def read_results(file=None, dir=None, scaling=1.0):
"""Extract the data from the Dasha results 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 scaling: The parameter scaling factor.
@type scaling: float
"""
# Extract the data.
data = extract_data(file=file, dir=dir)
# Remove comments.
data = strip(data)
# Repackage the data as a list of lists of spin ID, value, error.
new_data = []
for i in range(len(data)):
spin_id = ':%s@N' % data[i][0]
value = float(data[i][1]) * scaling
error = float(data[i][2]) * scaling
new_data.append([spin_id, value, error])
# Return the data.
return new_data
def read_results(file=None, dir=None, scaling=1.0):
"""Extract the data from the Dasha results 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 scaling: The parameter scaling factor.
@type scaling: float
"""
# Extract the data.
data = extract_data(file=file, dir=dir)
# Remove comments.
data = strip(data)
# Repackage the data as a list of lists of spin ID, value, error.
new_data = []
for i in range(len(data)):
spin_id = ':%s@N' % data[i][0]
value = float(data[i][1]) * scaling
error = float(data[i][2]) * scaling
new_data.append([spin_id, value, error])
# Return the data.
return new_data
def read(file='results', dir=None):
"""Function for reading the data out of a file."""
# Test if the current data pipe exists.
check_pipe()
# Make sure that the data pipe is empty.
if not cdp.is_empty():
raise RelaxError("The current data pipe is not empty.")
# Get the full file path, for later use.
file_path = get_file_path(file_name=file, dir=dir)
# Open the file.
file = open_read_file(file_name=file_path)
# Determine the format of the file.
format = determine_format(file)
# XML results.
if format == 'xml':
ds.from_xml(file, dir=dirname(file_path), pipe_to=pipes.cdp_name())
# Columnar results (for backwards compatibility with ancient relax results model-free files).
elif format == 'columnar':
# Extract the data from the file.
file_data = extract_data(file=file)
# Strip data.
file_data = strip(file_data)
# Do nothing if the file does not exist.
if not file_data:
raise RelaxFileEmptyError
# Read the results.
read_columnar_results(file_data)
# Unknown results file.
else:
raise RelaxError("The format of the results file " + repr(file_path) + " cannot be determined.")
# Update all of the required metadata structures.
mol_res_spin.metadata_update()
interatomic.metadata_update()
def read(file='results', dir=None):
"""Function for reading the data out of a file."""
# Test if the current data pipe exists.
check_pipe()
# Make sure that the data pipe is empty.
if not cdp.is_empty():
raise RelaxError("The current data pipe is not empty.")
# Get the full file path, for later use.
file_path = get_file_path(file_name=file, dir=dir)
# Open the file.
file = open_read_file(file_name=file_path)
# Determine the format of the file.
format = determine_format(file)
# XML results.
if format == 'xml':
ds.from_xml(file, dir=dirname(file_path), pipe_to=pipes.cdp_name())
# Columnar results (for backwards compatibility with ancient relax results model-free files).
elif format == 'columnar':
# Extract the data from the file.
file_data = extract_data(file=file)
# Strip data.
file_data = strip(file_data)
# Do nothing if the file does not exist.
if not file_data:
raise RelaxFileEmptyError
# Read the results.
read_columnar_results(file_data)
# Unknown results file.
else:
raise RelaxError("The format of the results file " + repr(file_path) + " cannot be determined.")
def intensity_generic(peak_list=None, file_data=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, data_col=None, sep=None, spin_id=None):
"""Extract the peak intensity information from the generic column formatted peak list.
@keyword peak_list: The peak list object to place all data into.
@type peak_list: lib.spectrum.objects.Peak_list instance
@keyword file_data: The data extracted from the file converted into a list of lists.
@type file_data: list of lists of 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 data_col: The column containing the peak intensities.
@type data_col: int or list of int
@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.
@type spin_id: None or str
@raises RelaxError: When the expected peak intensity is not a float.
"""
# Strip the data.
file_data = strip(file_data)
# Check the intensity column argument.
data_present = True
if data_col == None:
warn(RelaxWarning("The data column argument has not been supplied, and function will only return spin data."))
data_present = False
# Convert the the data_col argument to a list if needed.
if not isinstance(data_col, list):
data_col = [data_col]
# Loop over the file data.
for line in file_data:
# Loop over the intensity columns, storing the data.
intensity = []
for i in range(len(data_col)):
# Extract the data for the single line (loop of a single element).
for values in read_spin_data(file_data=[line], 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, data_col=data_col[i], sep=sep, spin_id=spin_id):
# Check the values.
if len(values) != 6 and data_present:
raise RelaxError("The molecule name, residue number and name, spin number and name, and value columns could not be found in the data %s." % repr(values))
# Unpack when peak data is present
elif data_present:
# Unpack.
mol_name, res_num, res_name, spin_num, spin_name, value = values
# Store the intensity.
intensity.append(value)
# Unpack when peak data is not present.
elif not data_present:
# Unpack.
mol_name, res_num, res_name, spin_num, spin_name = values
# Add the assignment to the peak list object.
peak_list.add(mol_names=[mol_name, mol_name], res_nums=[res_num, res_num], res_names=[res_name, res_name], spin_nums=[spin_num, spin_num], spin_names=[spin_name, spin_name], intensity=intensity)
def read_list(peak_list=None, file_data=None):
"""Extract the peak intensity information from the Sparky peak intensity file.
@keyword peak_list: The peak list object to place all data into.
@type peak_list: lib.spectrum.objects.Peak_list instance
@keyword file_data: The data extracted from the file converted into a list of lists.
@type file_data: list of lists of str
@raises RelaxError: When the expected peak intensity is not a float.
"""
# The number of header lines.
num = 0
if file_data[0][0] == 'Assignment':
num = num + 1
if file_data[1] == '':
num = num + 1
print("Number of header lines found: %s" % num)
# The columns according to the file.
w1_col = None
w2_col = None
w3_col = None
w4_col = None
int_col = None
for i in range(len(file_data[0])):
# The chemical shifts.
if file_data[0][i] == 'w1':
w1_col = i
elif file_data[0][i] == 'w2':
w2_col = i
elif file_data[0][i] == 'w3':
w3_col = i
elif file_data[0][i] == 'w4':
w4_col = i
# The peak height.
elif file_data[0][i] == 'Height':
# The peak height when exported from CcpNmr Analysis export without 'Data'.
int_col = i
# The peak height when exported from Sparky.
if file_data[0][i - 1] == 'Data' and file_data[0][i] == 'Height':
int_col = i - 1
# The peak volume.
elif file_data[0][i] == 'Intensity':
int_col = i
# Remove the header.
file_data = file_data[num:]
# Strip the data.
file_data = strip(file_data)
# The dimensionality.
if w4_col != None:
dim = 4
elif w3_col != None:
dim = 3
elif w2_col != None:
dim = 2
elif w1_col != None:
dim = 1
else:
raise RelaxError(
"The dimensionality of the peak list cannot be determined.")
print("%sD peak list detected." % dim)
# Loop over the file data.
for line in file_data:
# Skip non-assigned peaks.
if line[0] == '?-?':
continue
# Split up the assignments.
if dim == 1:
assign1 = line[0]
elif dim == 2:
assign1, assign2 = split('-', line[0])
elif dim == 3:
assign1, assign2, assign3 = split('-', line[0])
elif dim == 4:
assign1, assign2, assign3, assign4 = split('-', line[0])
# Process the assignment for each dimension.
if dim >= 1:
row1 = split('([a-zA-Z]+)', assign1)
name1 = row1[-2] + row1[-1]
if dim >= 2:
row2 = split('([a-zA-Z]+)', assign2)
name2 = row2[-2] + row2[-1]
if dim >= 3:
row3 = split('([a-zA-Z]+)', assign3)
name3 = row3[-2] + row3[-1]
if dim >= 4:
row4 = split('([a-zA-Z]+)', assign4)
name4 = row4[-2] + row4[-1]
# Get the residue number for dimension 1.
got_res_num1 = True
try:
res_num1 = int(row1[-3])
except:
got_res_num1 = False
raise RelaxError(
"Improperly formatted Sparky file, cannot process the residue number for dimension 1 in assignment: %s."
% line[0])
# Get the residue number for dimension 2.
try:
res_num2 = int(row2[-3])
except:
# We cannot always expect dimension 2 to have residue number.
if got_res_num1:
res_num2 = res_num1
else:
res_num2 = None
warn(
RelaxWarning(
"Improperly formatted Sparky file, cannot process the residue number for dimension 2 in assignment: %s. Setting residue number to %s."
% (line[0], res_num2)))
# The residue name for dimension 1.
got_res_name1 = True
try:
res_name1 = row1[-4]
except:
got_res_name1 = False
res_name1 = None
warn(
RelaxWarning(
"Improperly formatted Sparky file, cannot process the residue name for dimension 1 in assignment: %s. Setting residue name to %s."
% (line[0], res_name1)))
# The residue name for dimension 2.
try:
res_name2 = row2[-4]
except:
# We cannot always expect dimension 2 to have residue name.
if got_res_name1:
res_name2 = res_name1
else:
res_name2 = None
warn(
RelaxWarning(
"Improperly formatted NMRPipe SeriesTab file, cannot process the residue name for dimension 2 in assignment: %s. Setting residue name to %s."
% (line[0], res_name2)))
# Chemical shifts.
w1 = None
w2 = None
w3 = None
w4 = None
if w1_col != None:
try:
w1 = float(line[w1_col])
except ValueError:
raise RelaxError(
"The chemical shift from the line %s is invalid." % line)
if w2_col != None:
try:
w2 = float(line[w2_col])
except ValueError:
raise RelaxError(
"The chemical shift from the line %s is invalid." % line)
if w3_col != None:
try:
w3 = float(line[w3_col])
except ValueError:
raise RelaxError(
"The chemical shift from the line %s is invalid." % line)
if w4_col != None:
try:
w4 = float(line[w4_col])
except ValueError:
raise RelaxError(
"The chemical shift from the line %s is invalid." % line)
# Intensity.
if int_col != None:
try:
intensity = float(line[int_col])
except ValueError:
raise RelaxError(
"The peak intensity value from the line %s is invalid." %
line)
# Add the assignment to the peak list object.
if dim == 1:
peak_list.add(res_nums=[res_num1],
res_names=[res_name1],
spin_names=[name1],
shifts=[w1],
intensity=intensity)
elif dim == 2:
peak_list.add(res_nums=[res_num1, res_num2],
res_names=[res_name1, res_name2],
spin_names=[name1, name2],
shifts=[w1, w2],
intensity=intensity)
elif dim == 3:
peak_list.add(res_nums=[res_num1, res_num2, res_num1],
res_names=[res_name1, res_name2, res_name1],
spin_names=[name1, name2, name3],
shifts=[w1, w2, w3],
intensity=intensity)
elif dim == 4:
peak_list.add(
res_nums=[res_num1, res_num2, res_num1, res_num1],
res_names=[res_name1, res_name2, res_name1, res_name1],
spin_names=[name1, name2, name3, name4],
shifts=[w1, w2, w3, w4],
intensity=intensity)
# If no intensity column, for example when reading spins from a spectrum list.
elif int_col == None:
warn(
RelaxWarning((
"The peak intensity value from the line %s is invalid. The return value will be without intensity."
% line)))
# Add the assignment to the peak list object.
if dim == 1:
peak_list.add(res_nums=[res_num1],
res_names=[res_name1],
spin_names=[name1],
shifts=[w1])
elif dim == 2:
peak_list.add(res_nums=[res_num1, res_num2],
res_names=[res_name1, res_name2],
spin_names=[name1, name2],
shifts=[w1, w2])
elif dim == 3:
peak_list.add(res_nums=[res_num1, res_num2, res_num1],
res_names=[res_name1, res_name2, res_name1],
spin_names=[name1, name2, name3],
shifts=[w1, w2, w3])
elif dim == 4:
peak_list.add(
res_nums=[res_num1, res_num2, res_num1, res_num1],
res_names=[res_name1, res_name2, res_name1, res_name1],
spin_names=[name1, name2, name3, name4],
shifts=[w1, w2, w3, w4])
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 read_list(peak_list=None, file_data=None, int_col=None):
"""Extract the peak intensity information from the NMRView peak intensity file.
@keyword peak_list: The peak list object to place all data into.
@type peak_list: lib.spectrum.objects.Peak_list instance
@keyword file_data: The data extracted from the file converted into a list of lists.
@type file_data: list of lists of str
@keyword int_col: The column containing the peak intensity data. The default is 16 for intensities. Setting the int_col argument to 15 will use the volumes (or evolumes). For a non-standard formatted file, use a different value.
@type int_col: int
@raises RelaxError: When the expected peak intensity is not a float.
"""
# Assume the NMRView file has six header lines!
num = 6
print("Number of header lines: %s" % num)
# Remove the header.
file_data = file_data[num:]
# Strip the data.
file_data = strip(file_data)
# The chemical shift columns.
w2_col = 2
w1_col = 9
# The peak intensity column.
if int_col == None:
int_col = 16
if int_col == 16:
print('Using peak heights.')
if int_col == 15:
print('Using peak volumes (or evolumes).')
# Loop over the file data.
for line in file_data:
# Unknown assignment.
if line[1] == '{}':
warn(RelaxWarning("The assignment '%s' is unknown, skipping this peak." % line[1]))
continue
# The residue number
res_num = ''
try:
res_num = line[1].strip('{')
res_num = res_num.strip('}')
res_num = res_num.split('.')
res_num = int(res_num[0])
except ValueError:
raise RelaxError("Improperly formatted NMRView file, cannot process the assignment '%s'." % line[1])
# Nuclei names.
name2 = ''
if line[1]!='{}':
name2 = line[1].strip('{')
name2 = name2.strip('}')
name2 = name2.split('.')
name2 = name2[1]
name1 = ''
if line[8]!='{}':
name1 = line[8].strip('{')
name1 = name1.strip('}')
name1 = name1.split('.')
name1 = name1[1]
# Chemical shifts.
w1 = None
w2 = None
if w1_col != None:
try:
w1 = float(line[w1_col])
except ValueError:
raise RelaxError("The chemical shift from the line %s is invalid." % line)
if w2_col != None:
try:
w2 = float(line[w2_col])
except ValueError:
raise RelaxError("The chemical shift from the line %s is invalid." % line)
# Intensity.
try:
intensity = float(line[int_col])
except ValueError:
raise RelaxError("The peak intensity value " + repr(intensity) + " from the line " + repr(line) + " is invalid.")
# Add the assignment to the peak list object.
peak_list.add(res_nums=[res_num, res_num], spin_names=[name1, name2], shifts=[w1, w2], intensity=intensity)
def intensity_generic(peak_list=None,
file_data=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,
data_col=None,
sep=None,
spin_id=None):
"""Extract the peak intensity information from the generic column formatted peak list.
@keyword peak_list: The peak list object to place all data into.
@type peak_list: lib.spectrum.objects.Peak_list instance
@keyword file_data: The data extracted from the file converted into a list of lists.
@type file_data: list of lists of 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 data_col: The column containing the peak intensities.
@type data_col: int or list of int
@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.
@type spin_id: None or str
@raises RelaxError: When the expected peak intensity is not a float.
"""
# Strip the data.
file_data = strip(file_data)
# Check the intensity column argument.
data_present = True
if data_col == None:
warn(
RelaxWarning(
"The data column argument has not been supplied, and function will only return spin data."
))
data_present = False
# Convert the the data_col argument to a list if needed.
if not isinstance(data_col, list):
data_col = [data_col]
# Loop over the file data.
for line in file_data:
# Loop over the intensity columns, storing the data.
intensity = []
data_flag = False
for i in range(len(data_col)):
# Extract the data for the single line (loop of a single element).
for values in read_spin_data(file_data=[line],
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,
data_col=data_col[i],
sep=sep,
spin_id=spin_id,
raise_flag=False):
# The data flag.
data_flag = True
# Check the values.
if len(values) != 6 and data_present:
raise RelaxError(
"The molecule name, residue number and name, spin number and name, and value columns could not be found in the data %s."
% repr(values))
# Unpack when peak data is present
elif data_present:
# Unpack.
mol_name, res_num, res_name, spin_num, spin_name, value = values
# Store the intensity.
intensity.append(value)
# Unpack when peak data is not present.
elif not data_present:
# Unpack.
mol_name, res_num, res_name, spin_num, spin_name = values
# Add the assignment to the peak list object.
if data_flag:
peak_list.add(mol_names=[mol_name, mol_name],
res_nums=[res_num, res_num],
res_names=[res_name, res_name],
spin_nums=[spin_num, spin_num],
spin_names=[spin_name, spin_name],
intensity=intensity)
def read_list(peak_list=None, file_data=None, int_col=None):
"""Extract the peak intensity information from the NMRView peak intensity file.
@keyword peak_list: The peak list object to place all data into.
@type peak_list: lib.spectrum.objects.Peak_list instance
@keyword file_data: The data extracted from the file converted into a list of lists.
@type file_data: list of lists of str
@keyword int_col: The column containing the peak intensity data. The default is 16 for intensities. Setting the int_col argument to 15 will use the volumes (or evolumes). For a non-standard formatted file, use a different value.
@type int_col: int
@raises RelaxError: When the expected peak intensity is not a float.
"""
# Assume the NMRView file has six header lines!
num = 6
print("Number of header lines: %s" % num)
# Remove the header.
file_data = file_data[num:]
# Strip the data.
file_data = strip(file_data)
# The chemical shift columns.
w2_col = 2
w1_col = 9
# The peak intensity column.
if int_col == None:
int_col = 16
if int_col == 16:
print('Using peak heights.')
if int_col == 15:
print('Using peak volumes (or evolumes).')
# Loop over the file data.
for line in file_data:
# Unknown assignment.
if line[1] == '{}':
warn(
RelaxWarning(
"The assignment '%s' is unknown, skipping this peak." %
line[1]))
continue
# The residue number
res_num = ''
try:
res_num = line[1].strip('{')
res_num = res_num.strip('}')
res_num = res_num.split('.')
res_num = int(res_num[0])
except ValueError:
raise RelaxError(
"Improperly formatted NMRView file, cannot process the assignment '%s'."
% line[1])
# Nuclei names.
name2 = ''
if line[1] != '{}':
name2 = line[1].strip('{')
name2 = name2.strip('}')
name2 = name2.split('.')
name2 = name2[1]
name1 = ''
if line[8] != '{}':
name1 = line[8].strip('{')
name1 = name1.strip('}')
name1 = name1.split('.')
name1 = name1[1]
# Chemical shifts.
w1 = None
w2 = None
if w1_col != None:
try:
w1 = float(line[w1_col])
except ValueError:
raise RelaxError(
"The chemical shift from the line %s is invalid." % line)
if w2_col != None:
try:
w2 = float(line[w2_col])
except ValueError:
raise RelaxError(
"The chemical shift from the line %s is invalid." % line)
# Intensity.
try:
intensity = float(line[int_col])
except ValueError:
raise RelaxError("The peak intensity value " + repr(intensity) +
" from the line " + repr(line) + " is invalid.")
# Add the assignment to the peak list object.
peak_list.add(res_nums=[res_num, res_num],
spin_names=[name1, name2],
shifts=[w1, w2],
intensity=intensity)
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 read_list(peak_list=None, file_data=None, int_col=None):
"""Extract the peak intensity information from the XEasy file.
@keyword peak_list: The peak list object to place all data into.
@type peak_list: lib.spectrum.objects.Peak_list instance
@keyword file_data: The data extracted from the file converted into a list of lists.
@type file_data: list of lists of str
@keyword int_col: The column containing the peak intensity data (for a non-standard formatted file).
@type int_col: int
@raises RelaxError: When the expected peak intensity is not a float.
"""
# The hardcoded column positions (note that w1 and w2 are swapped!).
w1_col = 3
w2_col = 2
ass_w1_col = 7
ass_w2_col = 4
res_name1_col = 9
res_name2_col = 5
if int_col == None:
int_col = 10
# Determine the number of header lines.
num = 0
for line in file_data:
# Try to see if the intensity can be extracted.
try:
intensity = float(line[int_col])
except ValueError:
num = num + 1
except IndexError:
num = num + 1
else:
break
print("Number of header lines found: " + repr(num))
# Remove the header.
file_data = file_data[num:]
# Strip the data.
file_data = strip(file_data)
# Loop over the file data.
for line in file_data:
# Test for invalid assignment lines which have the column numbers changed and return empty data.
if line[ass_w1_col] == 'inv.' or line[ass_w2_col] == 'inv.':
continue
# The residue number for dimension 1.
try:
res_num1 = int(line[8])
except:
raise RelaxError(
"Improperly formatted XEasy file, cannot process the residue number for dimension 1 in assignment: %s."
% line)
# The residue number for dimension 2.
try:
res_num2 = int(line[5])
except:
warn(
RelaxWarning(
"Improperly formatted XEasy file, cannot process the residue number for dimension 2 in assignment: %s. Setting residue number to None."
% line))
res_num2 = None
# Nuclei names.
name1 = line[ass_w1_col]
name2 = line[ass_w2_col]
# Residue names.
res_name1 = line[res_name1_col]
res_name2 = line[res_name2_col]
# Chemical shifts.
try:
w1 = float(line[w1_col])
except ValueError:
raise RelaxError(
"The w1 chemical shift from the line %s is invalid." % line)
try:
w2 = float(line[w2_col])
except ValueError:
raise RelaxError(
"The w2 chemical shift from the line %s is invalid." % line)
# Intensity.
try:
intensity = float(line[int_col])
except ValueError:
raise RelaxError(
"The peak intensity value from the line %s is invalid." % line)
# Add the assignment to the peak list object.
peak_list.add(res_nums=[res_num1, res_num2],
res_names=[res_name1, res_name2],
spin_names=[name1, name2],
shifts=[w1, w2],
intensity=intensity)
def read_list(peak_list=None, file_data=None):
"""Extract the peak intensity information from the Sparky peak intensity file.
@keyword peak_list: The peak list object to place all data into.
@type peak_list: lib.spectrum.objects.Peak_list instance
@keyword file_data: The data extracted from the file converted into a list of lists.
@type file_data: list of lists of str
@raises RelaxError: When the expected peak intensity is not a float.
"""
# The number of header lines.
num = 0
if file_data[0][0] == 'Assignment':
num = num + 1
if file_data[1] == '':
num = num + 1
print("Number of header lines found: %s" % num)
# The columns according to the file.
w1_col = None
w2_col = None
w3_col = None
w4_col = None
int_col = None
for i in range(len(file_data[0])):
# The chemical shifts.
if file_data[0][i] == 'w1':
w1_col = i
elif file_data[0][i] == 'w2':
w2_col = i
elif file_data[0][i] == 'w3':
w3_col = i
elif file_data[0][i] == 'w4':
w4_col = i
# The peak height.
elif file_data[0][i] == 'Height':
# The peak height when exported from CcpNmr Analysis export without 'Data'.
int_col = i
# The peak height when exported from Sparky.
if file_data[0][i-1] == 'Data' and file_data[0][i] == 'Height':
int_col = i-1
# The peak volume.
elif file_data[0][i] == 'Intensity':
int_col = i
# Remove the header.
file_data = file_data[num:]
# Strip the data.
file_data = strip(file_data)
# The dimensionality.
if w4_col != None:
dim = 4
elif w3_col != None:
dim = 3
elif w2_col != None:
dim = 2
elif w1_col != None:
dim = 1
else:
raise RelaxError("The dimensionality of the peak list cannot be determined.")
print("%sD peak list detected." % dim)
# Loop over the file data.
for line in file_data:
# Skip non-assigned peaks.
if line[0] == '?-?':
continue
# Split up the assignments.
if dim == 1:
assign1 = line[0]
elif dim == 2:
assign1, assign2 = split('-', line[0])
elif dim == 3:
assign1, assign2, assign3 = split('-', line[0])
elif dim == 4:
assign1, assign2, assign3, assign4 = split('-', line[0])
# Process the assignment for each dimension.
if dim >= 1:
row1 = split('([a-zA-Z]+)', assign1)
name1 = row1[-2] + row1[-1]
if dim >= 2:
row2 = split('([a-zA-Z]+)', assign2)
name2 = row2[-2] + row2[-1]
if dim >= 3:
row3 = split('([a-zA-Z]+)', assign3)
name3 = row3[-2] + row3[-1]
if dim >= 4:
row4 = split('([a-zA-Z]+)', assign4)
name4 = row4[-2] + row4[-1]
# Get the residue number for dimension 1.
got_res_num1 = True
try:
res_num1 = int(row1[-3])
except:
got_res_num1 = False
raise RelaxError("Improperly formatted Sparky file, cannot process the residue number for dimension 1 in assignment: %s." % line[0])
# Get the residue number for dimension 2.
try:
res_num2 = int(row2[-3])
except:
# We cannot always expect dimension 2 to have residue number.
if got_res_num1:
res_num2 = res_num1
else:
res_num2 = None
warn(RelaxWarning("Improperly formatted Sparky file, cannot process the residue number for dimension 2 in assignment: %s. Setting residue number to %s." % (line[0], res_num2)))
# The residue name for dimension 1.
got_res_name1 = True
try:
res_name1 = row1[-4]
except:
got_res_name1 = False
res_name1 = None
warn(RelaxWarning("Improperly formatted Sparky file, cannot process the residue name for dimension 1 in assignment: %s. Setting residue name to %s." % (line[0], res_name1)))
# The residue name for dimension 2.
try:
res_name2 = row2[-4]
except:
# We cannot always expect dimension 2 to have residue name.
if got_res_name1:
res_name2 = res_name1
else:
res_name2 = None
warn(RelaxWarning("Improperly formatted NMRPipe SeriesTab file, cannot process the residue name for dimension 2 in assignment: %s. Setting residue name to %s." % (line[0], res_name2)))
# Chemical shifts.
w1 = None
w2 = None
w3 = None
w4 = None
if w1_col != None:
try:
w1 = float(line[w1_col])
except ValueError:
raise RelaxError("The chemical shift from the line %s is invalid." % line)
if w2_col != None:
try:
w2 = float(line[w2_col])
except ValueError:
raise RelaxError("The chemical shift from the line %s is invalid." % line)
if w3_col != None:
try:
w3 = float(line[w3_col])
except ValueError:
raise RelaxError("The chemical shift from the line %s is invalid." % line)
if w4_col != None:
try:
w4 = float(line[w4_col])
except ValueError:
raise RelaxError("The chemical shift from the line %s is invalid." % line)
# Intensity.
if int_col != None:
try:
intensity = float(line[int_col])
except ValueError:
raise RelaxError("The peak intensity value from the line %s is invalid." % line)
# Add the assignment to the peak list object.
if dim == 1:
peak_list.add(res_nums=[res_num1], res_names=[res_name1], spin_names=[name1], shifts=[w1], intensity=intensity)
elif dim == 2:
peak_list.add(res_nums=[res_num1, res_num2], res_names=[res_name1, res_name2], spin_names=[name1, name2], shifts=[w1, w2], intensity=intensity)
elif dim == 3:
peak_list.add(res_nums=[res_num1, res_num2, res_num1], res_names=[res_name1, res_name2, res_name1], spin_names=[name1, name2, name3], shifts=[w1, w2, w3], intensity=intensity)
elif dim == 4:
peak_list.add(res_nums=[res_num1, res_num2, res_num1, res_num1], res_names=[res_name1, res_name2, res_name1, res_name1], spin_names=[name1, name2, name3, name4], shifts=[w1, w2, w3, w4], intensity=intensity)
# If no intensity column, for example when reading spins from a spectrum list.
elif int_col == None:
warn(RelaxWarning(("The peak intensity value from the line %s is invalid. The return value will be without intensity." % line)))
# Add the assignment to the peak list object.
if dim == 1:
peak_list.add(res_nums=[res_num1], res_names=[res_name1], spin_names=[name1], shifts=[w1])
elif dim == 2:
peak_list.add(res_nums=[res_num1, res_num2], res_names=[res_name1, res_name2], spin_names=[name1, name2], shifts=[w1, w2])
elif dim == 3:
peak_list.add(res_nums=[res_num1, res_num2, res_num1], res_names=[res_name1, res_name2, res_name1], spin_names=[name1, name2, name3], shifts=[w1, w2, w3])
elif dim == 4:
peak_list.add(res_nums=[res_num1, res_num2, res_num1, res_num1], res_names=[res_name1, res_name2, res_name1, res_name1], spin_names=[name1, name2, name3, name4], shifts=[w1, w2, w3, w4])
def read_spin_data(file=None, dir=None, file_data=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, data_col=None, error_col=None, sep=None, spin_id=None, raise_flag=True):
"""Generator function for reading the spin specific data from file.
Description
===========
This function reads 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.
@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_id_col: The column containing the spin ID strings. 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. 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. 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. 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. 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. If supplied, spin_id_col must be None.
@type spin_num_col: int or None
@keyword data_col: The column containing the data.
@type data_col: int or None
@keyword error_col: The column containing the errors.
@type error_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.
@type spin_id: None or str
@keyword raise_flag: A flag which if True will cause a RelaxError to be raised if no data can be found.
@type raise_flag: bool
@return: A list of the spin specific data is yielded. The format is a list consisting of the spin ID string, the data value (if data_col is give), and the error value (if error_col is given). If both data_col and error_col are None, then the spin ID string is simply yielded.
@rtype: str, list of [str, float], or list of [str, float, float]
"""
# Argument tests.
col_args = [spin_id_col, mol_name_col, res_name_col, res_num_col, spin_name_col, spin_num_col, data_col, error_col]
col_arg_names = ['spin_id_col', 'mol_name_col', 'res_name_col', 'res_num_col', 'spin_name_col', 'spin_num_col', 'data_col', 'error_col']
for i in range(len(col_args)):
if col_args[i] == 0:
raise RelaxError("The '%s' argument cannot be zero, column numbering starts at one." % col_arg_names[i])
if spin_id_col and (mol_name_col or res_name_col or res_num_col or spin_name_col or spin_num_col):
raise RelaxError("If the 'spin_id_col' argument has been supplied, then the mol_name_col, res_name_col, res_num_col, spin_name_col, and spin_num_col must all be set to None.")
# Minimum number of columns.
min_col_num = max([_f for _f in [spin_id_col, mol_name_col, res_num_col, res_name_col, spin_num_col, spin_name_col, data_col, error_col] if _f])
# Extract the data from the file.
if not file_data:
# Extract.
file_data = extract_data(file, dir, sep=sep)
# Strip the data of all comments and empty lines.
if spin_id_col != None:
file_data = strip(file_data, comments=False)
else:
file_data = strip(file_data)
# No data!
if not file_data:
warn(RelaxFileEmptyWarning(file))
return
# Yield the data, spin by spin.
missing_data = True
for line in file_data:
# Convert the spin IDs.
if spin_id_col != None and line[spin_id_col-1][0] in ["\"", "\'"]:
line[spin_id_col-1] = eval(line[spin_id_col-1])
# Convert.
# Validate the sequence.
if not check_sequence(line, 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, data_col=data_col, error_col=error_col, escalate=1):
continue
# Get the spin data from the ID.
if spin_id_col:
# Invalid spin ID.
if line[spin_id_col-1] == '#':
warn(RelaxWarning("Invalid spin ID, skipping the line %s" % line))
continue
mol_name, res_num, res_name, spin_num, spin_name = spin_id_to_data_list(line[spin_id_col-1])
# Convert the spin data.
else:
# The molecule.
mol_name = None
if mol_name_col != None and line[mol_name_col-1] != 'None':
mol_name = line[mol_name_col-1]
# The residue number, catching bad values.
res_num = None
if res_num_col != None:
try:
if line[res_num_col-1] == 'None':
res_num = None
else:
res_num = int(line[res_num_col-1])
except ValueError:
warn(RelaxWarning("Invalid residue number, skipping the line %s" % line))
continue
# The residue name.
res_name = None
if res_name_col != None and line[res_name_col-1] != 'None':
res_name = line[res_name_col-1]
# The spin number, catching bad values.
spin_num = None
if spin_num_col != None:
try:
if line[spin_num_col-1] == 'None':
spin_num = None
else:
spin_num = int(line[spin_num_col-1])
except ValueError:
warn(RelaxWarning("Invalid spin number, skipping the line %s" % line))
continue
# The spin name.
spin_name = None
if spin_name_col != None and line[spin_name_col-1] != 'None':
spin_name = line[spin_name_col-1]
# Convert the data.
value = None
if data_col != None:
try:
# None.
if line[data_col-1] == 'None':
value = None
# A float.
else:
value = float(line[data_col-1])
# If it a float, test if is nan.
if isnan(value):
warn(RelaxWarning("The value is 'nan', skipping the line %s" % line))
continue
# Bad data.
except ValueError:
warn(RelaxWarning("Invalid data, skipping the line %s" % line))
continue
# Convert the errors.
error = None
if error_col != None:
try:
# None.
if line[error_col-1] == 'None':
error = None
# A float.
else:
error = float(line[error_col-1])
# If it a float, test if is nan.
if isnan(error):
warn(RelaxWarning("The error is 'nan', skipping the line %s" % line))
continue
# Bad data.
except ValueError:
warn(RelaxWarning("Invalid errors, skipping the line %s" % line))
continue
# Right, data is OK and exists.
missing_data = False
# Yield the data.
if data_col and error_col:
yield mol_name, res_num, res_name, spin_num, spin_name, value, error
elif data_col:
yield mol_name, res_num, res_name, spin_num, spin_name, value
elif error_col:
yield mol_name, res_num, res_name, spin_num, spin_name, error
else:
yield mol_name, res_num, res_name, spin_num, spin_name
# Hmmm, no data!
if raise_flag and missing_data:
raise RelaxError("No corresponding data could be found within the file.")
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 read_spin_data(file=None, dir=None, file_data=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, data_col=None, error_col=None, sep=None, spin_id=None, raise_flag=True):
"""Generator function for reading the spin specific data from file.
Description
===========
This function reads 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.
@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_id_col: The column containing the spin ID strings. 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. 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. 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. 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. 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. If supplied, spin_id_col must be None.
@type spin_num_col: int or None
@keyword data_col: The column containing the data.
@type data_col: int or None
@keyword error_col: The column containing the errors.
@type error_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.
@type spin_id: None or str
@keyword raise_flag: A flag which if True will cause a RelaxError to be raised if no data can be found.
@type raise_flag: bool
@return: A list of the spin specific data is yielded. The format is a list consisting of the spin ID string, the data value (if data_col is give), and the error value (if error_col is given). If both data_col and error_col are None, then the spin ID string is simply yielded.
@rtype: str, list of [str, float], or list of [str, float, float]
"""
# Argument tests.
col_args = [spin_id_col, mol_name_col, res_name_col, res_num_col, spin_name_col, spin_num_col, data_col, error_col]
col_arg_names = ['spin_id_col', 'mol_name_col', 'res_name_col', 'res_num_col', 'spin_name_col', 'spin_num_col', 'data_col', 'error_col']
for i in range(len(col_args)):
if col_args[i] == 0:
raise RelaxError("The '%s' argument cannot be zero, column numbering starts at one." % col_arg_names[i])
if spin_id_col and (mol_name_col or res_name_col or res_num_col or spin_name_col or spin_num_col):
raise RelaxError("If the 'spin_id_col' argument has been supplied, then the mol_name_col, res_name_col, res_num_col, spin_name_col, and spin_num_col must all be set to None.")
# Minimum number of columns.
min_col_num = max([_f for _f in [spin_id_col, mol_name_col, res_num_col, res_name_col, spin_num_col, spin_name_col, data_col, error_col] if _f])
# Extract the data from the file.
if not file_data:
# Extract.
file_data = extract_data(file, dir, sep=sep)
# Strip the data of all comments and empty lines.
if spin_id_col != None:
file_data = strip(file_data, comments=False)
else:
file_data = strip(file_data)
# No data!
if not file_data:
warn(RelaxFileEmptyWarning(file))
return
# Yield the data, spin by spin.
missing_data = True
for line in file_data:
# Convert the spin IDs.
if spin_id_col != None and line[spin_id_col-1][0] in ["\"", "\'"]:
line[spin_id_col-1] = eval(line[spin_id_col-1])
# Convert.
# Validate the sequence.
if not check_sequence(line, 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, data_col=data_col, error_col=error_col, escalate=1):
continue
# Get the spin data from the ID.
if spin_id_col:
# Invalid spin ID.
if line[spin_id_col-1] == '#':
warn(RelaxWarning("Invalid spin ID, skipping the line %s" % line))
continue
mol_name, res_num, res_name, spin_num, spin_name = spin_id_to_data_list(line[spin_id_col-1])
# Convert the spin data.
else:
# The molecule.
mol_name = None
if mol_name_col != None and line[mol_name_col-1] != 'None':
mol_name = line[mol_name_col-1]
# The residue number, catching bad values.
res_num = None
if res_num_col != None:
try:
if line[res_num_col-1] == 'None':
res_num = None
else:
res_num = int(line[res_num_col-1])
except ValueError:
warn(RelaxWarning("Invalid residue number, skipping the line %s" % line))
continue
# The residue name.
res_name = None
if res_name_col != None and line[res_name_col-1] != 'None':
res_name = line[res_name_col-1]
# The spin number, catching bad values.
spin_num = None
if spin_num_col != None:
try:
if line[spin_num_col-1] == 'None':
spin_num = None
else:
spin_num = int(line[spin_num_col-1])
except ValueError:
warn(RelaxWarning("Invalid spin number, skipping the line %s" % line))
continue
# The spin name.
spin_name = None
if spin_name_col != None and line[spin_name_col-1] != 'None':
spin_name = line[spin_name_col-1]
# Convert the data.
value = None
if data_col != None:
try:
# None.
if line[data_col-1] == 'None':
value = None
# A float.
else:
value = float(line[data_col-1])
# If it a float, test if is nan.
if not isFinite(value):
warn(RelaxWarning("The value is not finite, skipping the line %s" % line))
continue
# Bad data.
except ValueError:
warn(RelaxWarning("Invalid data, skipping the line %s" % line))
continue
# Convert the errors.
error = None
if error_col != None:
try:
# None.
if line[error_col-1] == 'None':
error = None
# A float.
else:
error = float(line[error_col-1])
# If it a float, test if is nan.
if not isFinite(error):
warn(RelaxWarning("The error is not finite, skipping the line %s" % line))
continue
# Bad data.
except ValueError:
warn(RelaxWarning("Invalid errors, skipping the line %s" % line))
continue
# Right, data is OK and exists.
missing_data = False
# Yield the data.
if data_col and error_col:
yield mol_name, res_num, res_name, spin_num, spin_name, value, error
elif data_col:
yield mol_name, res_num, res_name, spin_num, spin_name, value
elif error_col:
yield mol_name, res_num, res_name, spin_num, spin_name, error
else:
yield mol_name, res_num, res_name, spin_num, spin_name
# Hmmm, no data!
if raise_flag and missing_data:
raise RelaxError("No corresponding data could be found within the file.")
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 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_list(peak_list=None, file_data=None, int_col=None):
"""Extract the peak intensity information from the XEasy file.
@keyword peak_list: The peak list object to place all data into.
@type peak_list: lib.spectrum.objects.Peak_list instance
@keyword file_data: The data extracted from the file converted into a list of lists.
@type file_data: list of lists of str
@keyword int_col: The column containing the peak intensity data (for a non-standard formatted file).
@type int_col: int
@raises RelaxError: When the expected peak intensity is not a float.
"""
# The hardcoded column positions (note that w1 and w2 are swapped!).
w1_col = 3
w2_col = 2
ass_w1_col = 7
ass_w2_col = 4
res_name1_col = 9
res_name2_col = 5
if int_col == None:
int_col = 10
# Determine the number of header lines.
num = 0
for line in file_data:
# Try to see if the intensity can be extracted.
try:
intensity = float(line[int_col])
except ValueError:
num = num + 1
except IndexError:
num = num + 1
else:
break
print("Number of header lines found: " + repr(num))
# Remove the header.
file_data = file_data[num:]
# Strip the data.
file_data = strip(file_data)
# Loop over the file data.
for line in file_data:
# Test for invalid assignment lines which have the column numbers changed and return empty data.
if line[ass_w1_col] == 'inv.' or line[ass_w2_col] == 'inv.':
continue
# The residue number for dimension 1.
try:
res_num1 = int(line[8])
except:
raise RelaxError("Improperly formatted XEasy file, cannot process the residue number for dimension 1 in assignment: %s." % line)
# The residue number for dimension 2.
try:
res_num2 = int(line[5])
except:
warn(RelaxWarning("Improperly formatted XEasy file, cannot process the residue number for dimension 2 in assignment: %s. Setting residue number to None." % line))
res_num2 = None
# Nuclei names.
name1 = line[ass_w1_col]
name2 = line[ass_w2_col]
# Residue names.
res_name1 = line[res_name1_col]
res_name2 = line[res_name2_col]
# Chemical shifts.
try:
w1 = float(line[w1_col])
except ValueError:
raise RelaxError("The w1 chemical shift from the line %s is invalid." % line)
try:
w2 = float(line[w2_col])
except ValueError:
raise RelaxError("The w2 chemical shift from the line %s is invalid." % line)
# Intensity.
try:
intensity = float(line[int_col])
except ValueError:
raise RelaxError("The peak intensity value from the line %s is invalid." % line)
# Add the assignment to the peak list object.
peak_list.add(res_nums=[res_num1, res_num2], res_names=[res_name1, res_name2], spin_names=[name1, name2], shifts=[w1, w2], intensity=intensity)