
interatom.r = ave_dist
# Store the data for the printout.
data.append([repr(interatom.spin_id1), repr(interatom.spin_id2), repr(ave_dist)])
# No data, so fail!
if not len(data):
raise RelaxError("No data could be extracted from the file.")
# Print out.
print("The following averaged distances have been read:\n")
write_data(out=sys.stdout, headings=["Spin_ID_1", "Spin_ID_2", "Ave_distance(meters)"], data=data)
def pack_data(ri_id, ri_type, frq, values, errors, spin_ids=None, mol_names=None, res_nums=None, res_names=None, spin_nums=None, spin_names=None, spin_id=None, gen_seq=False, verbose=True):
"""Pack the relaxation data into the data pipe and spin containers.
The values, errors, and spin_ids arguments must be lists of equal length or None. Each element i corresponds to a unique spin.
@param ri_id: The relaxation data ID string.
@type ri_id: str
@param ri_type: The relaxation data type, ie 'R1', 'R2', or 'NOE'.
@type ri_type: str
@param frq: The spectrometer proton frequency in Hz.
@type frq: float
@keyword values: The relaxation data for each spin.
@type values: None or list of float or float array
@keyword errors: The relaxation data errors for each spin.
@type errors: None or list of float or float array
@keyword spin_ids: The list of spin ID strings. If the other spin identifiers are given, i.e. mol_names, res_nums, res_names, spin_nums, and/or spin_names, then this argument is not necessary.
@type spin_ids: None or list of str
@keyword mol_names: The list of molecule names used for creating the spin IDs (if not given) or for generating the sequence data.
@type mol_names: None or list of str
@keyword res_nums: The list of residue numbers used for creating the spin IDs (if not given) or for generating the sequence data.
@type res_nums: None or list of str
@keyword res_names: The list of residue names used for creating the spin IDs (if not given) or for generating the sequence data.
@type res_names: None or list of str
@keyword spin_nums: The list of spin numbers used for creating the spin IDs (if not given) or for generating the sequence data.
@type spin_nums: None or list of str
@keyword spin_names: The list of spin names used for creating the spin IDs (if not given) or for generating the sequence data.
@type spin_names: None or list of str
@keyword gen_seq: A flag which if True will cause the molecule, residue, and spin sequence data to be generated.
@type gen_seq: bool
@keyword verbose: A flag which if True will cause all relaxation data loaded to be printed out.
@type verbose: bool
"""
# The number of spins.
N = len(values)
# Test the data.
if errors != None and len(errors) != N:
raise RelaxError("The length of the errors arg (%s) does not match that of the value arg (%s)." % (len(errors), N))
if spin_ids and len(spin_ids) != N:
raise RelaxError("The length of the spin ID strings arg (%s) does not match that of the value arg (%s)." % (len(mol_names), N))
if mol_names and len(mol_names) != N:
raise RelaxError("The length of the molecule names arg (%s) does not match that of the value arg (%s)." % (len(mol_names), N))
if res_nums and len(res_nums) != N:
raise RelaxError("The length of the residue numbers arg (%s) does not match that of the value arg (%s)." % (len(res_nums), N))
if res_names and len(res_names) != N:
raise RelaxError("The length of the residue names arg (%s) does not match that of the value arg (%s)." % (len(res_names), N))
if spin_nums and len(spin_nums) != N:
raise RelaxError("The length of the spin numbers arg (%s) does not match that of the value arg (%s)." % (len(spin_nums), N))
if spin_names and len(spin_names) != N:
raise RelaxError("The length of the spin names arg (%s) does not match that of the value arg (%s)." % (len(spin_names), N))
# Generate some empty lists.
if not mol_names:
mol_names = [None] * N
if not res_nums:
res_nums = [None] * N
if not res_names:
res_names = [None] * N
if not spin_nums:
spin_nums = [None] * N
if not spin_names:
spin_names = [None] * N
if errors == None:
errors = [None] * N
# Generate the spin IDs.
if not spin_ids:
spin_ids = []
for i in range(N):
spin_ids.append(generate_spin_id_unique(spin_num=spin_nums[i], spin_name=spin_names[i], res_num=res_nums[i], res_name=res_names[i], mol_name=mol_names[i]))
# Initialise the global data for the current pipe if necessary.
if not hasattr(cdp, 'ri_type'):
cdp.ri_type = {}
if not hasattr(cdp, 'ri_ids'):
cdp.ri_ids = []
# Set the spectrometer frequency.
set_frequency(id=ri_id, frq=frq)
# Update the global data.
cdp.ri_ids.append(ri_id)
cdp.ri_type[ri_id] = ri_type
# The selection object.
select_obj = None
if spin_id:
select_obj = Selection(spin_id)
# Loop over the spin data.
data = []
for i in range(N):
# Get the corresponding spin container.
match_mol_names, match_res_nums, match_res_names, spins = return_spin_from_selection(spin_ids[i], full_info=True, multi=True)
if spins in [None, []]:
raise RelaxNoSpinError(spin_ids[i])
# Remove non-matching spins.
if select_obj:
new_spins = []
new_mol_names = []
new_res_nums = []
new_res_names = []
new_ids = []
for j in range(len(spins)):
if select_obj.contains_spin(spin_num=spins[j].num, spin_name=spins[j].name, res_num=match_res_nums[j], res_name=match_res_names[j], mol=match_mol_names[j]):
new_spins.append(spins[j])
new_mol_names.append(match_mol_names[j])
new_res_nums.append(match_res_nums[j])
new_res_names.append(match_res_names[j])
new_ids.append(generate_spin_id_unique(mol_name=mol_names[i], res_num=res_nums[i], res_name=res_names[i], spin_num=spins[j].num, spin_name=spins[j].name))
new_id = new_ids[0]
# Aliases for normal operation.
else:
new_spins = spins
new_mol_names = match_mol_names
new_res_nums = match_res_nums
new_res_names = match_res_names
new_id = spin_ids[i]
new_ids = None
# Check that only a singe spin is present.
if len(new_spins) > 1:
if new_ids:
raise RelaxMultiSpinIDError(spin_ids[i], new_ids)
else:
raise RelaxMultiSpinIDError(spin_ids[i], new_ids)
if len(new_spins) == 0:
raise RelaxNoSpinError(spin_ids[i])
# Loop over the spins.
for j in range(len(new_spins)):
# No match to the selection.
if select_obj and not select_obj.contains_spin(spin_num=new_spins[j].num, spin_name=new_spins[j].name, res_num=new_res_nums[j], res_name=new_res_names[j], mol=new_mol_names[j]):
continue
# Initialise the spin data if necessary.
if not hasattr(new_spins[j], 'ri_data') or new_spins[j].ri_data == None:
new_spins[j].ri_data = {}
if not hasattr(new_spins[j], 'ri_data_err') or new_spins[j].ri_data_err == None:
new_spins[j].ri_data_err = {}
# Update all data structures.
new_spins[j].ri_data[ri_id] = values[i]
new_spins[j].ri_data_err[ri_id] = errors[i]
# Append the data for printing out.
data.append([new_id, repr(values[i]), repr(errors[i])])
# Print out.
if verbose:
print("\nThe following %s MHz %s relaxation data with the ID '%s' has been loaded into the relax data store:\n" % (frq/1e6, ri_type, ri_id))
write_data(out=sys.stdout, headings=["Spin_ID", "Value", "Error"], data=data)
def select(method=None, modsel_pipe=None, bundle=None, pipes=None):
"""Model selection function.
@keyword method: The model selection method. This can currently be one of:
- 'AIC', Akaike's Information Criteria.
- 'AICc', Small sample size corrected AIC.
- 'BIC', Bayesian or Schwarz Information Criteria.
- 'CV', Single-item-out cross-validation.
None of the other model selection techniques are currently supported.
@type method: str
@keyword modsel_pipe: The name of the new data pipe to be created by copying of the selected data pipe.
@type modsel_pipe: str
@keyword bundle: The optional data pipe bundle to associate the newly created pipe with.
@type bundle: str or None
@keyword pipes: A list of the data pipes to use in the model selection.
@type pipes: list of str
"""
# Test if the pipe already exists.
if has_pipe(modsel_pipe):
raise RelaxPipeError(modsel_pipe)
# Use all pipes.
if pipes == None:
# Get all data pipe names from the relax data store.
pipes = pipe_names()
# Select the model selection technique.
if method == 'AIC':
print("AIC model selection.")
formula = aic
elif method == 'AICc':
print("AICc model selection.")
formula = aicc
elif method == 'BIC':
print("BIC model selection.")
formula = bic
elif method == 'CV':
print("CV model selection.")
raise RelaxError("The model selection technique " + repr(method) + " is not currently supported.")
else:
raise RelaxError("The model selection technique " + repr(method) + " is not currently supported.")
# No pipes.
if len(pipes) == 0:
raise RelaxError("No data pipes are available for use in model selection.")
# Initialise.
function_type = {}
model_loop = {}
model_type = {}
duplicate_data = {}
model_statistics = {}
skip_function = {}
modsel_pipe_exists = False
# Cross validation setup.
if isinstance(pipes[0], list):
# No pipes.
if len(pipes[0]) == 0:
raise RelaxError("No pipes are available for use in model selection in the array " + repr(pipes[0]) + ".")
# Loop over the data pipes.
for i in range(len(pipes)):
for j in range(len(pipes[i])):
# Specific functions.
model_loop[pipes[i][j]] = get_specific_fn('model_loop', get_type(pipes[i][j]))
model_type[pipes[i][j]] = get_specific_fn('model_type', get_type(pipes[i][j]))
duplicate_data[pipes[i][j]] = get_specific_fn('duplicate_data', get_type(pipes[i][j]))
model_statistics[pipes[i][j]] = get_specific_fn('model_stats', get_type(pipes[i][j]))
skip_function[pipes[i][j]] = get_specific_fn('skip_function', get_type(pipes[i][j]))
# The model loop should be the same for all data pipes!
for i in range(len(pipes)):
for j in range(len(pipes[i])):
if model_loop[pipes[0][j]] != model_loop[pipes[i][j]]:
raise RelaxError("The models for each data pipes should be the same.")
model_loop = model_loop[pipes[0][0]]
# The model description.
model_desc = get_specific_fn('model_desc', get_type(pipes[0]))
# Global vs. local models.
global_flag = False
for i in range(len(pipes)):
for j in range(len(pipes[i])):
if model_type[pipes[i][j]]() == 'global':
global_flag = True
# All other model selection setup.
else:
# Loop over the data pipes.
for i in range(len(pipes)):
# Specific functions.
model_loop[pipes[i]] = get_specific_fn('model_loop', get_type(pipes[i]))
model_type[pipes[i]] = get_specific_fn('model_type', get_type(pipes[i]))
duplicate_data[pipes[i]] = get_specific_fn('duplicate_data', get_type(pipes[i]))
model_statistics[pipes[i]] = get_specific_fn('model_stats', get_type(pipes[i]))
skip_function[pipes[i]] = get_specific_fn('skip_function', get_type(pipes[i]))
model_loop = model_loop[pipes[0]]
# The model description.
model_desc = get_specific_fn('model_desc', get_type(pipes[0]))
# Global vs. local models.
global_flag = False
for j in range(len(pipes)):
if model_type[pipes[j]]() == 'global':
global_flag = True
# Loop over the base models.
for model_info in model_loop():
# Print out.
print("\n")
desc = model_desc(model_info)
if desc:
print(desc)
# Initial model.
best_model = None
best_crit = 1e300
data = []
# Loop over the pipes.
for j in range(len(pipes)):
# Single-item-out cross validation.
if method == 'CV':
# Sum of chi-squared values.
sum_crit = 0.0
# Loop over the validation samples and sum the chi-squared values.
for k in range(len(pipes[j])):
# Alias the data pipe name.
pipe = pipes[j][k]
# Switch to this pipe.
switch(pipe)
# Skip function.
if skip_function[pipe](model_info):
continue
# Get the model statistics.
k, n, chi2 = model_statistics[pipe](model_info)
# Missing data sets.
if k == None or n == None or chi2 == None:
continue
# Chi2 sum.
sum_crit = sum_crit + chi2
# Cross-validation criterion (average chi-squared value).
crit = sum_crit / float(len(pipes[j]))
# Other model selection methods.
else:
# Reassign the pipe.
pipe = pipes[j]
# Switch to this pipe.
switch(pipe)
# Skip function.
if skip_function[pipe](model_info):
continue
# Get the model statistics.
k, n, chi2 = model_statistics[pipe](model_info, global_stats=global_flag)
# Missing data sets.
if k == None or n == None or chi2 == None:
continue
# Calculate the criterion value.
crit = formula(chi2, float(k), float(n))
# Store the values for a later printout.
data.append([pipe, repr(k), repr(n), "%.5f" % chi2, "%.5f" % crit])
# Select model.
if crit < best_crit:
best_model = pipe
best_crit = crit
# Write out the table.
write_data(out=sys.stdout, headings=["Data pipe", "Num_params_(k)", "Num_data_sets_(n)", "Chi2", "Criterion"], data=data)
# Duplicate the data from the 'best_model' to the model selection data pipe.
if best_model != None:
# Print out of selected model.
print("The model from the data pipe " + repr(best_model) + " has been selected.")
# Switch to the selected data pipe.
switch(best_model)
# Duplicate.
duplicate_data[best_model](best_model, modsel_pipe, model_info, global_stats=global_flag, verbose=False)
# Model selection pipe now exists.
modsel_pipe_exists = True
# No model selected.
else:
# Print out of selected model.
print("No model has been selected.")
# Switch to the model selection pipe.
if modsel_pipe_exists:
switch(modsel_pipe)
# Bundle the data pipe.
if bundle:
pipe_control.pipes.bundle(bundle=bundle, pipe=modsel_pipe)
def signal_noise_ratio(verbose=True):
"""Calculate the signal to noise ratio per spin.
@keyword verbose: A flag which if True will print additional information out.
@type verbose: bool
"""
# Tests.
check_pipe()
check_mol_res_spin_data()
# Test if spectra have been loaded.
if not hasattr(cdp, 'spectrum_ids'):
raise RelaxError("No spectra have been loaded.")
# Possible print.
if verbose:
print("\nThe following signal to noise ratios has been calculated:\n")
# Set the spin specific signal to noise ratio.
for spin, spin_id in spin_loop(return_id=True):
# Skip deselected spins.
if not spin.select:
continue
# Skip spins missing intensity data.
if not hasattr(spin, 'peak_intensity'):
continue
# Test if error analysis has been performed.
if not hasattr(spin, 'peak_intensity_err'):
raise RelaxError("Intensity error analysis has not been performed. Please see spectrum.error_analysis().")
# If necessary, create the dictionary.
if not hasattr(spin, 'sn_ratio'):
spin.sn_ratio = {}
# Loop over the ID.
ids = []
for id in spin.peak_intensity:
# Append the ID to the list.
ids.append(id)
# Calculate the sn_ratio.
pint = float(spin.peak_intensity[id])
pint_err = float(spin.peak_intensity_err[id])
sn_ratio = pint / pint_err
# Assign the sn_ratio.
spin.sn_ratio[id] = sn_ratio
# Sort the ids alphanumeric.
ids = sort_filenames(filenames=ids, rev=False)
# Collect the data under sorted ids.
data_i = []
for id in ids:
# Get the values.
pint = spin.peak_intensity[id]
pint_err = spin.peak_intensity_err[id]
sn_ratio = spin.sn_ratio[id]
# Store the data.
data_i.append([id, repr(pint), repr(pint_err), repr(sn_ratio)])
if verbose:
section(file=sys.stdout, text="Signal to noise ratio for spin ID '%s'"%spin_id, prespace=1)
write_data(out=sys.stdout, headings=["Spectrum ID", "Signal", "Noise", "S/N"], data=data_i)
def pack_data(ri_id,
ri_type,
frq,
values,
errors,
spin_ids=None,
mol_names=None,
res_nums=None,
res_names=None,
spin_nums=None,
spin_names=None,
spin_id=None,
gen_seq=False,
verbose=True):
"""Pack the relaxation data into the data pipe and spin containers.
The values, errors, and spin_ids arguments must be lists of equal length or None. Each element i corresponds to a unique spin.
@param ri_id: The relaxation data ID string.
@type ri_id: str
@param ri_type: The relaxation data type, ie 'R1', 'R2', or 'NOE'.
@type ri_type: str
@param frq: The spectrometer proton frequency in Hz.
@type frq: float
@keyword values: The relaxation data for each spin.
@type values: None or list of float or float array
@keyword errors: The relaxation data errors for each spin.
@type errors: None or list of float or float array
@keyword spin_ids: The list of spin ID strings. If the other spin identifiers are given, i.e. mol_names, res_nums, res_names, spin_nums, and/or spin_names, then this argument is not necessary.
@type spin_ids: None or list of str
@keyword mol_names: The list of molecule names used for creating the spin IDs (if not given) or for generating the sequence data.
@type mol_names: None or list of str
@keyword res_nums: The list of residue numbers used for creating the spin IDs (if not given) or for generating the sequence data.
@type res_nums: None or list of str
@keyword res_names: The list of residue names used for creating the spin IDs (if not given) or for generating the sequence data.
@type res_names: None or list of str
@keyword spin_nums: The list of spin numbers used for creating the spin IDs (if not given) or for generating the sequence data.
@type spin_nums: None or list of str
@keyword spin_names: The list of spin names used for creating the spin IDs (if not given) or for generating the sequence data.
@type spin_names: None or list of str
@keyword gen_seq: A flag which if True will cause the molecule, residue, and spin sequence data to be generated.
@type gen_seq: bool
@keyword verbose: A flag which if True will cause all relaxation data loaded to be printed out.
@type verbose: bool
"""
# The number of spins.
N = len(values)
# Test the data.
if errors != None and len(errors) != N:
raise RelaxError(
"The length of the errors arg (%s) does not match that of the value arg (%s)."
% (len(errors), N))
if spin_ids and len(spin_ids) != N:
raise RelaxError(
"The length of the spin ID strings arg (%s) does not match that of the value arg (%s)."
% (len(mol_names), N))
if mol_names and len(mol_names) != N:
raise RelaxError(
"The length of the molecule names arg (%s) does not match that of the value arg (%s)."
% (len(mol_names), N))
if res_nums and len(res_nums) != N:
raise RelaxError(
"The length of the residue numbers arg (%s) does not match that of the value arg (%s)."
% (len(res_nums), N))
if res_names and len(res_names) != N:
raise RelaxError(
"The length of the residue names arg (%s) does not match that of the value arg (%s)."
% (len(res_names), N))
if spin_nums and len(spin_nums) != N:
raise RelaxError(
"The length of the spin numbers arg (%s) does not match that of the value arg (%s)."
% (len(spin_nums), N))
if spin_names and len(spin_names) != N:
raise RelaxError(
"The length of the spin names arg (%s) does not match that of the value arg (%s)."
% (len(spin_names), N))
# Generate some empty lists.
if not mol_names:
mol_names = [None] * N
if not res_nums:
res_nums = [None] * N
if not res_names:
res_names = [None] * N
if not spin_nums:
spin_nums = [None] * N
if not spin_names:
spin_names = [None] * N
if errors == None:
errors = [None] * N
# Generate the spin IDs.
if not spin_ids:
spin_ids = []
for i in range(N):
spin_ids.append(
generate_spin_id_unique(spin_num=spin_nums[i],
spin_name=spin_names[i],
res_num=res_nums[i],
res_name=res_names[i],
mol_name=mol_names[i]))
# Initialise the global data for the current pipe if necessary.
if not hasattr(cdp, 'ri_type'):
cdp.ri_type = {}
if not hasattr(cdp, 'ri_ids'):
cdp.ri_ids = []
# Set the spectrometer frequency.
set_frequency(id=ri_id, frq=frq)
# Update the global data.
cdp.ri_ids.append(ri_id)
cdp.ri_type[ri_id] = ri_type
# The selection object.
select_obj = None
if spin_id:
select_obj = Selection(spin_id)
# Loop over the spin data.
data = []
for i in range(N):
# A selection union.
select_id = spin_ids[i]
if spin_id != None:
select_id = "%s&%s" % (select_id, spin_id)
# Get the corresponding spin container.
match_mol_names, match_res_nums, match_res_names, spins = return_spin_from_selection(
selection=select_id, full_info=True, multi=True)
# No spin.
if len(spins) == 0:
continue
# Check that multiple spins are not present.
if len(spins) > 1:
# Generate the list of spin IDs.
new_ids = []
for j in range(len(spins)):
new_ids.append(
generate_spin_id_unique(mol_name=match_mol_names[j],
res_num=match_res_nums[j],
res_name=match_res_names[j],
spin_num=spins[j].num,
spin_name=spins[j].name))
# Raise the error.
raise RelaxMultiSpinIDError(spin_ids[i], new_ids)
# Check that at least one spin is present.
if len(spins) == 0:
raise RelaxNoSpinError(spin_ids[i])
# Loop over the spins.
for j in range(len(spins)):
# No match to the selection.
if select_obj and not select_obj.contains_spin(
spin_num=spins[j].num,
spin_name=spins[j].name,
res_num=res_nums[j],
res_name=res_names[j],
mol=mol_names[j]):
continue
# Initialise the spin data if necessary.
if not hasattr(spins[j], 'ri_data') or spins[j].ri_data == None:
spins[j].ri_data = {}
if not hasattr(spins[j],
'ri_data_err') or spins[j].ri_data_err == None:
spins[j].ri_data_err = {}
# Update all data structures.
spins[j].ri_data[ri_id] = values[i]
spins[j].ri_data_err[ri_id] = errors[i]
# Append the data for printing out.
data.append([spin_ids[i], repr(values[i]), repr(errors[i])])
# Print out.
if verbose:
print(
"\nThe following %s MHz %s relaxation data with the ID '%s' has been loaded into the relax data store:\n"
% (frq / 1e6, ri_type, ri_id))
write_data(out=sys.stdout,
headings=["Spin_ID", "Value", "Error"],
data=data)
def define(spin_id1=None, spin_id2=None, pipe=None, direct_bond=False, spin_selection=False, verbose=True):
"""Set up the magnetic dipole-dipole interaction.
@keyword spin_id1: The spin identifier string of the first spin of the pair.
@type spin_id1: str
@keyword spin_id2: The spin identifier string of the second spin of the pair.
@type spin_id2: str
@param pipe: The data pipe to operate on. Defaults to the current data pipe.
@type pipe: str
@keyword direct_bond: A flag specifying if the two spins are directly bonded.
@type direct_bond: bool
@keyword spin_selection: Define the interatomic data container selection based on the spin selection. If either spin is deselected, the interatomic container will also be deselected. Otherwise the container will be selected.
@type spin_selection: bool
@keyword verbose: A flag which if True will result in printouts of the created interatomoic data containers.
@type verbose: bool
"""
# The data pipe.
if pipe == None:
pipe = pipes.cdp_name()
# Get the data pipe.
dp = pipes.get_pipe(pipe)
# Initialise the spin ID pairs list.
ids = []
spin_selections = []
# Use the structural data to find connected atoms.
if hasattr(dp, 'structure'):
# The selection objects.
selection1 = cdp.structure.selection(atom_id=spin_id1)
selection2 = cdp.structure.selection(atom_id=spin_id2)
# Loop over the atoms of the first spin selection.
for mol_name1, res_num1, res_name1, atom_num1, atom_name1, mol_index1, atom_index1 in dp.structure.atom_loop(selection=selection1, model_num=1, mol_name_flag=True, res_num_flag=True, res_name_flag=True, atom_num_flag=True, atom_name_flag=True, mol_index_flag=True, index_flag=True):
# Generate the first spin ID.
id1 = generate_spin_id_unique(pipe_cont=dp, mol_name=mol_name1, res_num=res_num1, res_name=res_name1, spin_num=atom_num1, spin_name=atom_name1)
# Do the spin exist?
spin1 = return_spin(id1)
if not spin1:
continue
# Loop over the atoms of the second spin selection.
for mol_name2, res_num2, res_name2, atom_num2, atom_name2, mol_index2, atom_index2 in dp.structure.atom_loop(selection=selection2, model_num=1, mol_name_flag=True, res_num_flag=True, res_name_flag=True, atom_num_flag=True, atom_name_flag=True, mol_index_flag=True, index_flag=True):
# Directly bonded atoms.
if direct_bond:
# Different molecules.
if mol_name1 != mol_name2:
continue
# Skip non-bonded atom pairs.
if not dp.structure.are_bonded_index(mol_index1=mol_index1, atom_index1=atom_index1, mol_index2=mol_index2, atom_index2=atom_index2):
continue
# Generate the second spin ID.
id2 = generate_spin_id_unique(pipe_cont=dp, mol_name=mol_name2, res_num=res_num2, res_name=res_name2, spin_num=atom_num2, spin_name=atom_name2)
# Do the spin exist?
spin2 = return_spin(id2)
if not spin2:
continue
# Store the IDs for the printout.
ids.append([id1, id2])
spin_selections.append([spin1.select, spin2.select])
# No structural data present or the spin IDs are not in the structural data, so use spin loops and some basic rules.
if ids == []:
for spin1, mol_name1, res_num1, res_name1, id1 in spin_loop(spin_id1, pipe=pipe, full_info=True, return_id=True):
for spin2, mol_name2, res_num2, res_name2, id2 in spin_loop(spin_id2, pipe=pipe, full_info=True, return_id=True):
# Directly bonded atoms.
if direct_bond:
# Different molecules.
if mol_name1 != mol_name2:
continue
# No element info.
if not hasattr(spin1, 'element'):
raise RelaxError("The spin '%s' does not have the element type set." % id1)
if not hasattr(spin2, 'element'):
raise RelaxError("The spin '%s' does not have the element type set." % id2)
# Backbone NH and CH pairs.
pair = False
if (spin1.element == 'N' and spin2.element == 'H') or (spin2.element == 'N' and spin1.element == 'H'):
pair = True
elif (spin1.element == 'C' and spin2.element == 'H') or (spin2.element == 'C' and spin1.element == 'H'):
pair = True
# Same residue, so skip.
if pair and res_num1 != None and res_num1 != res_num2:
continue
elif pair and res_num1 == None and res_name1 != res_name2:
continue
# Store the IDs for the printout.
ids.append([id1, id2])
spin_selections.append([spin1.select, spin2.select])
# No matches, so fail!
if not len(ids):
# Find the problem.
count1 = 0
count2 = 0
for spin in spin_loop(spin_id1):
count1 += 1
for spin in spin_loop(spin_id2):
count2 += 1
# Report the problem.
if count1 == 0 and count2 == 0:
raise RelaxError("Neither spin IDs '%s' and '%s' match any spins." % (spin_id1, spin_id2))
elif count1 == 0:
raise RelaxError("The spin ID '%s' matches no spins." % spin_id1)
elif count2 == 0:
raise RelaxError("The spin ID '%s' matches no spins." % spin_id2)
else:
raise RelaxError("Unknown error.")
# Define the interaction.
for i in range(len(ids)):
# Unpack.
id1, id2 = ids[i]
# Get the interatomic data object, if it exists.
interatom = return_interatom(id1, id2, pipe=pipe)
# Create the container if needed.
if interatom == None:
interatom = create_interatom(spin_id1=id1, spin_id2=id2, pipe=pipe)
# Check that this has not already been set up.
if interatom.dipole_pair:
raise RelaxError("The magnetic dipole-dipole interaction already exists between the spins '%s' and '%s'." % (id1, id2))
# Set a flag indicating that a dipole-dipole interaction is present.
interatom.dipole_pair = True
# Set the selection.
if spin_selection:
interatom.select = False
if spin_selections[i][0] and spin_selections[i][1]:
interatom.select = True
# Printout.
if verbose:
# Conversion.
for i in range(len(ids)):
ids[i][0] = repr(ids[i][0])
ids[i][1] = repr(ids[i][1])
# The printout.
print("Interatomic interactions are now defined for the following spins:\n")
write_data(out=sys.stdout, headings=["Spin_ID_1", "Spin_ID_2"], data=ids)
def read(file=None, dir=None, spectrum_id=None, dim=1, int_col=None, int_method=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, ncproc=None, verbose=True):
"""Read the peak intensity data.
@keyword file: The name of the file(s) containing the peak intensities.
@type file: str or list of str
@keyword dir: The directory where the file is located.
@type dir: str
@keyword spectrum_id: The spectrum identification string.
@type spectrum_id: str or list of str
@keyword dim: The dimension of the peak list to associate the data with.
@type dim: int
@keyword int_col: The column containing the peak intensity data (used by the generic intensity file format).
@type int_col: int or list of int
@keyword int_method: The integration method, one of 'height', 'point sum' or 'other'.
@type int_method: str
@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.
@type mol_name_col: int or None
@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.
@type res_name_col: int or None
@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.
@type res_num_col: int or None
@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.
@type spin_name_col: int or None
@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.
@type spin_num_col: int or None
@keyword sep: The column separator which, if None, defaults to whitespace.
@type sep: str or None
@keyword spin_id: The spin ID string used to restrict data loading to a subset of all spins. If 'auto' is provided for a NMRPipe seriesTab formatted file, the ID's are auto generated in form of Z_Ai.
@type spin_id: None or str
@keyword ncproc: The Bruker ncproc binary intensity scaling factor.
@type ncproc: int or None
@keyword verbose: A flag which if True will cause all relaxation data loaded to be printed out.
@type verbose: bool
"""
# Data checks.
check_pipe()
check_mol_res_spin_data()
# Check the file name.
if file == None:
raise RelaxError("The file name must be supplied.")
# Test that the intensity measures are identical.
if hasattr(cdp, 'int_method') and cdp.int_method != int_method:
raise RelaxError("The '%s' measure of peak intensities does not match '%s' of the previously loaded spectra." % (int_method, cdp.int_method))
# Multiple ID flags.
flag_multi = False
flag_multi_file = False
flag_multi_col = False
if isinstance(spectrum_id, list) or spectrum_id == 'auto':
flag_multi = True
if isinstance(file, list):
flag_multi_file = True
if isinstance(int_col, list) or spectrum_id == 'auto':
flag_multi_col = True
# List argument checks.
if flag_multi:
# Too many lists.
if flag_multi_file and flag_multi_col:
raise RelaxError("If a list of spectrum IDs is supplied, the file names and intensity column arguments cannot both be lists.")
# Not enough lists.
if not flag_multi_file and not flag_multi_col:
raise RelaxError("If a list of spectrum IDs is supplied, either the file name or intensity column arguments must be a list of equal length.")
# List lengths for multiple files.
if flag_multi_file and len(spectrum_id) != len(file):
raise RelaxError("The file list %s and spectrum ID list %s do not have the same number of elements." % (file, spectrum_id))
# List lengths for multiple intensity columns.
if flag_multi_col and spectrum_id != 'auto' and len(spectrum_id) != len(int_col):
raise RelaxError("The spectrum ID list %s and intensity column list %s do not have the same number of elements." % (spectrum_id, int_col))
# More list argument checks (when only one spectrum ID is supplied).
else:
# Multiple files.
if flag_multi_file:
raise RelaxError("If multiple files are supplied, then multiple spectrum IDs must also be supplied.")
# Multiple intensity columns.
if flag_multi_col:
raise RelaxError("If multiple intensity columns are supplied, then multiple spectrum IDs must also be supplied.")
# Intensity column checks.
if spectrum_id != 'auto' and not flag_multi and flag_multi_col:
raise RelaxError("If a list of intensity columns is supplied, the spectrum ID argument must also be a list of equal length.")
# Check the intensity measure.
if not int_method in ['height', 'point sum', 'other']:
raise RelaxError("The intensity measure '%s' is not one of 'height', 'point sum', 'other'." % int_method)
# Set the peak intensity measure.
cdp.int_method = int_method
# Convert the file argument to a list if necessary.
if not isinstance(file, list):
file = [file]
# Loop over all files.
for file_index in range(len(file)):
# Read the peak list data.
peak_list = read_peak_list(file=file[file_index], dir=dir, int_col=int_col, 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, sep=sep, spin_id=spin_id)
# Automatic spectrum IDs.
if spectrum_id == 'auto':
spectrum_id = peak_list[0].intensity_name
# Loop over the assignments.
data = []
data_flag = False
for assign in peak_list:
# Generate the spin_id.
spin_id = generate_spin_id_unique(res_num=assign.res_nums[dim-1], spin_name=assign.spin_names[dim-1])
# Convert the intensity data to a list if needed.
intensity = assign.intensity
if not isinstance(intensity, list):
intensity = [intensity]
# Loop over the intensity data.
for int_index in range(len(intensity)):
# Sanity check.
if intensity[int_index] == 0.0:
warn(RelaxWarning("A peak intensity of zero has been encountered for the spin '%s' - this could be fatal later on." % spin_id))
# Get the spin container.
spin = return_spin(spin_id)
if not spin:
warn(RelaxNoSpinWarning(spin_id))
continue
# Skip deselected spins.
if not spin.select:
continue
# Initialise.
if not hasattr(spin, 'peak_intensity'):
spin.peak_intensity = {}
# Intensity scaling.
if ncproc != None:
intensity[int_index] = intensity[int_index] / float(2**ncproc)
# Add the data.
if flag_multi_file:
id = spectrum_id[file_index]
elif flag_multi_col:
id = spectrum_id[int_index]
else:
id = spectrum_id
spin.peak_intensity[id] = intensity[int_index]
# Switch the flag.
data_flag = True
# Append the data for printing out.
data.append([spin_id, repr(intensity[int_index])])
# Add the spectrum id (and ncproc) to the relax data store.
spectrum_ids = spectrum_id
if isinstance(spectrum_id, str):
spectrum_ids = [spectrum_id]
if ncproc != None and not hasattr(cdp, 'ncproc'):
cdp.ncproc = {}
for i in range(len(spectrum_ids)):
add_spectrum_id(spectrum_ids[i])
if ncproc != None:
cdp.ncproc[spectrum_ids[i]] = ncproc
# No data.
if not data_flag:
# Delete all the data.
delete(spectrum_id)
# Raise the error.
raise RelaxError("No data could be loaded from the peak list")
# Printout.
if verbose:
print("\nThe following intensities have been loaded into the relax data store:\n")
write_data(out=sys.stdout, headings=["Spin_ID", "Intensity"], data=data)
print('')
def read(file=None, dir=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, verbose=True):
"""Read the peak intensity data.
@keyword file: The name of the file containing the peak intensities.
@type file: str
@keyword dir: The directory where the file is located.
@type dir: str
@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.
@type mol_name_col: int or None
@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.
@type res_name_col: int or None
@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.
@type res_num_col: int or None
@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.
@type spin_name_col: int or None
@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.
@type spin_num_col: int or None
@keyword sep: The column separator which, if None, defaults to whitespace.
@type sep: str or None
@keyword spin_id: The spin ID string used to restrict data loading to a subset of all spins. If 'auto' is provided for a NMRPipe seriesTab formatted file, the ID's are auto generated in form of Z_Ai.
@type spin_id: None or str
@keyword verbose: A flag which if True will cause all chemical shift data loaded to be printed out.
@type verbose: bool
"""
# Test if the current data pipe exists.
check_pipe()
# Test if sequence data is loaded.
if not exists_mol_res_spin_data():
raise RelaxNoSequenceError
# Check the file name.
if file == None:
raise RelaxError("The file name must be supplied.")
# Read the peak list data.
peak_list = read_peak_list(file=file, dir=dir, 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, sep=sep, spin_id=spin_id)
# Loop over the assignments.
data = []
data_flag = False
for assign in peak_list:
# Loop over the dimensions of the peak list.
for i in range(peak_list.dimensionality):
# Generate the spin_id.
spin_id = generate_spin_id_unique(res_num=assign.res_nums[i], spin_name=assign.spin_names[i])
# Get the spin container.
spin = return_spin(spin_id=spin_id)
if not spin:
warn(RelaxNoSpinWarning(spin_id))
continue
# Skip deselected spins.
if not spin.select:
continue
# Store the shift.
spin.chemical_shift = assign.shifts[i]
# Switch the flag.
data_flag = True
# Append the data for printing out.
data.append([spin_id, repr(spin.chemical_shift)])
# No data.
if not data_flag:
raise RelaxError("No chemical shifts could be loaded from the peak list")
# Print out.
if verbose:
print("\nThe following chemical shifts have been loaded into the relax data store:\n")
write_data(out=sys.stdout, headings=["Spin_ID", "Chemical shift"], data=data)
def write_spin_data(file, dir=None, sep=None, spin_ids=None, mol_names=None, res_nums=None, res_names=None, spin_nums=None, spin_names=None, force=False, data=None, data_name=None, error=None, error_name=None, float_format="%20.15g"):
"""Generator function for reading the spin specific data from file.
Description
===========
This function writes a columnar formatted file where each line corresponds to a spin system. Spin identification is either through a spin ID string or through columns containing the molecule name, residue name and number, and/or spin name and number.
@param file: The name of the file to write the data to (or alternatively an already opened file object).
@type file: str or file object
@keyword dir: The directory to place the file into (defaults to the current directory if None and the file argument is not a file object).
@type dir: str or None
@keyword sep: The column separator which, if None, defaults to whitespace.
@type sep: str or None
@keyword spin_ids: The list of spin ID strings.
@type spin_ids: None or list of str
@keyword mol_names: The list of molecule names.
@type mol_names: None or list of str
@keyword res_nums: The list of residue numbers.
@type res_nums: None or list of int
@keyword res_names: The list of residue names.
@type res_names: None or list of str
@keyword spin_nums: The list of spin numbers.
@type spin_nums: None or list of int
@keyword spin_names: The list of spin names.
@type spin_names: None or list of str
@keyword force: A flag which if True will cause an existing file to be overwritten.
@type force: bool
@keyword data: A list of the data to write out. The first dimension corresponds to the spins. A second dimension can also be given if multiple data sets across multiple columns are desired.
@type data: list or list of lists
@keyword data_name: A name corresponding to the data argument. If the data argument is a list of lists, then this must also be a list with the same length as the second dimension of the data arg.
@type data_name: str or list of str
@keyword error: A list of the errors to write out. The first dimension corresponds to the spins. A second dimension can also be given if multiple data sets across multiple columns are desired. These will be inter-dispersed between the data columns, if the data is given. If the data arg is not None, then this must have the same dimensions as that object.
@type error: list or list of lists
@keyword error_name: A name corresponding to the error argument. If the error argument is a list of lists, then this must also be a list with the same length at the second dimension of the error arg.
@type error_name: str or list of str
@keyword float_format: A float formatting string to use for the data and error whenever a float is found.
@type float_format: str
"""
# Data argument tests.
if data:
# Data is a list of lists.
if isinstance(data[0], list):
# Data and data_name don't match.
if not isinstance(data_name, list):
raise RelaxError("The data_name arg '%s' must be a list as the data argument is a list of lists." % data_name)
# Error doesn't match.
if error and (len(data) != len(error) or len(data[0]) != len(error[0])):
raise RelaxError("The data arg:\n%s\n\ndoes not have the same dimensions as the error arg:\n%s." % (data, error))
# Data is a simple list.
else:
# Data and data_name don't match.
if not isinstance(data_name, str):
raise RelaxError("The data_name arg '%s' must be a string as the data argument is a simple list." % data_name)
# Error doesn't match.
if error and len(data) != len(error):
raise RelaxError("The data arg:\n%s\n\ndoes not have the same dimensions as the error arg:\n%s." % (data, error))
# Error argument tests.
if error:
# Error is a list of lists.
if isinstance(error[0], list):
# Error and error_name don't match.
if not isinstance(error_name, list):
raise RelaxError("The error_name arg '%s' must be a list as the error argument is a list of lists." % error_name)
# Error is a simple list.
else:
# Error and error_name don't match.
if not isinstance(error_name, str):
raise RelaxError("The error_name arg '%s' must be a string as the error argument is a simple list." % error_name)
# Number of spins check.
args = [spin_ids, mol_names, res_nums, res_names, spin_nums, spin_names]
arg_names = ['spin_ids', 'mol_names', 'res_nums', 'res_names', 'spin_nums', 'spin_names']
N = None
first_arg = None
first_arg_name = None
for i in range(len(args)):
if isinstance(args[i], list):
# First list match.
if N == None:
N = len(args[i])
first_arg = args[i]
first_arg_name = arg_names[i]
# Length check.
if len(args[i]) != N:
raise RelaxError("The %s and %s arguments do not have the same number of spins ('%s' vs. '%s' respectively)." % (first_arg_name, arg_names[i], len(first_arg), len(args[i])))
# Nothing?!?
if N == None:
raise RelaxError("No spin ID data is present.")
# Data and error length check.
if data and len(data) != N:
raise RelaxError("The %s and data arguments do not have the same number of spins ('%s' vs. '%s' respectively)." % (first_arg_name, len(first_arg), len(data)))
if error and len(error) != N:
raise RelaxError("The %s and error arguments do not have the same number of spins ('%s' vs. '%s' respectively)." % (first_arg_name, len(first_arg), len(error)))
# The spin arguments.
args = [spin_ids, mol_names, res_nums, res_names, spin_nums, spin_names]
arg_names = ['spin_id', 'mol_name', 'res_num', 'res_name', 'spin_num', 'spin_name']
# Init.
headings = []
file_data = []
# Headers - the spin ID info.
for i in range(len(args)):
if args[i]:
headings.append(arg_names[i])
# Headers - the data.
if data:
# List of lists.
if isinstance(data[0], list):
# Loop over the list.
for i in range(len(data[0])):
# The data.
headings.append(data_name[i])
# The error.
if error:
headings.append(error_name[i])
# Simple list.
else:
# The data.
headings.append(data_name)
# The error.
if error:
headings.append(error_name)
# Headers - only errors.
elif error:
# List of lists.
if isinstance(error[0], list):
for i in range(len(error[0])):
headings.append(error_name[i])
# Simple list.
else:
headings.append(error_name)
# No headings.
if headings == []:
headings = None
# Spin specific data.
for spin_index in range(N):
# Append a new data row.
file_data.append([])
# The spin ID info.
for i in range(len(args)):
if args[i]:
value = args[i][spin_index]
if not isinstance(value, str):
value = repr(value)
file_data[-1].append(value)
# The data.
if data:
# List of lists.
if isinstance(data[0], list):
# Loop over the list.
for i in range(len(data[0])):
# The data.
if is_float(data[spin_index][i]):
file_data[-1].append(float_format % data[spin_index][i])
else:
file_data[-1].append(repr(data[spin_index][i]))
# The error.
if error:
if is_float(error[spin_index][i]):
file_data[-1].append(float_format % error[spin_index][i])
else:
file_data[-1].append(repr(error[spin_index][i]))
# Simple list.
else:
# The data.
if is_float(data[spin_index]):
file_data[-1].append(float_format % data[spin_index])
else:
file_data[-1].append(repr(data[spin_index]))
# The error.
if error:
if is_float(error[spin_index]):
file_data[-1].append(float_format % error[spin_index])
else:
file_data[-1].append(repr(error[spin_index]))
# Only errors.
elif error:
# List of lists.
if isinstance(error[0], list):
for i in range(len(error[0])):
file_data[-1].append(repr(error[spin_index][i]))
# Simple list.
else:
file_data[-1].append(repr(error[spin_index]))
# No data to write, so do nothing!
if file_data == [] or file_data == [[]]:
return
# Open the file for writing.
file = open_write_file(file_name=file, dir=dir, force=force)
# Write out the file data.
write_data(out=file, headings=headings, data=file_data, sep=sep)
def copy(pipe_from=None, pipe_to=None, align_id=None, back_calc=True):
"""Copy the PCS data from one data pipe to another.
@keyword pipe_from: The data pipe to copy the PCS data from. This defaults to the current data pipe.
@type pipe_from: str
@keyword pipe_to: The data pipe to copy the PCS data to. This defaults to the current data pipe.
@type pipe_to: str
@keyword align_id: The alignment ID string.
@type align_id: str
@keyword back_calc: A flag which if True will cause any back-calculated RDCs present to also be copied with the real values and errors.
@type back_calc: bool
"""
# Defaults.
if pipe_from == None and pipe_to == None:
raise RelaxError("The pipe_from and pipe_to arguments cannot both be set to None.")
elif pipe_from == None:
pipe_from = pipes.cdp_name()
elif pipe_to == None:
pipe_to = pipes.cdp_name()
# Check the pipe setup.
check_pipe_setup(pipe=pipe_from, pcs_id=align_id, sequence=True, pcs=True)
check_pipe_setup(pipe=pipe_to, sequence=True)
# Get the data pipes.
dp_from = pipes.get_pipe(pipe_from)
dp_to = pipes.get_pipe(pipe_to)
# The IDs.
if align_id == None:
align_ids = dp_from.align_ids
else:
align_ids = [align_id]
# Init target pipe global structures.
if not hasattr(dp_to, 'align_ids'):
dp_to.align_ids = []
if not hasattr(dp_to, 'pcs_ids'):
dp_to.pcs_ids = []
# Loop over the align IDs.
for align_id in align_ids:
# Printout.
print("\nCoping PCSs for the alignment ID '%s'." % align_id)
# Copy the global data.
if align_id not in dp_to.align_ids and align_id not in dp_to.align_ids:
dp_to.align_ids.append(align_id)
if align_id in dp_from.pcs_ids and align_id not in dp_to.pcs_ids:
dp_to.pcs_ids.append(align_id)
# Spin loop.
data = []
for spin_from, spin_id in spin_loop(return_id=True, skip_desel=True, pipe=pipe_from):
# Find the matching spin container in the target data pipe.
spin_to = return_spin(spin_id, pipe=pipe_to)
# No matching spin container.
if spin_to == None:
warn(RelaxWarning("The spin container for the spin '%s' cannot be found in the target data pipe." % spin_id))
continue
# No data or errors.
if (not hasattr(spin_from, 'pcs') or not align_id in spin_from.pcs) and (not hasattr(spin_from, 'pcs_err') or not align_id in spin_from.pcs_err):
continue
# Initialise the spin data if necessary.
if hasattr(spin_from, 'pcs') and not hasattr(spin_to, 'pcs'):
spin_to.pcs = {}
if back_calc and hasattr(spin_from, 'pcs_bc') and not hasattr(spin_to, 'pcs_bc'):
spin_to.pcs_bc = {}
if hasattr(spin_from, 'pcs_err') and not hasattr(spin_to, 'pcs_err'):
spin_to.pcs_err = {}
# Copy the value and error from pipe_from.
value = None
error = None
value_bc = None
if hasattr(spin_from, 'pcs'):
value = spin_from.pcs[align_id]
spin_to.pcs[align_id] = value
if back_calc and hasattr(spin_from, 'pcs_bc'):
value_bc = spin_from.pcs_bc[align_id]
spin_to.pcs_bc[align_id] = value_bc
if hasattr(spin_from, 'pcs_err'):
error = spin_from.pcs_err[align_id]
spin_to.pcs_err[align_id] = error
# Append the data for printout.
data.append([spin_id])
if is_float(value):
data[-1].append("%20.15f" % value)
else:
data[-1].append("%20s" % value)
if back_calc:
if is_float(value_bc):
data[-1].append("%20.15f" % value_bc)
else:
data[-1].append("%20s" % value_bc)
if is_float(error):
data[-1].append("%20.15f" % error)
else:
data[-1].append("%20s" % error)
# Printout.
print("The following PCSs have been copied:\n")
if back_calc:
write_data(out=sys.stdout, headings=["Spin_ID", "Value", "Back-calculated", "Error"], data=data)
else:
write_data(out=sys.stdout, headings=["Spin_ID", "Value", "Error"], data=data)
def write_spin_data(file, dir=None, sep=None, spin_ids=None, mol_names=None, res_nums=None, res_names=None, spin_nums=None, spin_names=None, force=False, data=None, data_name=None, error=None, error_name=None, float_format="%20.15g"):
"""Generator function for reading the spin specific data from file.
Description
===========
This function writes a columnar formatted file where each line corresponds to a spin system. Spin identification is either through a spin ID string or through columns containing the molecule name, residue name and number, and/or spin name and number.
@param file: The name of the file to write the data to (or alternatively an already opened file object).
@type file: str or file object
@keyword dir: The directory to place the file into (defaults to the current directory if None and the file argument is not a file object).
@type dir: str or None
@keyword sep: The column separator which, if None, defaults to whitespace.
@type sep: str or None
@keyword spin_ids: The list of spin ID strings.
@type spin_ids: None or list of str
@keyword mol_names: The list of molecule names.
@type mol_names: None or list of str
@keyword res_nums: The list of residue numbers.
@type res_nums: None or list of int
@keyword res_names: The list of residue names.
@type res_names: None or list of str
@keyword spin_nums: The list of spin numbers.
@type spin_nums: None or list of int
@keyword spin_names: The list of spin names.
@type spin_names: None or list of str
@keyword force: A flag which if True will cause an existing file to be overwritten.
@type force: bool
@keyword data: A list of the data to write out. The first dimension corresponds to the spins. A second dimension can also be given if multiple data sets across multiple columns are desired.
@type data: list or list of lists
@keyword data_name: A name corresponding to the data argument. If the data argument is a list of lists, then this must also be a list with the same length as the second dimension of the data arg.
@type data_name: str or list of str
@keyword error: A list of the errors to write out. The first dimension corresponds to the spins. A second dimension can also be given if multiple data sets across multiple columns are desired. These will be inter-dispersed between the data columns, if the data is given. If the data arg is not None, then this must have the same dimensions as that object.
@type error: list or list of lists
@keyword error_name: A name corresponding to the error argument. If the error argument is a list of lists, then this must also be a list with the same length at the second dimension of the error arg.
@type error_name: str or list of str
@keyword float_format: A float formatting string to use for the data and error whenever a float is found.
@type float_format: str
"""
# Data argument tests.
if data:
# Data is a list of lists.
if isinstance(data[0], list):
# Data and data_name don't match.
if not isinstance(data_name, list):
raise RelaxError("The data_name arg '%s' must be a list as the data argument is a list of lists." % data_name)
# Error doesn't match.
if error and (len(data) != len(error) or len(data[0]) != len(error[0])):
raise RelaxError("The data arg:\n%s\n\ndoes not have the same dimensions as the error arg:\n%s." % (data, error))
# Data is a simple list.
else:
# Data and data_name don't match.
if not isinstance(data_name, str):
raise RelaxError("The data_name arg '%s' must be a string as the data argument is a simple list." % data_name)
# Error doesn't match.
if error and len(data) != len(error):
raise RelaxError("The data arg:\n%s\n\ndoes not have the same dimensions as the error arg:\n%s." % (data, error))
# Error argument tests.
if error:
# Error is a list of lists.
if isinstance(error[0], list):
# Error and error_name don't match.
if not isinstance(error_name, list):
raise RelaxError("The error_name arg '%s' must be a list as the error argument is a list of lists." % error_name)
# Error is a simple list.
else:
# Error and error_name don't match.
if not isinstance(error_name, str):
raise RelaxError("The error_name arg '%s' must be a string as the error argument is a simple list." % error_name)
# Number of spins check.
args = [spin_ids, mol_names, res_nums, res_names, spin_nums, spin_names]
arg_names = ['spin_ids', 'mol_names', 'res_nums', 'res_names', 'spin_nums', 'spin_names']
N = None
first_arg = None
first_arg_name = None
for i in range(len(args)):
if isinstance(args[i], list):
# First list match.
if N == None:
N = len(args[i])
first_arg = args[i]
first_arg_name = arg_names[i]
# Length check.
if len(args[i]) != N:
raise RelaxError("The %s and %s arguments do not have the same number of spins ('%s' vs. '%s' respectively)." % (first_arg_name, arg_names[i], len(first_arg), len(args[i])))
# Nothing?!?
if N == None:
raise RelaxError("No spin ID data is present.")
# Data and error length check.
if data and len(data) != N:
raise RelaxError("The %s and data arguments do not have the same number of spins ('%s' vs. '%s' respectively)." % (first_arg_name, len(first_arg), len(data)))
if error and len(error) != N:
raise RelaxError("The %s and error arguments do not have the same number of spins ('%s' vs. '%s' respectively)." % (first_arg_name, len(first_arg), len(error)))
# The spin arguments.
args = [spin_ids, mol_names, res_nums, res_names, spin_nums, spin_names]
arg_names = ['spin_id', 'mol_name', 'res_num', 'res_name', 'spin_num', 'spin_name']
# Init.
headings = []
file_data = []
# Headers - the spin ID info.
for i in range(len(args)):
if args[i]:
headings.append(arg_names[i])
# Headers - the data.
if data:
# List of lists.
if isinstance(data[0], list):
# Loop over the list.
for i in range(len(data[0])):
# The data.
headings.append(data_name[i])
# The error.
if error:
headings.append(error_name[i])
# Simple list.
else:
# The data.
headings.append(data_name)
# The error.
if error:
headings.append(error_name)
# Headers - only errors.
elif error:
# List of lists.
if isinstance(error[0], list):
for i in range(len(error[0])):
headings.append(error_name[i])
# Simple list.
else:
headings.append(error_name)
# No headings.
if headings == []:
headings = None
# Spin specific data.
for spin_index in range(N):
# Append a new data row.
file_data.append([])
# The spin ID info.
for i in range(len(args)):
if args[i]:
value = args[i][spin_index]
if not isinstance(value, str):
value = repr(value)
file_data[-1].append(value)
# The data.
if data:
# List of lists.
if isinstance(data[0], list):
# Loop over the list.
for i in range(len(data[0])):
# The data.
if is_float(data[spin_index][i]):
file_data[-1].append(float_format % data[spin_index][i])
else:
file_data[-1].append(repr(data[spin_index][i]))
# The error.
if error:
if is_float(error[spin_index][i]):
file_data[-1].append(float_format % error[spin_index][i])
else:
file_data[-1].append(repr(error[spin_index][i]))
# Simple list.
else:
# The data.
if is_float(data[spin_index]):
file_data[-1].append(float_format % data[spin_index])
else:
file_data[-1].append(repr(data[spin_index]))
# The error.
if error:
if is_float(error[spin_index]):
file_data[-1].append(float_format % error[spin_index])
else:
file_data[-1].append(repr(error[spin_index]))
# Only errors.
elif error:
# List of lists.
if isinstance(error[0], list):
for i in range(len(error[0])):
file_data[-1].append(repr(error[spin_index][i]))
# Simple list.
else:
file_data[-1].append(repr(error[spin_index]))
# No data to write, so do nothing!
if file_data == [] or file_data == [[]]:
return
# Open the file for writing.
file = open_write_file(file_name=file, dir=dir, force=force)
# Write out the file data.
write_data(out=file, headings=headings, data=file_data, sep=sep)
# Save all values of chi2. To help find reasonale level for the Innermost, Inner, Middle and Outer Isosurface.
all_chi.append(chi2)
# Increment the value of the second parameter.
values[1] = values[1] + step_size[1]
counter += 1
# Increment the value of the first parameter.
values[0] = values[0] + step_size[0]
print("\nMin cluster point %s=%3.3f, %s=%3.3f, with chi2=%3.3f" % (params[0], pcm[0], params[1], pcm[1], pre_chi2))
# Open file
file_name = '3_simulate_graphs_S65_dw_r2a_FT128.txt'
surface_file = open_write_file(file_name=file_name, dir=None, force=True)
write_data(out=surface_file, headings=headings, data=data)
# Close file
surface_file.close()
# Check spins.
display_spin()
# Now de-select spins from cluster.
for spin_id in cur_spin_ids:
deselect.spin(spin_id=spin_id)
relax_disp.plot_disp_curves(dir='grace', y_axis='r2_eff', x_axis='disp', num_points=1000, extend_hz=500.0, extend_ppm=500.0, interpolate='disp', force=True)
def read(align_id=None, file=None, dir=None, file_data=None, data_type='D', spin_id1_col=None, spin_id2_col=None, data_col=None, error_col=None, sep=None, neg_g_corr=False, absolute=False):
"""Read the RDC data from file.
@keyword align_id: The alignment tensor ID string.
@type align_id: str
@keyword file: The name of the file to open.
@type file: str
@keyword dir: The directory containing the file (defaults to the current directory if None).
@type dir: str or None
@keyword file_data: An alternative to opening a file, if the data already exists in the correct format. The format is a list of lists where the first index corresponds to the row and the second the column.
@type file_data: list of lists
@keyword data_type: A string which is set to 'D' means that the splitting in the aligned sample was assumed to be J + D, or if set to '2D' then the splitting was taken as J + 2D. If set to 'T', then the data will be marked as being J+D values.
@keyword spin_id1_col: The column containing the spin ID strings of the first spin.
@type spin_id1_col: int
@keyword spin_id2_col: The column containing the spin ID strings of the second spin.
@type spin_id2_col: int
@keyword data_col: The column containing the RDC data in Hz.
@type data_col: int or None
@keyword error_col: The column containing the RDC errors.
@type error_col: int or None
@keyword sep: The column separator which, if None, defaults to whitespace.
@type sep: str or None
@keyword neg_g_corr: A flag which is used to correct for the negative gyromagnetic ratio of 15N. If True, a sign inversion will be applied to all RDC values to be loaded.
@type neg_g_corr: bool
@keyword absolute: A flag which if True indicates that the RDCs to load are signless. All RDCs will then be converted to positive values.
@type absolute: bool
"""
# Check the pipe setup.
check_pipe_setup(sequence=True)
# Either the data or error column must be supplied.
if data_col == None and error_col == None:
raise RelaxError("One of either the data or error column must be supplied.")
# Check the data types.
rdc_types = ['D', '2D', 'T']
if data_type not in rdc_types:
raise RelaxError("The RDC data type '%s' must be one of %s." % (data_type, rdc_types))
# Spin specific data.
#####################
# Extract the data from the file, and remove comments and blank lines.
file_data = extract_data(file, dir, sep=sep)
file_data = strip(file_data, comments=True)
# Loop over the RDC data.
data = []
for line in file_data:
# Invalid columns.
if spin_id1_col > len(line):
warn(RelaxWarning("The data %s is invalid, no first spin ID column can be found." % line))
continue
if spin_id2_col > len(line):
warn(RelaxWarning("The data %s is invalid, no second spin ID column can be found." % line))
continue
if data_col and data_col > len(line):
warn(RelaxWarning("The data %s is invalid, no data column can be found." % line))
continue
if error_col and error_col > len(line):
warn(RelaxWarning("The data %s is invalid, no error column can be found." % line))
continue
# Unpack.
spin_id1 = line[spin_id1_col-1]
spin_id2 = line[spin_id2_col-1]
value = None
if data_col:
value = line[data_col-1]
error = None
if error_col:
error = line[error_col-1]
# Convert the spin IDs.
if spin_id1[0] in ["\"", "\'"]:
spin_id1 = eval(spin_id1)
if spin_id2[0] in ["\"", "\'"]:
spin_id2 = eval(spin_id2)
# Convert and check the value.
if value == 'None':
value = None
if value != None:
try:
value = float(value)
except ValueError:
warn(RelaxWarning("The RDC value of the line %s is invalid." % line))
continue
# Convert and check the error.
if error == 'None':
error = None
if error != None:
try:
error = float(error)
except ValueError:
warn(RelaxWarning("The error value of the line %s is invalid." % line))
continue
# Get the spins.
spin1 = return_spin(spin_id1)
spin2 = return_spin(spin_id2)
# Check the spin IDs.
if not spin1:
warn(RelaxWarning("The spin ID '%s' cannot be found in the current data pipe, skipping the data %s." % (spin_id1, line)))
continue
if not spin2:
warn(RelaxWarning("The spin ID '%s' cannot be found in the current data pipe, skipping the data %s." % (spin_id2, line)))
continue
# Get the interatomic data container.
interatom = return_interatom(spin_id1, spin_id2)
# Create the container if needed.
if interatom == None:
interatom = create_interatom(spin_id1=spin_id1, spin_id2=spin_id2)
# Test the error value (a value of 0.0 will cause the interatomic container to be deselected).
if error == 0.0:
interatom.select = False
warn(RelaxWarning("An error value of zero has been encountered, deselecting the interatomic container between spin '%s' and '%s'." % (spin_id1, spin_id2)))
continue
# Store the data type as global data (need for the conversion of RDC data).
if not hasattr(interatom, 'rdc_data_types'):
interatom.rdc_data_types = {}
if not align_id in interatom.rdc_data_types:
interatom.rdc_data_types[align_id] = data_type
# Convert and add the data.
if data_col:
# Data conversion.
value = convert(value, data_type, align_id, to_intern=True)
# Correction for the negative gyromagnetic ratio of 15N.
if neg_g_corr and value != None:
value = -value
# Absolute values.
if absolute:
# Force the value to be positive.
value = abs(value)
# Initialise.
if not hasattr(interatom, 'rdc'):
interatom.rdc = {}
# Add the value.
interatom.rdc[align_id] = value
# Store the absolute value flag.
if not hasattr(interatom, 'absolute_rdc'):
interatom.absolute_rdc = {}
interatom.absolute_rdc[align_id] = absolute
# Convert and add the error.
if error_col:
# Data conversion.
error = convert(error, data_type, align_id, to_intern=True)
# Initialise.
if not hasattr(interatom, 'rdc_err'):
interatom.rdc_err = {}
# Append the error.
interatom.rdc_err[align_id] = error
# Append the data for printout.
data.append([spin_id1, spin_id2])
if is_float(value):
data[-1].append("%20.15f" % value)
else:
data[-1].append("%20s" % value)
if is_float(error):
data[-1].append("%20.15f" % error)
else:
data[-1].append("%20s" % error)
# No data, so fail hard!
if not len(data):
raise RelaxError("No RDC data could be extracted.")
# Print out.
print("The following RDCs have been loaded into the relax data store:\n")
write_data(out=sys.stdout, headings=["Spin_ID1", "Spin_ID2", "Value", "Error"], data=data)
# Initialise some global structures.
if not hasattr(cdp, 'align_ids'):
cdp.align_ids = []
if not hasattr(cdp, 'rdc_ids'):
cdp.rdc_ids = []
# Add the RDC id string.
if align_id not in cdp.align_ids:
cdp.align_ids.append(align_id)
if align_id not in cdp.rdc_ids:
cdp.rdc_ids.append(align_id)
def grid_setup(lower=None,
upper=None,
inc=None,
verbosity=1,
skip_preset=True):
"""Determine the per-model grid bounds, allowing for the zooming grid search.
@keyword lower: The user supplied lower bounds of the grid search which must be equal to the number of parameters in the model.
@type lower: list of numbers
@keyword upper: The user supplied upper bounds of the grid search which must be equal to the number of parameters in the model.
@type upper: list of numbers
@keyword inc: The user supplied grid search increments.
@type inc: int or list of int
@keyword verbosity: The amount of information to print. The higher the value, the greater the verbosity.
@type verbosity: int
@keyword skip_preset: This argument, when True, allows any parameter which already has a value set to be skipped in the grid search.
@type skip_preset: bool
@return: The per-model grid upper and lower bounds. The first dimension of each structure corresponds to the model, the second the model parameters.
@rtype: tuple of lists of lists of float, lists of lists of float, list of lists of int
"""
# The specific analysis API object and parameter object.
api = return_api()
param_object = return_parameter_object()
# Initialise.
model_lower = []
model_upper = []
model_inc = []
# Loop over the models.
for model_info in api.model_loop():
# Get the parameter names and current values.
names = api.get_param_names(model_info)
values = api.get_param_values(model_info)
# No parameters for this model.
if names == None or len(names) == 0:
model_lower.append([])
model_upper.append([])
model_inc.append([])
continue
# The parameter number.
n = len(names)
# Make sure that the length of the parameter array is > 0.
if n == 0:
raise RelaxError(
"Cannot run a grid search on a model with zero parameters.")
# Check that the user supplied bound lengths are ok.
if lower != None and len(lower) != n:
raise RelaxLenError('lower bounds', n)
if upper != None and len(upper) != n:
raise RelaxLenError('upper bounds', n)
# Check the user supplied increments.
if isinstance(inc, list) and len(inc) != n:
raise RelaxLenError('increment', n)
if isinstance(inc, list):
for i in range(n):
if not (isinstance(inc[i], int) or inc[i] == None):
raise RelaxIntListIntError('increment', inc)
elif not isinstance(inc, int):
raise RelaxIntListIntError('increment', inc)
# Convert to the model increment list.
if isinstance(inc, int):
model_inc.append([inc] * n)
else:
model_inc.append(inc)
# Print out the model title.
api.print_model_title(prefix="Grid search setup: ",
model_info=model_info)
# The grid zoom level.
zoom = 0
if hasattr(cdp, 'grid_zoom_level'):
zoom = cdp.grid_zoom_level
zoom_factor = 1.0 / 2.0**zoom
if zoom > 0:
print(
"Zooming grid level of %s, scaling the grid size by a factor of %s.\n"
% (zoom, zoom_factor))
# Append empty lists for the bounds to be built up.
model_lower.append([])
model_upper.append([])
# Loop over the parameters.
data = []
for i in range(n):
# A comment for user feedback.
comment = 'Default bounds'
if lower != None and upper != None:
comment = 'User supplied lower and upper bound'
elif lower != None:
comment = 'User supplied lower bound'
elif upper != None:
comment = 'User supplied upper bound'
# Alias the number of increments for this parameter.
incs = model_inc[-1][i]
# Error checking for increment values of None.
if incs == None and values[i] in [None, {}, []]:
raise RelaxError(
"The parameter '%s' has no preset value, therefore a grid increment of None is not valid."
% names[i])
# The lower bound for this parameter.
if lower != None:
lower_i = lower[i]
else:
lower_i = param_object.grid_lower(names[i],
incs=incs,
model_info=model_info)
# The upper bound for this parameter.
if upper != None:
upper_i = upper[i]
else:
upper_i = param_object.grid_upper(names[i],
incs=incs,
model_info=model_info)
# The skipping logic.
skip = False
if skip_preset:
# Override the flag if the zoom is on.
if zoom:
skip = False
# No preset value.
elif values[i] in [None, {}, []]:
skip = False
# The preset value is a NaN value due to numpy conversions of None.
elif isNaN(values[i]):
skip = False
# Ok, now the parameter can be skipped.
else:
skip = True
# Override the skip flag if the incs value is None.
if incs == None:
skip = True
# Skip preset values.
if skip:
lower_i = values[i]
upper_i = values[i]
model_inc[-1][i] = incs = 1
comment = 'Preset value'
# Zooming grid.
elif zoom:
# The full size and scaled size.
size = upper_i - lower_i
zoom_size = size * zoom_factor
half_size = zoom_size / 2.0
comment = 'Zoom grid width of %s %s' % (
zoom_size, param_object.units(names[i]))
# The new size around the current value.
lower_zoom = values[i] - half_size
upper_zoom = values[i] + half_size
# Outside of the original lower bound, so shift the grid to fit.
if zoom > 0 and lower_zoom < lower_i:
# The amount to shift by.
shift = lower_i - lower_zoom
# Set the new bounds.
upper_i = upper_zoom + shift
# Outside of the original upper bound, so shift the grid to fit.
elif zoom > 0 and upper_zoom > upper_i:
# The amount to shift by.
shift = upper_i - upper_zoom
# Set the new bounds.
lower_i = lower_zoom + shift
# Inside the original bounds.
else:
lower_i = lower_zoom
upper_i = upper_zoom
# Add to the data list for printing out.
data.append([
names[i],
"%15s" % lower_i,
"%15s" % upper_i,
"%15s" % incs, comment
])
# Scale the bounds.
scaling = param_object.scaling(names[i], model_info=model_info)
lower_i /= scaling
upper_i /= scaling
# Append.
model_lower[-1].append(lower_i)
model_upper[-1].append(upper_i)
# Printout.
if verbosity:
write_data(out=sys.stdout,
headings=[
"Parameter", "Lower bound", "Upper bound",
"Increments", "Comment"
],
data=data)
sys.stdout.write('\n')
# Return the bounds.
return model_lower, model_upper, model_inc
def select(method=None, modsel_pipe=None, bundle=None, pipes=None):
"""Model selection function.
@keyword method: The model selection method. This can currently be one of:
- 'AIC', Akaike's Information Criteria.
- 'AICc', Small sample size corrected AIC.
- 'BIC', Bayesian or Schwarz Information Criteria.
- 'CV', Single-item-out cross-validation.
None of the other model selection techniques are currently supported.
@type method: str
@keyword modsel_pipe: The name of the new data pipe to be created by copying of the selected data pipe.
@type modsel_pipe: str
@keyword bundle: The optional data pipe bundle to associate the newly created pipe with.
@type bundle: str or None
@keyword pipes: A list of the data pipes to use in the model selection.
@type pipes: list of str
"""
# Test if the pipe already exists.
if has_pipe(modsel_pipe):
raise RelaxPipeError(modsel_pipe)
# Use all pipes.
if pipes == None:
# Get all data pipe names from the relax data store.
pipes = pipe_names()
# Select the model selection technique.
if method == 'AIC':
print("AIC model selection.")
formula = aic
elif method == 'AICc':
print("AICc model selection.")
formula = aicc
elif method == 'BIC':
print("BIC model selection.")
formula = bic
elif method == 'CV':
print("CV model selection.")
raise RelaxError("The model selection technique " + repr(method) + " is not currently supported.")
else:
raise RelaxError("The model selection technique " + repr(method) + " is not currently supported.")
# No pipes.
if len(pipes) == 0:
raise RelaxError("No data pipes are available for use in model selection.")
# Initialise.
function_type = {}
model_loop = {}
model_type = {}
duplicate_data = {}
model_statistics = {}
skip_function = {}
modsel_pipe_exists = False
# Cross validation setup.
if isinstance(pipes[0], list):
# No pipes.
if len(pipes[0]) == 0:
raise RelaxError("No pipes are available for use in model selection in the array " + repr(pipes[0]) + ".")
# Loop over the data pipes.
for i in range(len(pipes)):
for j in range(len(pipes[i])):
# The specific analysis API object.
api = return_api(pipe_name=pipes[i][j])
# Store the specific functions.
model_loop[pipes[i][j]] = api.model_loop
model_type[pipes[i][j]] = api.model_type
duplicate_data[pipes[i][j]] = api.duplicate_data
model_statistics[pipes[i][j]] = api.model_statistics
skip_function[pipes[i][j]] = api.skip_function
# The model loop should be the same for all data pipes!
for i in range(len(pipes)):
for j in range(len(pipes[i])):
if model_loop[pipes[0][j]] != model_loop[pipes[i][j]]:
raise RelaxError("The models for each data pipes should be the same.")
# Alias some function from the specific API of the first data pipe.
api = return_api(pipe_name=pipes[0][0])
model_loop = api.model_loop
model_desc = api.model_desc
# Global vs. local models.
global_flag = False
for i in range(len(pipes)):
for j in range(len(pipes[i])):
if model_type[pipes[i][j]]() == 'global':
global_flag = True
# All other model selection setup.
else:
# Loop over the data pipes.
for i in range(len(pipes)):
# The specific analysis API object.
api = return_api()
# Store the specific functions.
model_loop[pipes[i]] = api.model_loop
model_type[pipes[i]] = api.model_type
duplicate_data[pipes[i]] = api.duplicate_data
model_statistics[pipes[i]] = api.model_statistics
skip_function[pipes[i]] = api.skip_function
# Alias some function from the specific API of the first data pipe.
api = return_api(pipe_name=pipes[0])
model_loop = api.model_loop
model_desc = api.model_desc
# Global vs. local models.
global_flag = False
for j in range(len(pipes)):
if model_type[pipes[j]]() == 'global':
global_flag = True
# Loop over the base models.
for model_info in model_loop():
# Print out.
print("\n")
desc = model_desc(model_info)
if desc:
print(desc)
# Initial model.
best_model = None
best_crit = 1e300
data = []
# Loop over the pipes.
for j in range(len(pipes)):
# Single-item-out cross validation.
if method == 'CV':
# Sum of chi-squared values.
sum_crit = 0.0
# Loop over the validation samples and sum the chi-squared values.
for k in range(len(pipes[j])):
# Alias the data pipe name.
pipe = pipes[j][k]
# Switch to this pipe.
switch(pipe)
# Skip function.
if skip_function[pipe](model_info):
continue
# Get the model statistics.
k, n, chi2 = model_statistics[pipe](model_info)
# Missing data sets.
if k == None or n == None or chi2 == None:
continue
# Chi2 sum.
sum_crit = sum_crit + chi2
# Cross-validation criterion (average chi-squared value).
crit = sum_crit / float(len(pipes[j]))
# Other model selection methods.
else:
# Reassign the pipe.
pipe = pipes[j]
# Switch to this pipe.
switch(pipe)
# Skip function.
if skip_function[pipe](model_info):
continue
# Get the model statistics.
k, n, chi2 = model_statistics[pipe](model_info, global_stats=global_flag)
# Missing data sets.
if k == None or n == None or chi2 == None:
continue
# Calculate the criterion value.
crit = formula(chi2, float(k), float(n))
# Store the values for a later printout.
data.append([pipe, repr(k), repr(n), "%.5f" % chi2, "%.5f" % crit])
# Select model.
if crit < best_crit:
best_model = pipe
best_crit = crit
# Write out the table.
write_data(out=sys.stdout, headings=["Data pipe", "Num_params_(k)", "Num_data_sets_(n)", "Chi2", "Criterion"], data=data)
# Duplicate the data from the 'best_model' to the model selection data pipe.
if best_model != None:
# Print out of selected model.
print("The model from the data pipe " + repr(best_model) + " has been selected.")
# Switch to the selected data pipe.
switch(best_model)
# Duplicate.
duplicate_data[best_model](best_model, modsel_pipe, model_info, global_stats=global_flag, verbose=False)
# Model selection pipe now exists.
modsel_pipe_exists = True
# No model selected.
else:
# Print out of selected model.
print("No model has been selected.")
# Switch to the model selection pipe.
if modsel_pipe_exists:
switch(modsel_pipe)
# Bundle the data pipe.
if bundle:
pipe_control.pipes.bundle(bundle=bundle, pipe=modsel_pipe)
# Update all of the required metadata structures.
mol_res_spin.metadata_update()
interatomic.metadata_update()
def grid_setup(lower=None, upper=None, inc=None, verbosity=1, skip_preset=True):
"""Determine the per-model grid bounds, allowing for the zooming grid search.
@keyword lower: The user supplied lower bounds of the grid search which must be equal to the number of parameters in the model.
@type lower: list of numbers
@keyword upper: The user supplied upper bounds of the grid search which must be equal to the number of parameters in the model.
@type upper: list of numbers
@keyword inc: The user supplied grid search increments.
@type inc: int or list of int
@keyword verbosity: The amount of information to print. The higher the value, the greater the verbosity.
@type verbosity: int
@keyword skip_preset: This argument, when True, allows any parameter which already has a value set to be skipped in the grid search.
@type skip_preset: bool
@return: The per-model grid upper and lower bounds. The first dimension of each structure corresponds to the model, the second the model parameters.
@rtype: tuple of lists of lists of float, lists of lists of float, list of lists of int
"""
# The specific analysis API object and parameter object.
api = return_api()
param_object = return_parameter_object()
# Initialise.
model_lower = []
model_upper = []
model_inc = []
# Loop over the models.
for model_info in api.model_loop():
# Get the parameter names and current values.
names = api.get_param_names(model_info)
values = api.get_param_values(model_info)
# No parameters for this model.
if names == None or len(names) == 0:
model_lower.append([])
model_upper.append([])
model_inc.append([])
continue
# The parameter number.
n = len(names)
# Make sure that the length of the parameter array is > 0.
if n == 0:
raise RelaxError("Cannot run a grid search on a model with zero parameters.")
# Check that the user supplied bound lengths are ok.
if lower != None and len(lower) != n:
raise RelaxLenError('lower bounds', n)
if upper != None and len(upper) != n:
raise RelaxLenError('upper bounds', n)
# Check the user supplied increments.
if isinstance(inc, list) and len(inc) != n:
raise RelaxLenError('increment', n)
if isinstance(inc, list):
for i in range(n):
if not (isinstance(inc[i], int) or inc[i] == None):
raise RelaxIntListIntError('increment', inc)
elif not isinstance(inc, int):
raise RelaxIntListIntError('increment', inc)
# Convert to the model increment list.
if isinstance(inc, int):
model_inc.append([inc]*n)
else:
model_inc.append(inc)
# Print out the model title.
api.print_model_title(prefix="Grid search setup: ", model_info=model_info)
# The grid zoom level.
zoom = 0
if hasattr(cdp, 'grid_zoom_level'):
zoom = cdp.grid_zoom_level
zoom_factor = 1.0 / 2.0**zoom
if zoom > 0:
print("Zooming grid level of %s, scaling the grid size by a factor of %s.\n" % (zoom, zoom_factor))
# Append empty lists for the bounds to be built up.
model_lower.append([])
model_upper.append([])
# Loop over the parameters.
data = []
for i in range(n):
# A comment for user feedback.
comment = 'Default bounds'
if lower != None and upper != None:
comment = 'User supplied lower and upper bound'
elif lower != None:
comment = 'User supplied lower bound'
elif upper != None:
comment = 'User supplied upper bound'
# Alias the number of increments for this parameter.
incs = model_inc[-1][i]
# Error checking for increment values of None.
if incs == None and values[i] in [None, {}, []]:
raise RelaxError("The parameter '%s' has no preset value, therefore a grid increment of None is not valid." % names[i])
# The lower bound for this parameter.
if lower != None:
lower_i = lower[i]
else:
lower_i = param_object.grid_lower(names[i], incs=incs, model_info=model_info)
# The upper bound for this parameter.
if upper != None:
upper_i = upper[i]
else:
upper_i = param_object.grid_upper(names[i], incs=incs, model_info=model_info)
# The skipping logic.
skip = False
if skip_preset:
# Override the flag if the zoom is on.
if zoom:
skip = False
# No preset value.
elif values[i] in [None, {}, []]:
skip = False
# The preset value is a NaN value due to numpy conversions of None.
elif isNaN(values[i]):
skip = False
# Ok, now the parameter can be skipped.
else:
skip = True
# Override the skip flag if the incs value is None.
if incs == None:
skip = True
# Skip preset values.
if skip:
lower_i = values[i]
upper_i = values[i]
model_inc[-1][i] = incs = 1
comment = 'Preset value'
# Zooming grid.
elif zoom:
# The full size and scaled size.
size = upper_i - lower_i
zoom_size = size * zoom_factor
half_size = zoom_size / 2.0
comment = 'Zoom grid width of %s %s' % (zoom_size, param_object.units(names[i]))
# The new size around the current value.
lower_zoom = values[i] - half_size
upper_zoom = values[i] + half_size
# Outside of the original lower bound, so shift the grid to fit.
if zoom > 0 and lower_zoom < lower_i:
# The amount to shift by.
shift = lower_i - lower_zoom
# Set the new bounds.
upper_i = upper_zoom + shift
# Outside of the original upper bound, so shift the grid to fit.
elif zoom > 0 and upper_zoom > upper_i:
# The amount to shift by.
shift = upper_i - upper_zoom
# Set the new bounds.
lower_i = lower_zoom + shift
# Inside the original bounds.
else:
lower_i = lower_zoom
upper_i = upper_zoom
# Add to the data list for printing out.
data.append([names[i], "%15s" % lower_i, "%15s" % upper_i, "%15s" % incs, comment])
# Scale the bounds.
scaling = param_object.scaling(names[i], model_info=model_info)
lower_i /= scaling
upper_i /= scaling
# Append.
model_lower[-1].append(lower_i)
model_upper[-1].append(upper_i)
# Printout.
if verbosity:
write_data(out=sys.stdout, headings=["Parameter", "Lower bound", "Upper bound", "Increments", "Comment"], data=data)
sys.stdout.write('\n')
# Return the bounds.
return model_lower, model_upper, model_inc
def read(file=None,
dir=None,
spectrum_id=None,
dim=1,
int_col=None,
int_method=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,
ncproc=None,
verbose=True):
"""Read the peak intensity data.
@keyword file: The name of the file(s) containing the peak intensities.
@type file: str or list of str
@keyword dir: The directory where the file is located.
@type dir: str
@keyword spectrum_id: The spectrum identification string.
@type spectrum_id: str or list of str
@keyword dim: The dimension of the peak list to associate the data with.
@type dim: int
@keyword int_col: The column containing the peak intensity data (used by the generic intensity file format).
@type int_col: int or list of int
@keyword int_method: The integration method, one of 'height', 'point sum' or 'other'.
@type int_method: str
@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.
@type mol_name_col: int or None
@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.
@type res_name_col: int or None
@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.
@type res_num_col: int or None
@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.
@type spin_name_col: int or None
@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.
@type spin_num_col: int or None
@keyword sep: The column separator which, if None, defaults to whitespace.
@type sep: str or None
@keyword spin_id: The spin ID string used to restrict data loading to a subset of all spins. If 'auto' is provided for a NMRPipe seriesTab formatted file, the ID's are auto generated in form of Z_Ai.
@type spin_id: None or str
@keyword ncproc: The Bruker ncproc binary intensity scaling factor.
@type ncproc: int or None
@keyword verbose: A flag which if True will cause all relaxation data loaded to be printed out.
@type verbose: bool
"""
# Data checks.
check_pipe()
check_mol_res_spin_data()
# Check the file name.
if file == None:
raise RelaxError("The file name must be supplied.")
# Test that the intensity measures are identical.
if hasattr(cdp, 'int_method') and cdp.int_method != int_method:
raise RelaxError(
"The '%s' measure of peak intensities does not match '%s' of the previously loaded spectra."
% (int_method, cdp.int_method))
# Multiple ID flags.
flag_multi = False
flag_multi_file = False
flag_multi_col = False
if isinstance(spectrum_id, list) or spectrum_id == 'auto':
flag_multi = True
if isinstance(file, list):
flag_multi_file = True
if isinstance(int_col, list) or spectrum_id == 'auto':
flag_multi_col = True
# List argument checks.
if flag_multi:
# Too many lists.
if flag_multi_file and flag_multi_col:
raise RelaxError(
"If a list of spectrum IDs is supplied, the file names and intensity column arguments cannot both be lists."
)
# Not enough lists.
if not flag_multi_file and not flag_multi_col:
raise RelaxError(
"If a list of spectrum IDs is supplied, either the file name or intensity column arguments must be a list of equal length."
)
# List lengths for multiple files.
if flag_multi_file and len(spectrum_id) != len(file):
raise RelaxError(
"The file list %s and spectrum ID list %s do not have the same number of elements."
% (file, spectrum_id))
# List lengths for multiple intensity columns.
if flag_multi_col and spectrum_id != 'auto' and len(
spectrum_id) != len(int_col):
raise RelaxError(
"The spectrum ID list %s and intensity column list %s do not have the same number of elements."
% (spectrum_id, int_col))
# More list argument checks (when only one spectrum ID is supplied).
else:
# Multiple files.
if flag_multi_file:
raise RelaxError(
"If multiple files are supplied, then multiple spectrum IDs must also be supplied."
)
# Multiple intensity columns.
if flag_multi_col:
raise RelaxError(
"If multiple intensity columns are supplied, then multiple spectrum IDs must also be supplied."
)
# Intensity column checks.
if spectrum_id != 'auto' and not flag_multi and flag_multi_col:
raise RelaxError(
"If a list of intensity columns is supplied, the spectrum ID argument must also be a list of equal length."
)
# Check the intensity measure.
if not int_method in ['height', 'point sum', 'other']:
raise RelaxError(
"The intensity measure '%s' is not one of 'height', 'point sum', 'other'."
% int_method)
# Set the peak intensity measure.
cdp.int_method = int_method
# Convert the file argument to a list if necessary.
if not isinstance(file, list):
file = [file]
# Loop over all files.
for file_index in range(len(file)):
# Read the peak list data.
peak_list = read_peak_list(file=file[file_index],
dir=dir,
int_col=int_col,
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,
sep=sep,
spin_id=spin_id)
# Automatic spectrum IDs.
if spectrum_id == 'auto':
spectrum_id = peak_list[0].intensity_name
# Loop over the assignments.
data = []
data_flag = False
for assign in peak_list:
# Generate the spin_id.
spin_id = generate_spin_id_unique(res_num=assign.res_nums[dim - 1],
spin_name=assign.spin_names[dim -
1])
# Convert the intensity data to a list if needed.
intensity = assign.intensity
if not isinstance(intensity, list):
intensity = [intensity]
# Loop over the intensity data.
for int_index in range(len(intensity)):
# Sanity check.
if intensity[int_index] == 0.0:
warn(
RelaxWarning(
"A peak intensity of zero has been encountered for the spin '%s' - this could be fatal later on."
% spin_id))
# Get the spin container.
spin = return_spin(spin_id=spin_id)
if not spin:
warn(RelaxNoSpinWarning(spin_id))
continue
# Skip deselected spins.
if not spin.select:
continue
# Initialise.
if not hasattr(spin, 'peak_intensity'):
spin.peak_intensity = {}
# Intensity scaling.
if ncproc != None:
intensity[int_index] = intensity[int_index] / float(2**
ncproc)
# Add the data.
if flag_multi_file:
id = spectrum_id[file_index]
elif flag_multi_col:
id = spectrum_id[int_index]
else:
id = spectrum_id
spin.peak_intensity[id] = intensity[int_index]
# Switch the flag.
data_flag = True
# Append the data for printing out.
data.append([spin_id, repr(intensity[int_index])])
# Add the spectrum id (and ncproc) to the relax data store.
spectrum_ids = spectrum_id
if isinstance(spectrum_id, str):
spectrum_ids = [spectrum_id]
if ncproc != None and not hasattr(cdp, 'ncproc'):
cdp.ncproc = {}
for i in range(len(spectrum_ids)):
add_spectrum_id(spectrum_ids[i])
if ncproc != None:
cdp.ncproc[spectrum_ids[i]] = ncproc
# No data.
if not data_flag:
# Delete all the data.
delete(spectrum_id)
# Raise the error.
raise RelaxError("No data could be loaded from the peak list")
# Printout.
if verbose:
print(
"\nThe following intensities have been loaded into the relax data store:\n"
)
write_data(out=sys.stdout,
headings=["Spin_ID", "Intensity"],
data=data)
print('')
def define(spin_id1=None, spin_id2=None, pipe=None, direct_bond=False, verbose=True):
"""Set up the magnetic dipole-dipole interaction.
@keyword spin_id1: The spin identifier string of the first spin of the pair.
@type spin_id1: str
@keyword spin_id2: The spin identifier string of the second spin of the pair.
@type spin_id2: str
@param pipe: The data pipe to operate on. Defaults to the current data pipe.
@type pipe: str
@keyword direct_bond: A flag specifying if the two spins are directly bonded.
@type direct_bond: bool
@keyword verbose: A flag which if True will result in printouts of the created interatomoic data containers.
@type verbose: bool
"""
# The data pipe.
if pipe == None:
pipe = pipes.cdp_name()
# Get the data pipe.
dp = pipes.get_pipe(pipe)
# Loop over both spin selections.
ids = []
for spin1, mol_name1, res_num1, res_name1, id1 in spin_loop(spin_id1, pipe=pipe, full_info=True, return_id=True):
for spin2, mol_name2, res_num2, res_name2, id2 in spin_loop(spin_id2, pipe=pipe, full_info=True, return_id=True):
# Directly bonded atoms.
if direct_bond:
# Different molecules.
if mol_name1 != mol_name2:
continue
# From structural info.
if hasattr(dp, 'structure') and dp.structure.get_molecule(mol_name1, model=1):
if not dp.structure.are_bonded(atom_id1=id1, atom_id2=id2):
continue
# From the residue info.
else:
# No element info.
if not hasattr(spin1, 'element'):
raise RelaxError("The spin '%s' does not have the element type set." % id1)
if not hasattr(spin2, 'element'):
raise RelaxError("The spin '%s' does not have the element type set." % id2)
# Backbone NH and CH pairs.
pair = False
if (spin1.element == 'N' and spin2.element == 'H') or (spin2.element == 'N' and spin1.element == 'H'):
pair = True
elif (spin1.element == 'C' and spin2.element == 'H') or (spin2.element == 'C' and spin1.element == 'H'):
pair = True
# Same residue, so skip.
if pair and res_num1 != None and res_num1 != res_num2:
continue
elif pair and res_num1 == None and res_name1 != res_name2:
continue
# Get the interatomic data object, if it exists.
interatom = return_interatom(id1, id2, pipe=pipe)
# Create the container if needed.
if interatom == None:
interatom = create_interatom(spin_id1=id1, spin_id2=id2, pipe=pipe)
# Check that this has not already been set up.
if interatom.dipole_pair:
raise RelaxError("The magnetic dipole-dipole interaction already exists between the spins '%s' and '%s'." % (id1, id2))
# Set a flag indicating that a dipole-dipole interaction is present.
interatom.dipole_pair = True
# Store the IDs for the printout.
ids.append([repr(id1), repr(id2)])
# No matches, so fail!
if not len(ids):
# Find the problem.
count1 = 0
count2 = 0
for spin in spin_loop(spin_id1):
count1 += 1
for spin in spin_loop(spin_id2):
count2 += 1
# Report the problem.
if count1 == 0 and count2 == 0:
raise RelaxError("Neither spin IDs '%s' and '%s' match any spins." % (spin_id1, spin_id2))
elif count1 == 0:
raise RelaxError("The spin ID '%s' matches no spins." % spin_id1)
elif count2 == 0:
raise RelaxError("The spin ID '%s' matches no spins." % spin_id2)
else:
raise RelaxError("Unknown error.")
# Print out.
if verbose:
print("Interatomic interactions are now defined for the following spins:\n")
write_data(out=sys.stdout, headings=["Spin_ID_1", "Spin_ID_2"], data=ids)
def read(file=None, dir=None, file_data=None, spin_id1_col=None, spin_id2_col=None, data_col=None, error_col=None, sign_col=None, sep=None):
"""Read the J coupling data from file.
@keyword file: The name of the file to open.
@type file: str
@keyword dir: The directory containing the file (defaults to the current directory if None).
@type dir: str or None
@keyword file_data: An alternative to opening a file, if the data already exists in the correct format. The format is a list of lists where the first index corresponds to the row and the second the column.
@type file_data: list of lists
@keyword spin_id1_col: The column containing the spin ID strings of the first spin.
@type spin_id1_col: int
@keyword spin_id2_col: The column containing the spin ID strings of the second spin.
@type spin_id2_col: int
@keyword data_col: The column containing the J coupling data in Hz.
@type data_col: int or None
@keyword error_col: The column containing the J coupling errors.
@type error_col: int or None
@keyword sign_col: The optional column containing the sign of the J coupling.
@type sign_col: int or None
@keyword sep: The column separator which, if None, defaults to whitespace.
@type sep: str or None
"""
# Check the pipe setup.
check_pipe_setup(sequence=True)
# Either the data or error column must be supplied.
if data_col == None and error_col == None:
raise RelaxError("One of either the data or error column must be supplied.")
# Extract the data from the file, and remove comments and blank lines.
file_data = extract_data(file, dir, sep=sep)
file_data = strip(file_data, comments=True)
# Loop over the J coupling data.
data = []
for line in file_data:
# Invalid columns.
if spin_id1_col > len(line):
warn(RelaxWarning("The data %s is invalid, no first spin ID column can be found." % line))
continue
if spin_id2_col > len(line):
warn(RelaxWarning("The data %s is invalid, no second spin ID column can be found." % line))
continue
if data_col and data_col > len(line):
warn(RelaxWarning("The data %s is invalid, no data column can be found." % line))
continue
if error_col and error_col > len(line):
warn(RelaxWarning("The data %s is invalid, no error column can be found." % line))
continue
if sign_col and sign_col > len(line):
warn(RelaxWarning("The data %s is invalid, no sign column can be found." % line))
continue
# Unpack.
spin_id1 = line[spin_id1_col-1]
spin_id2 = line[spin_id2_col-1]
value = None
if data_col:
value = line[data_col-1]
error = None
if error_col:
error = line[error_col-1]
sign = None
if sign_col:
sign = line[sign_col-1]
# Convert the spin IDs.
if spin_id1[0] in ["\"", "\'"]:
spin_id1 = eval(spin_id1)
if spin_id2[0] in ["\"", "\'"]:
spin_id2 = eval(spin_id2)
# Convert and check the value.
if value == 'None':
value = None
if value != None:
try:
value = float(value)
except ValueError:
warn(RelaxWarning("The J coupling value of the line %s is invalid." % line))
continue
# The sign data.
if sign == 'None':
sign = None
if sign != None:
try:
sign = float(sign)
except ValueError:
warn(RelaxWarning("The J coupling sign of the line %s is invalid." % line))
continue
if sign not in [1.0, -1.0]:
warn(RelaxWarning("The J coupling sign of the line %s is invalid." % line))
continue
# Convert and check the error.
if error == 'None':
error = None
if error != None:
try:
error = float(error)
except ValueError:
warn(RelaxWarning("The error value of the line %s is invalid." % line))
continue
# Get the spins.
spin1 = return_spin(spin_id1)
spin2 = return_spin(spin_id2)
# Check the spin IDs.
if not spin1:
warn(RelaxWarning("The spin ID '%s' cannot be found in the current data pipe, skipping the data %s." % (spin_id1, line)))
continue
if not spin2:
warn(RelaxWarning("The spin ID '%s' cannot be found in the current data pipe, skipping the data %s." % (spin_id2, line)))
continue
# Test the error value (cannot be 0.0).
if error == 0.0:
raise RelaxError("An invalid error value of zero has been encountered.")
# Get the interatomic data container.
interatom = return_interatom(spin_id1, spin_id2)
# Create the container if needed.
if interatom == None:
interatom = create_interatom(spin_id1=spin_id1, spin_id2=spin_id2)
# Add the data.
if data_col:
# Sign conversion.
if sign != None:
value = value * sign
# Add the value.
interatom.j_coupling = value
# Add the error.
if error_col:
interatom.j_coupling_err = error
# Append the data for printout.
data.append([spin_id1, spin_id2])
if is_float(value):
data[-1].append("%20.15f" % value)
else:
data[-1].append("%20s" % value)
if is_float(error):
data[-1].append("%20.15f" % error)
else:
data[-1].append("%20s" % error)
# No data, so fail hard!
if not len(data):
raise RelaxError("No J coupling data could be extracted.")
# Print out.
print("The following J coupling have been loaded into the relax data store:\n")
write_data(out=sys.stdout, headings=["Spin_ID1", "Spin_ID2", "Value", "Error"], data=data)
def signal_noise_ratio(verbose=True):
"""Calculate the signal to noise ratio per spin.
@keyword verbose: A flag which if True will print additional information out.
@type verbose: bool
"""
# Tests.
check_pipe()
check_mol_res_spin_data()
# Test if spectra have been loaded.
if not hasattr(cdp, 'spectrum_ids'):
raise RelaxError("No spectra have been loaded.")
# Possible print.
if verbose:
print("\nThe following signal to noise ratios has been calculated:\n")
# Set the spin specific signal to noise ratio.
for spin, spin_id in spin_loop(return_id=True):
# Skip deselected spins.
if not spin.select:
continue
# Skip spins missing intensity data.
if not hasattr(spin, 'peak_intensity'):
continue
# Test if error analysis has been performed.
if not hasattr(spin, 'peak_intensity_err'):
raise RelaxError(
"Intensity error analysis has not been performed. Please see spectrum.error_analysis()."
)
# If necessary, create the dictionary.
if not hasattr(spin, 'sn_ratio'):
spin.sn_ratio = {}
# Loop over the ID.
ids = []
for id in spin.peak_intensity:
# Append the ID to the list.
ids.append(id)
# Calculate the sn_ratio.
pint = float(spin.peak_intensity[id])
pint_err = float(spin.peak_intensity_err[id])
sn_ratio = pint / pint_err
# Assign the sn_ratio.
spin.sn_ratio[id] = sn_ratio
# Sort the ids alphanumeric.
ids = sort_filenames(filenames=ids, rev=False)
# Collect the data under sorted ids.
data_i = []
for id in ids:
# Get the values.
pint = spin.peak_intensity[id]
pint_err = spin.peak_intensity_err[id]
sn_ratio = spin.sn_ratio[id]
# Store the data.
data_i.append([id, repr(pint), repr(pint_err), repr(sn_ratio)])
if verbose:
section(file=sys.stdout,
text="Signal to noise ratio for spin ID '%s'" % spin_id,
prespace=1)
write_data(out=sys.stdout,
headings=["Spectrum ID", "Signal", "Noise", "S/N"],
data=data_i)
def define_dipole_pair(spin_id1=None, spin_id2=None, spin1=None, spin2=None, pipe=None, direct_bond=False, spin_selection=False, verbose=True):
"""Set up the magnetic dipole-dipole interaction.
@keyword spin_id1: The spin identifier string of the first spin of the pair.
@type spin_id1: str
@keyword spin_id2: The spin identifier string of the second spin of the pair.
@type spin_id2: str
@keyword spin1: An optional single spin container for the first atom. This is for speeding up the interatomic data container creation, if the spin containers are already available in the calling function.
@type spin1: str
@keyword spin2: An optional single spin container for the second atom. This is for speeding up the interatomic data container creation, if the spin containers are already available in the calling function.
@type spin2: str
@param pipe: The data pipe to operate on. Defaults to the current data pipe.
@type pipe: str
@keyword direct_bond: A flag specifying if the two spins are directly bonded.
@type direct_bond: bool
@keyword spin_selection: Define the interatomic data container selection based on the spin selection. If either spin is deselected, the interatomic container will also be deselected. Otherwise the container will be selected.
@type spin_selection: bool
@keyword verbose: A flag which if True will result in printouts of the created interatomoic data containers.
@type verbose: bool
"""
# The data pipe.
if pipe == None:
pipe = pipes.cdp_name()
# Get the data pipe.
dp = pipes.get_pipe(pipe)
# Initialise data structures for storing spin data.
ids = []
spins = []
spin_selections = []
# Pre-supplied spins.
if spin1 and spin2:
# Store the IDs for the printout.
ids.append([spin_id1, spin_id2])
# Store the spin data.
spins.append([spin1, spin2])
spin_selections.append([spin1.select, spin2.select])
# Use the structural data to find connected atoms.
elif hasattr(dp, 'structure'):
# The selection objects.
selection1 = cdp.structure.selection(atom_id=spin_id1)
selection2 = cdp.structure.selection(atom_id=spin_id2)
# Loop over the atoms of the first spin selection.
for mol_name1, res_num1, res_name1, atom_num1, atom_name1, mol_index1, atom_index1 in dp.structure.atom_loop(selection=selection1, model_num=1, mol_name_flag=True, res_num_flag=True, res_name_flag=True, atom_num_flag=True, atom_name_flag=True, mol_index_flag=True, index_flag=True):
# Generate the first spin ID.
id1 = generate_spin_id_unique(pipe_cont=dp, mol_name=mol_name1, res_num=res_num1, res_name=res_name1, spin_num=atom_num1, spin_name=atom_name1)
# Do the spin exist?
spin1 = return_spin(spin_id=id1)
if not spin1:
continue
# Loop over the atoms of the second spin selection.
for mol_name2, res_num2, res_name2, atom_num2, atom_name2, mol_index2, atom_index2 in dp.structure.atom_loop(selection=selection2, model_num=1, mol_name_flag=True, res_num_flag=True, res_name_flag=True, atom_num_flag=True, atom_name_flag=True, mol_index_flag=True, index_flag=True):
# Directly bonded atoms.
if direct_bond:
# Different molecules.
if mol_name1 != mol_name2:
continue
# Skip non-bonded atom pairs.
if not dp.structure.are_bonded_index(mol_index1=mol_index1, atom_index1=atom_index1, mol_index2=mol_index2, atom_index2=atom_index2):
continue
# Generate the second spin ID.
id2 = generate_spin_id_unique(pipe_cont=dp, mol_name=mol_name2, res_num=res_num2, res_name=res_name2, spin_num=atom_num2, spin_name=atom_name2)
# Do the spin exist?
spin2 = return_spin(spin_id=id2)
if not spin2:
continue
# Store the IDs for the printout.
ids.append([id1, id2])
# Store the spin data.
spins.append([spin1, spin2])
spin_selections.append([spin1.select, spin2.select])
# No structural data present or the spin IDs are not in the structural data, so use spin loops and some basic rules.
if ids == []:
for spin1, mol_name1, res_num1, res_name1, id1 in spin_loop(spin_id1, pipe=pipe, full_info=True, return_id=True):
for spin2, mol_name2, res_num2, res_name2, id2 in spin_loop(spin_id2, pipe=pipe, full_info=True, return_id=True):
# Directly bonded atoms.
if direct_bond:
# Different molecules.
if mol_name1 != mol_name2:
continue
# No element info.
if not hasattr(spin1, 'element'):
raise RelaxError("The spin '%s' does not have the element type set." % id1)
if not hasattr(spin2, 'element'):
raise RelaxError("The spin '%s' does not have the element type set." % id2)
# Backbone NH and CH pairs.
pair = False
if (spin1.element == 'N' and spin2.element == 'H') or (spin2.element == 'N' and spin1.element == 'H'):
pair = True
elif (spin1.element == 'C' and spin2.element == 'H') or (spin2.element == 'C' and spin1.element == 'H'):
pair = True
# Same residue, so skip.
if pair and res_num1 != None and res_num1 != res_num2:
continue
elif pair and res_num1 == None and res_name1 != res_name2:
continue
# Store the IDs for the printout.
ids.append([id1, id2])
# Store the spin data.
spins.append([spin1, spin2])
spin_selections.append([spin1.select, spin2.select])
# No matches, so fail!
if not len(ids):
# Find the problem.
count1 = 0
count2 = 0
for spin in spin_loop(spin_id1):
count1 += 1
for spin in spin_loop(spin_id2):
count2 += 1
# Report the problem.
if count1 == 0 and count2 == 0:
raise RelaxError("Neither spin IDs '%s' and '%s' match any spins." % (spin_id1, spin_id2))
elif count1 == 0:
raise RelaxError("The spin ID '%s' matches no spins." % spin_id1)
elif count2 == 0:
raise RelaxError("The spin ID '%s' matches no spins." % spin_id2)
else:
raise RelaxError("Unknown error.")
# Define the interaction.
for i in range(len(ids)):
# Unpack.
id1, id2 = ids[i]
spin1, spin2 = spins[i]
# Get the interatomic data object, if it exists.
interatom = return_interatom(spin_hash1=spin1._hash, spin_hash2=spin2._hash, pipe=pipe)
# Create the container if needed.
if interatom == None:
interatom = create_interatom(spin_id1=id1, spin_id2=id2, spin1=spins[i][0], spin2=spins[i][1], pipe=pipe)
# Check that this has not already been set up.
if interatom.dipole_pair:
raise RelaxError("The magnetic dipole-dipole interaction already exists between the spins '%s' and '%s'." % (id1, id2))
# Set a flag indicating that a dipole-dipole interaction is present.
interatom.dipole_pair = True
# Set the selection.
if spin_selection:
interatom.select = False
if spin_selections[i][0] and spin_selections[i][1]:
interatom.select = True
# Printout.
if verbose:
# Conversion.
for i in range(len(ids)):
ids[i][0] = repr(ids[i][0])
ids[i][1] = repr(ids[i][1])
# The printout.
print("Interatomic interactions are now defined for the following spins:\n")
write_data(out=sys.stdout, headings=["Spin_ID_1", "Spin_ID_2"], data=ids)
def copy(pipe_from=None, pipe_to=None, spin_id1=None, spin_id2=None, verbose=True):
"""Copy the interatomic data from one data pipe to another.
@keyword pipe_from: The data pipe to copy the interatomic data from. This defaults to the current data pipe.
@type pipe_from: str
@keyword pipe_to: The data pipe to copy the interatomic data to. This defaults to the current data pipe.
@type pipe_to: str
@keyword spin_id1: The spin ID string of the first atom.
@type spin_id1: str
@keyword spin_id2: The spin ID string of the second atom.
@type spin_id2: str
@keyword verbose: A flag which if True will cause info about each spin pair to be printed out.
@type verbose: bool
"""
# Defaults.
if pipe_from == None and pipe_to == None:
raise RelaxError("The pipe_from and pipe_to arguments cannot both be set to None.")
elif pipe_from == None:
pipe_from = pipes.cdp_name()
elif pipe_to == None:
pipe_to = pipes.cdp_name()
# Test if the pipe_from and pipe_to data pipes exist.
check_pipe(pipe_from)
check_pipe(pipe_to)
# Check that the spin IDs exist.
if spin_id1:
if count_spins(selection=spin_id1, pipe=pipe_from, skip_desel=False) == 0:
raise RelaxNoSpinError(spin_id1, pipe_from)
if count_spins(selection=spin_id1, pipe=pipe_to, skip_desel=False) == 0:
raise RelaxNoSpinError(spin_id1, pipe_to)
if spin_id2:
if count_spins(selection=spin_id2, pipe=pipe_from, skip_desel=False) == 0:
raise RelaxNoSpinError(spin_id2, pipe_from)
if count_spins(selection=spin_id2, pipe=pipe_to, skip_desel=False) == 0:
raise RelaxNoSpinError(spin_id2, pipe_to)
# Check for the sequence data in the target pipe if no spin IDs are given.
if not spin_id1 and not spin_id2:
for spin, spin_id in spin_loop(pipe=pipe_from, return_id=True):
if not return_spin(spin_id=spin_id, pipe=pipe_to):
raise RelaxNoSpinError(spin_id, pipe_to)
# Test if pipe_from contains interatomic data (skipping the rest of the function if it is missing).
if not exists_data(pipe_from):
return
# Loop over the interatomic data of the pipe_from data pipe.
ids = []
for interatom in interatomic_loop(selection1=spin_id1, selection2=spin_id2, pipe=pipe_from):
# Create a new container.
new_interatom = create_interatom(spin_id1=interatom.spin_id1, spin_id2=interatom.spin_id2, pipe=pipe_to)
# Duplicate all the objects of the container.
for name in dir(interatom):
# Skip special objects.
if search('^_', name):
continue
# Skip the spin IDs.
if name in ['spin_id1', 'spin_id2']:
continue
# Skip class methods.
if name in interatom.__class__.__dict__:
continue
# Duplicate all other objects.
obj = deepcopy(getattr(interatom, name))
setattr(new_interatom, name, obj)
# Store the IDs for the printout.
ids.append([repr(interatom.spin_id1), repr(interatom.spin_id2)])
# Reconfigure the spin hashes.
hash_update(interatom=new_interatom, pipe=pipe_to)
# Print out.
if verbose:
write_data(out=sys.stdout, headings=["Spin_ID_1", "Spin_ID_2"], data=ids)
def read(file=None, dir=None, file_data=None, spin_id1_col=None, spin_id2_col=None, data_col=None, error_col=None, sign_col=None, sep=None):
"""Read the J coupling data from file.
@keyword file: The name of the file to open.
@type file: str
@keyword dir: The directory containing the file (defaults to the current directory if None).
@type dir: str or None
@keyword file_data: An alternative to opening a file, if the data already exists in the correct format. The format is a list of lists where the first index corresponds to the row and the second the column.
@type file_data: list of lists
@keyword spin_id1_col: The column containing the spin ID strings of the first spin.
@type spin_id1_col: int
@keyword spin_id2_col: The column containing the spin ID strings of the second spin.
@type spin_id2_col: int
@keyword data_col: The column containing the J coupling data in Hz.
@type data_col: int or None
@keyword error_col: The column containing the J coupling errors.
@type error_col: int or None
@keyword sign_col: The optional column containing the sign of the J coupling.
@type sign_col: int or None
@keyword sep: The column separator which, if None, defaults to whitespace.
@type sep: str or None
"""
# Check the pipe setup.
check_pipe_setup(sequence=True)
# Either the data or error column must be supplied.
if data_col == None and error_col == None:
raise RelaxError("One of either the data or error column must be supplied.")
# Extract the data from the file, and remove comments and blank lines.
file_data = extract_data(file, dir, sep=sep)
file_data = strip(file_data, comments=True)
# Loop over the J coupling data.
data = []
for line in file_data:
# Invalid columns.
if spin_id1_col > len(line):
warn(RelaxWarning("The data %s is invalid, no first spin ID column can be found." % line))
continue
if spin_id2_col > len(line):
warn(RelaxWarning("The data %s is invalid, no second spin ID column can be found." % line))
continue
if data_col and data_col > len(line):
warn(RelaxWarning("The data %s is invalid, no data column can be found." % line))
continue
if error_col and error_col > len(line):
warn(RelaxWarning("The data %s is invalid, no error column can be found." % line))
continue
if sign_col and sign_col > len(line):
warn(RelaxWarning("The data %s is invalid, no sign column can be found." % line))
continue
# Unpack.
spin_id1 = line[spin_id1_col-1]
spin_id2 = line[spin_id2_col-1]
value = None
if data_col:
value = line[data_col-1]
error = None
if error_col:
error = line[error_col-1]
sign = None
if sign_col:
sign = line[sign_col-1]
# Convert the spin IDs.
if spin_id1[0] in ["\"", "\'"]:
spin_id1 = eval(spin_id1)
if spin_id2[0] in ["\"", "\'"]:
spin_id2 = eval(spin_id2)
# Convert and check the value.
if value == 'None':
value = None
if value != None:
try:
value = float(value)
except ValueError:
warn(RelaxWarning("The J coupling value of the line %s is invalid." % line))
continue
# The sign data.
if sign == 'None':
sign = None
if sign != None:
try:
sign = float(sign)
except ValueError:
warn(RelaxWarning("The J coupling sign of the line %s is invalid." % line))
continue
if sign not in [1.0, -1.0]:
warn(RelaxWarning("The J coupling sign of the line %s is invalid." % line))
continue
# Convert and check the error.
if error == 'None':
error = None
if error != None:
try:
error = float(error)
except ValueError:
warn(RelaxWarning("The error value of the line %s is invalid." % line))
continue
# Get the spins.
spin1 = return_spin(spin_id=spin_id1)
spin2 = return_spin(spin_id=spin_id2)
# Check the spin IDs.
if not spin1:
warn(RelaxWarning("The spin ID '%s' cannot be found in the current data pipe, skipping the data %s." % (spin_id1, line)))
continue
if not spin2:
warn(RelaxWarning("The spin ID '%s' cannot be found in the current data pipe, skipping the data %s." % (spin_id2, line)))
continue
# Test the error value (cannot be 0.0).
if error == 0.0:
raise RelaxError("An invalid error value of zero has been encountered.")
# Get the interatomic data container.
interatom = return_interatom(spin_hash1=spin1._hash, spin_hash2=spin2._hash)
# Create the container if needed.
if interatom == None:
interatom = create_interatom(spin_id1=spin_id1, spin_id2=spin_id2)
# Add the data.
if data_col:
# Sign conversion.
if sign != None:
value = value * sign
# Add the value.
interatom.j_coupling = value
# Add the error.
if error_col:
interatom.j_coupling_err = error
# Append the data for printout.
data.append([spin_id1, spin_id2])
if is_float(value):
data[-1].append("%20.15f" % value)
else:
data[-1].append("%20s" % value)
if is_float(error):
data[-1].append("%20.15f" % error)
else:
data[-1].append("%20s" % error)
# No data, so fail hard!
if not len(data):
raise RelaxError("No J coupling data could be extracted.")
# Print out.
print("The following J coupling have been loaded into the relax data store:\n")
write_data(out=sys.stdout, headings=["Spin_ID1", "Spin_ID2", "Value", "Error"], data=data)
def read_dist(file=None, dir=None, unit='meter', spin_id1_col=None, spin_id2_col=None, data_col=None, sep=None):
"""Set up the magnetic dipole-dipole interaction.
@keyword file: The name of the file to open.
@type file: str
@keyword dir: The directory containing the file (defaults to the current directory if None).
@type dir: str or None
@keyword unit: The measurement unit. This can be either 'meter' or 'Angstrom'.
@type unit: str
@keyword spin_id1_col: The column containing the spin ID strings of the first spin.
@type spin_id1_col: int
@keyword spin_id2_col: The column containing the spin ID strings of the second spin.
@type spin_id2_col: int
@keyword data_col: The column containing the averaged distances in meters.
@type data_col: int or None
@keyword sep: The column separator which, if None, defaults to whitespace.
@type sep: str or None
"""
# Check the units.
if unit not in ['meter', 'Angstrom']:
raise RelaxError("The measurement unit of '%s' must be one of 'meter' or 'Angstrom'." % unit)
# Test if the current data pipe exists.
check_pipe()
# Test if sequence data exists.
if not exists_mol_res_spin_data():
raise RelaxNoSequenceError
# Extract the data from the file, and clean it up.
file_data = extract_data(file, dir, sep=sep)
file_data = strip(file_data, comments=True)
# Loop over the RDC data.
data = []
for line in file_data:
# Invalid columns.
if spin_id1_col > len(line):
warn(RelaxWarning("The data %s is invalid, no first spin ID column can be found." % line))
continue
if spin_id2_col > len(line):
warn(RelaxWarning("The data %s is invalid, no second spin ID column can be found." % line))
continue
if data_col and data_col > len(line):
warn(RelaxWarning("The data %s is invalid, no data column can be found." % line))
continue
# Unpack.
spin_id1 = line[spin_id1_col-1]
spin_id2 = line[spin_id2_col-1]
ave_dist = None
if data_col:
ave_dist = line[data_col-1]
# Convert and check the value.
if ave_dist != None:
try:
ave_dist = float(ave_dist)
except ValueError:
warn(RelaxWarning("The averaged distance of '%s' from the line %s is invalid." % (ave_dist, line)))
continue
# Unit conversion.
if unit == 'Angstrom':
ave_dist = ave_dist * 1e-10
# Get the interatomic data container.
spin1 = return_spin(spin_id=spin_id1)
spin2 = return_spin(spin_id=spin_id2)
interatom = return_interatom(spin_hash1=spin1._hash, spin_hash2=spin2._hash)
# No container found, so create it.
if interatom == None:
interatom = create_interatom(spin_id1=spin_id1, spin_id2=spin_id2, verbose=True)
# Store the averaged distance.
interatom.r = ave_dist
# Store the data for the printout.
data.append([repr(interatom.spin_id1), repr(interatom.spin_id2), repr(ave_dist)])
# No data, so fail!
if not len(data):
raise RelaxError("No data could be extracted from the file.")
# Print out.
print("The following averaged distances have been read:\n")
write_data(out=sys.stdout, headings=["Spin_ID_1", "Spin_ID_2", "Ave_distance(meters)"], data=data)
def get_pos(spin_id=None, str_id=None, ave_pos=False):
"""Load the spins from the structural object into the relax data store.
@keyword spin_id: The molecule, residue, and spin identifier string.
@type spin_id: str
@keyword str_id: The structure identifier. This can be the file name, model number, or structure number.
@type str_id: int or str
@keyword ave_pos: A flag specifying if the average atom position or the atom position from all loaded structures is loaded into the SpinContainer.
@type ave_pos: bool
"""
# Test if the current data pipe exists.
pipes.test()
# Test if the structure exists.
if not hasattr(cdp, 'structure') or not cdp.structure.num_models() or not cdp.structure.num_molecules():
raise RelaxNoPdbError
# Loop over all atoms of the spin_id selection.
data = []
for mol_name, res_num, res_name, atom_num, atom_name, element, pos in cdp.structure.atom_loop(atom_id=spin_id, str_id=str_id, mol_name_flag=True, res_num_flag=True, res_name_flag=True, atom_num_flag=True, atom_name_flag=True, element_flag=True, pos_flag=True, ave=ave_pos):
# Remove the '+' regular expression character from the mol, res, and spin names!
if mol_name and search('\+', mol_name):
mol_name = mol_name.replace('+', '')
if res_name and search('\+', res_name):
res_name = res_name.replace('+', '')
if atom_name and search('\+', atom_name):
atom_name = atom_name.replace('+', '')
# The spin identification string.
id = generate_spin_id_unique(res_num=res_num, res_name=None, spin_num=atom_num, spin_name=atom_name)
# Get the spin container.
spin_cont = return_spin(id)
# Skip the spin if it doesn't exist.
if spin_cont == None:
continue
# Add the position vector to the spin container.
spin_cont.pos = pos
# Store the data for a printout at the end.
data.append([id, repr(pos)])
# No positions found.
if not len(data):
raise RelaxError("No positional information matching the spin ID '%s' could be found." % spin_id)
# Update pseudo-atoms.
for spin in spin_loop():
if hasattr(spin, 'members'):
# Get the spin positions.
positions = []
for atom in spin.members:
# Get the spin container.
subspin = return_spin(atom)
# Test that the spin exists.
if subspin == None:
raise RelaxNoSpinError(atom)
# Test the position.
if not hasattr(subspin, 'pos') or subspin.pos == None or not len(subspin.pos):
raise RelaxError("Positional information is not available for the atom '%s'." % atom)
# Alias the position.
pos = subspin.pos
# Convert to a list of lists if not already.
multi_model = True
if type(pos[0]) in [float, float64]:
multi_model = False
pos = [pos]
# Store the position.
positions.append([])
for i in range(len(pos)):
positions[-1].append(pos[i].tolist())
# The averaging.
if spin.averaging == 'linear':
# Average pos.
ave = linear_ave(positions)
# Convert to the correct structure.
if multi_model:
spin.pos = ave
else:
spin.pos = ave[0]
# Print out.
write_data(out=sys.stdout, headings=["Spin_ID", "Position"], data=data)
def copy(pipe_from=None, pipe_to=None, spin_id1=None, spin_id2=None, verbose=True):
"""Copy the interatomic data from one data pipe to another.
@keyword pipe_from: The data pipe to copy the interatomic data from. This defaults to the current data pipe.
@type pipe_from: str
@keyword pipe_to: The data pipe to copy the interatomic data to. This defaults to the current data pipe.
@type pipe_to: str
@keyword spin_id1: The spin ID string of the first atom.
@type spin_id1: str
@keyword spin_id2: The spin ID string of the second atom.
@type spin_id2: str
@keyword verbose: A flag which if True will cause info about each spin pair to be printed out.
@type verbose: bool
"""
# Defaults.
if pipe_from == None and pipe_to == None:
raise RelaxError("The pipe_from and pipe_to arguments cannot both be set to None.")
elif pipe_from == None:
pipe_from = pipes.cdp_name()
elif pipe_to == None:
pipe_to = pipes.cdp_name()
# Test if the pipe_from and pipe_to data pipes exist.
pipes.test(pipe_from)
pipes.test(pipe_to)
# Check that the spin IDs exist.
if spin_id1:
if count_spins(selection=spin_id1, pipe=pipe_from, skip_desel=False) == 0:
raise RelaxNoSpinError(spin_id1, pipe_from)
if count_spins(selection=spin_id1, pipe=pipe_to, skip_desel=False) == 0:
raise RelaxNoSpinError(spin_id1, pipe_to)
if spin_id2:
if count_spins(selection=spin_id2, pipe=pipe_from, skip_desel=False) == 0:
raise RelaxNoSpinError(spin_id2, pipe_from)
if count_spins(selection=spin_id2, pipe=pipe_to, skip_desel=False) == 0:
raise RelaxNoSpinError(spin_id2, pipe_to)
# Check for the sequence data in the target pipe if no spin IDs are given.
if not spin_id1 and not spin_id2:
for spin, spin_id in spin_loop(pipe=pipe_from, return_id=True):
if not return_spin(spin_id, pipe=pipe_to):
raise RelaxNoSpinError(spin_id, pipe_to)
# Test if pipe_from contains interatomic data (skipping the rest of the function if it is missing).
if not exists_data(pipe_from):
return
# Loop over the interatomic data of the pipe_from data pipe.
ids = []
for interatom in interatomic_loop(selection1=spin_id1, selection2=spin_id2, pipe=pipe_from):
# Create a new container.
new_interatom = create_interatom(spin_id1=interatom.spin_id1, spin_id2=interatom.spin_id2, pipe=pipe_to)
# Duplicate all the objects of the container.
for name in dir(interatom):
# Skip special objects.
if search('^_', name):
continue
# Skip the spin IDs.
if name in ['spin_id1', 'spin_id2']:
continue
# Skip class methods.
if name in list(interatom.__class__.__dict__.keys()):
continue
# Duplicate all other objects.
obj = deepcopy(getattr(interatom, name))
setattr(new_interatom, name, obj)
# Store the IDs for the printout.
ids.append([repr(interatom.spin_id1), repr(interatom.spin_id2)])
# Print out.
if verbose:
write_data(out=sys.stdout, headings=["Spin_ID_1", "Spin_ID_2"], data=ids)
