def test_equality(andi):
assert andi == GCMS_data(andi.time_list, andi.scan_list)
assert andi != GCMS_data(list(range(len(andi.scan_list))), andi.scan_list)
assert andi != test_string
assert andi != test_int
assert andi != test_float
assert andi != test_list_ints
assert andi != test_list_strs
assert andi != test_tuple
assert andi != test_dict
def test_equality(data):
assert data == GCMS_data(data.time_list, data.scan_list)
assert data != GCMS_data(list(range(len(data.scan_list))), data.scan_list)
assert data != test_string
assert data != test_int
assert data != test_float
assert data != test_list_ints
assert data != test_list_strs
assert data != test_tuple
assert data != test_dict
def test_GCMS_data(andi):
assert isinstance(andi, GCMS_data)
GCMS_data(andi.time_list, andi.scan_list)
# Errors
for obj in [test_string, *test_numbers, test_list_strs, test_dict]:
with pytest.raises(TypeError):
GCMS_data(obj, andi.scan_list)
for obj in [test_string, *test_numbers, *test_sequences, test_dict]:
with pytest.raises(TypeError):
GCMS_data(andi.time_list, obj)
def test_GCMS_data(data):
assert isinstance(data, GCMS_data)
GCMS_data(data.time_list, data.scan_list)
# Errors
for obj in [test_string, *test_numbers, test_list_strs, test_dict]:
with pytest.raises(TypeError):
GCMS_data(obj, data.scan_list) # type: ignore
for obj in [test_string, *test_numbers, *test_sequences, test_dict]:
with pytest.raises(TypeError):
GCMS_data(data.time_list, obj) # type: ignore
def ANDI_reader(file_name):
# pyMs写的太烂了！！！！其中的很多构架严重不合理，将必然造成计算缓慢！！！
# 尽量减少内存的复制，有助性能的提升。最好是cdf的dada读进来就作为文件就好，不要进行过多的内存copy
print "ok in andi"
scan_list, scan_acquisition_time = CDF_Reader(file_name)
data = GCMS_data(scan_list=scan_list, time_list=scan_acquisition_time)
return data
def Agilent_reader(file_name):
if not isinstance(file_name, (str, pathlib.Path)):
raise TypeError(
"'file_name' must be a string or a pathlib.Path object")
if not isinstance(file_name, pathlib.Path):
file_name = pathlib.Path(file_name)
assert os.path.exists(file_name)
if (file_name / 'DATA.MS').exists():
d_file = open(file_name / 'DATA.MS', 'rb')
elif (file_name / 'data.ms').exists():
d_file = open(file_name / 'data.ms', 'rb')
else:
print(f'Error: {file_name} does not contain a data.ms file.')
raise ValueError(
f'Error: {file_name} does not contain a data.ms file.')
data = AgilentGCMSData()
options = Options()
load_file_info(d_file, data, options)
load_tic(d_file, data, options)
load_xic(d_file, data, options)
time_list = list(data.time)
rows, _ = data.xic.shape
scan_list = [Scan(data.mz, list(data.xic[r, :])) for r in range(rows)]
return GCMS_data(time_list, scan_list)
def ANDI_reader(file_name):
"""
A reader for ANDI-MS NetCDF files
:param file_name: The path of the ANDI-MS file
:type file_name: str or os.PathLike
:return: GC-MS data object
:rtype: :class:`pyms.GCMS.Class.GCMS_data`
:author: Qiao Wang
:author: Andrew Isaac
:author: Vladimir Likic
:author: Dominic Davis-Foster
"""
if not isinstance(file_name, (str, pathlib.Path)):
raise TypeError(
"'file_name' must be a string or a pathlib.Path object")
rootgrp = Dataset(file_name, "r+", format='NETCDF3_CLASSIC')
# TODO: find out if netCDF4 throws specific errors that we can use here
print(f" -> Reading netCDF file '{file_name}'")
scan_list = []
mass = rootgrp.variables[__MASS_STRING][:]
intensity = rootgrp.variables[__INTENSITY_STRING][:]
scan_lengths = rootgrp.variables[
"point_count"] # The number of data points in each scan
mass_values = mass.tolist()
intensity_values = intensity.tolist()
if len(mass_values) != len(intensity_values):
raise ValueError("The lengths of the mass and intensity lists differ!")
offset = 0
for idx, length in enumerate(scan_lengths):
mass_list = mass_values[offset:offset + length]
assert len(mass_values[offset:offset + length]) == length
intensity_list = intensity_values[offset:offset + length]
assert len(intensity_values[offset:offset + length]) == length
scan_list.append(Scan(mass_list, intensity_list))
offset += length
assert offset == len(mass_values)
time = rootgrp.variables[__TIME_STRING][:]
time_list = time.tolist()
# sanity check
if not len(time_list) == len(scan_list):
raise ValueError(
"number of time points does not equal the number of scans")
return GCMS_data(time_list, scan_list)
def mzML_reader(file_name):
"""
@summary: A reader for mzML files, returns
a GC-MS data object
@param file_name: The name of the mzML file
@type file_name: StringType
@author: Sean O'Callaghan
"""
if not is_str(file_name):
error("'file_name' must be a string")
try:
mzml_file = pymzml.run.Reader(file_name)
except:
error("Cannot open file '%s'" % file_name)
print " -> Reading mzML file '%s'" % (file_name)
scan_list = []
time_list = []
for spectrum in mzml_file:
mass_list = []
intensity_list = []
for mz,i in spectrum.peaks:
mass_list.append(mz)
intensity_list.append(i)
#scan_list.append(Scan(mass_list, intensity_list))
for element in spectrum.xmlTree:
# For some reason there are spectra with no time value,
# Ignore these????????????
if element.get('accession') == "MS:1000016": #time value
# We need time in seconds not minutes
time_list.append(60*float(element.get('value')))
scan_list.append(Scan(mass_list, intensity_list))
print "time:", len(time_list)
print "scan:", len(scan_list)
data = GCMS_data(time_list, scan_list)
return data
def agilent_reader(
file_name: PathLike) -> GCMS_data: # pragma: no cover (!Windows)
"""
Reader for Agilent MassHunter ``.d`` files.
:param file_name: Path of the file to read.
:return: GC-MS data object.
"""
if not isinstance(file_name, (str, pathlib.Path)):
raise TypeError(
"'file_name' must be a string or a pathlib.Path object")
if not isinstance(file_name, pathlib.Path):
file_name = pathlib.Path(file_name)
print(f" -> Reading Agilent data file '{file_name}'")
time_list = []
scan_list = []
reader = MassSpecDataReader(file_name)
for scan_no in range(
reader.file_information.ms_scan_file_info.total_scans):
spectrum = reader.get_spectrum_by_scan(scan_no)
scan_list.append(Scan(spectrum.x_data, spectrum.y_data))
time_list.append(mean(spectrum.acquired_time_ranges[0]) * 60.0)
# sanity check
time_len = len(time_list)
scan_len = len(scan_list)
if not time_len == scan_len: # pragma: no cover
print(time_list)
print(scan_list)
raise ValueError(
f"Number of time points ({time_len}) does not equal the number of scans ({scan_len})."
)
data = GCMS_data(time_list, scan_list)
return data
def JCAMP_reader(file_name: Union[str, os.PathLike]) -> GCMS_data:
"""
Generic reader for JCAMP DX files
:param file_name: Path of the file to read
:type file_name: str or os.PathLike
:return: GC-MS data object
:rtype: :class:`pyms.GCMS.Class.GCMS_data`
:authors: Qiao Wang, Andrew Isaac, Vladimir Likic, David Kainer, Dominic Davis-Foster (pathlib support)
"""
if not is_path(file_name):
raise TypeError("'file_name' must be a string or a PathLike object")
file_name = prepare_filepath(file_name, mkdirs=False)
print(f" -> Reading JCAMP file '{file_name}'")
lines_list = file_name.open('r')
data = []
page_idx = 0
xydata_idx = 0
time_list = []
scan_list = []
header_info = {} # Dictionary containing header information
for line in lines_list:
if len(line.strip()) != 0:
# prefix = line.find('#')
# if prefix == 0:
if line.startswith("##"):
# key word or information
fields = line.split('=', 1)
fields[0] = fields[0].lstrip("##").upper()
fields[1] = fields[1].strip()
if "PAGE" in fields[0]:
if "T=" in fields[1]:
# PAGE contains retention time starting with T=
# FileConverter Pro style
time = float(fields[1].lstrip(
"T=")) # rt for the scan to be submitted
time_list.append(time)
page_idx = page_idx + 1
elif "RETENTION_TIME" in fields[0]:
# OpenChrom style
time = float(fields[1]) # rt for the scan to be submitted
# Check to make sure time is not already in the time list;
# Can happen when both ##PAGE and ##RETENTION_TIME are specified
if time_list[-1] != time:
time_list.append(time)
elif fields[0] in xydata_tags:
xydata_idx = xydata_idx + 1
elif fields[0] in header_info_fields:
if fields[1].isdigit():
header_info[fields[0]] = int(fields[1])
elif is_float(fields[1]):
header_info[fields[0]] = float(fields[1])
else:
header_info[fields[0]] = fields[1]
# elif prefix == -1:
else:
# Line doesn't start with ##
# data
if page_idx > 1 or xydata_idx > 1:
if len(data) % 2 == 1:
# TODO: This means the data is not in x, y pairs
# Make a better error message
raise ValueError("data not in pair !")
mass_list = []
intensity_list = []
for i in range(len(data) // 2):
mass_list.append(data[i * 2])
intensity_list.append(data[i * 2 + 1])
if len(mass_list) != len(intensity_list):
raise ValueError(
"len(mass_list) is not equal to len(intensity_list)"
)
scan_list.append(Scan(mass_list, intensity_list))
data = []
data_sub = line.strip().split(',')
for item in data_sub:
if not len(item.strip()) == 0:
data.append(float(item.strip()))
if page_idx > 1:
page_idx = 1
if xydata_idx > 1:
xydata_idx = 1
else:
data_sub = line.strip().split(',')
for item in data_sub:
if not len(item.strip()) == 0:
data.append(float(item.strip()))
if len(data) % 2 == 1:
# TODO: This means the data is not in x, y pairs
# Make a better error message
raise ValueError("data not in pair !")
# get last scan
mass = []
intensity = []
for i in range(len(data) // 2):
mass.append(data[i * 2])
intensity.append(data[i * 2 + 1])
if len(mass) != len(intensity):
raise ValueError("len(mass) is not equal to len(intensity)")
scan_list.append(Scan(mass, intensity))
# sanity check
time_len = len(time_list)
scan_len = len(scan_list)
if time_len != scan_len:
print(time_list)
print(scan_list)
raise ValueError(
f"Number of time points ({time_len}) does not equal the number of scans ({scan_len})"
)
data = GCMS_data(time_list, scan_list)
return data
def JCAMP_reader(file_name):
"""
@summary: Generic reader for JCAMP DX files, produces GC-MS data
object
@author: Qiao Wang
@author: Andrew Isaac
@author: Vladimir Likic
"""
if not is_str(file_name):
error("'file_name' not a string")
print " -> Reading JCAMP file '%s'" % (file_name)
lines_list = open(file_name,'r')
data = []
page_idx = 0
xydata_idx = 0
time_list = []
scan_list = []
for line in lines_list:
if not len(line.strip()) == 0:
prefix = line.find('#')
# key word or information
if prefix == 0:
fields = line.split('=')
if fields[0].find("##PAGE") >= 0:
time = float(fields[2].strip()) #rt for the scan to be submitted
time_list.append(time)
page_idx = page_idx + 1
elif fields[0].find("##DATA TABLE") >= 0:
xydata_idx = xydata_idx + 1
# data
elif prefix == -1:
if page_idx > 1 or xydata_idx > 1:
if len(data) % 2 == 1:
error("data not in pair !")
mass = []
intensity = []
for i in range(len(data) / 2):
mass.append(data[i * 2])
intensity.append(data[i * 2 + 1])
if not len(mass) == len(intensity):
error("len(mass) is not equal to len(intensity)")
scan_list.append(Scan(mass, intensity))
data = []
data_sub = line.strip().split(',')
for item in data_sub:
if not len(item.strip()) == 0:
data.append(float(item.strip()))
if page_idx > 1:
page_idx = 1
if xydata_idx > 1:
xydata_idx = 1
else:
data_sub = line.strip().split(',')
for item in data_sub:
if not len(item.strip()) == 0:
data.append(float(item.strip()))
if len(data) % 2 == 1:
error("data not in pair !")
# get last scan
mass = []
intensity = []
for i in range(len(data) / 2):
mass.append(data[i * 2])
intensity.append(data[i * 2 + 1])
if not len(mass) == len(intensity):
error("len(mass) is not equal to len(intensity)")
scan_list.append(Scan(mass, intensity))
# sanity check
if not len(time_list) == len(scan_list):
error("number of time points does not equal the number of scans")
data = GCMS_data(time_list, scan_list)
return data
def mzML_reader(file_name):
"""
A reader for mzML files
:param file_name: The name of the mzML file
:type file_name: str or pathlib.Path
:return: GC-MS data object
:rtype: :class:`pyms.GCMS.Class.GCMS_data`
:author: Sean O'Callaghan
:author: Dominic Davis-Foster (pathlib support)
"""
if not is_path(file_name):
raise TypeError("'file_name' must be a string or a PathLike object")
mzml_file = pymzml.run.Reader(str(file_name))
try: # avoid printing from each rank
comm = MPI.COMM_WORLD
rank = comm.Get_rank()
size = comm.Get_size()
if rank == 0:
file_names = []
for i in range(1, size):
recv_buffer = ""
file_n = comm.recv(recv_buffer, i)
file_names.append(file_n)
print(" -> Reading mzML files:")
print(file_name)
for file_n in file_names:
print(file_n)
else:
comm.send(file_name, dest=0)
# TODO: Find specific error
except Exception as e:
print(e)
print(f" -> Reading mzML file '{file_name}'")
scan_list = []
time_list = []
for spectrum in mzml_file:
mass_list = []
intensity_list = []
for mz, i in spectrum.peaks:
mass_list.append(mz)
intensity_list.append(i)
# scan_list.append(Scan(mass_list, intensity_list))
for element in spectrum.xmlTree:
# For some reason there are spectra with no time value,
# Ignore these????????????
if element.get('accession') == "MS:1000016": # time value
# We need time in seconds not minutes
time_list.append(60 * float(element.get('value')))
scan_list.append(Scan(mass_list, intensity_list))
# print("time:", len(time_list))
# print("scan:", len(scan_list))
data = GCMS_data(time_list, scan_list)
return data
def ANDI_reader(file_name):
"""
@summary: A reader for ANDI-MS NetCDF files, returns
a GC-MS data object
@param file_name: The name of the ANDI-MS file
@type file_name: StringType
@author: Qiao Wang
@author: Andrew Isaac
@author: Vladimir Likic
"""
## TODO: use 'point_count' and allow for zero len scans
# the keys used to retrieve certain data from the NetCDF file
__MASS_STRING = "mass_values"
__INTENSITY_STRING = "intensity_values"
__TIME_STRING = "scan_acquisition_time"
if not is_str(file_name):
error("'file_name' must be a string")
try:
file = CDF(file_name)
except CDFError:
error("Cannot open file '%s'" % file_name)
print " -> Reading netCDF file '%s'" % (file_name)
scan_list = []
mass = file.var(__MASS_STRING)
intensity = file.var(__INTENSITY_STRING)
mass_values = mass.get().tolist()
mass_list = []
mass_previous = mass_values[0]
mass_list.append(mass_previous)
intensity_values = intensity.get().tolist()
intensity_list = []
intensity_previous = intensity_values[0]
intensity_list.append(intensity_previous)
if not len(mass_values) == len(intensity_values):
error("length of mass_list is not equal to length of intensity_list !")
for i in range(len(mass_values) - 1):
# assume masses in ascending order until new scan
if mass_previous <= mass_values[i + 1]:
#print mass_values[i+1]
mass_list.append(mass_values[i + 1])
mass_previous = mass_values[i + 1]
intensity_list.append(intensity_values[i + 1])
intensity_previous = intensity_values[i + 1]
# new scan
else:
scan_list.append(Scan(mass_list, intensity_list))
#print "Added scan"
mass_previous = mass_values[i + 1]
intensity_previous = intensity_values[i + 1]
mass_list = []
intensity_list = []
mass_list.append(mass_previous)
intensity_list.append(intensity_previous)
# store final scan
scan_list.append(Scan(mass_list, intensity_list))
time = file.var(__TIME_STRING)
time_list = time.get().tolist()
# sanity check
if not len(time_list) == len(scan_list):
#JT: Debug for old gcms data
#JT: time longer than scans so trim
print "Time list is"
print len(time_list) - len(scan_list)
print "longer than scan list. Trimming...."
time_list = time_list[0:len(scan_list)]
print len(time_list)
print len(scan_list)
#error("number of time points does not equal the number of scans")
data = GCMS_data(time_list, scan_list)
return data
def mzML_reader(file_name):
"""
@summary: A reader for mzML files, returns
a GC-MS data object
@param file_name: The name of the mzML file
@type file_name: StringType
@author: Sean O'Callaghan
"""
if not is_str(file_name):
error("'file_name' must be a string")
try:
mzml_file = pymzml.run.Reader(file_name)
except:
error("Cannot open file '%s'" % file_name)
try: # avoid printing from each rank
comm = MPI.COMM_WORLD
rank = comm.Get_rank()
size = comm.Get_size()
if rank == 0:
file_names = []
for i in range(1, size):
recv_buffer = ""
file_n = comm.recv(recv_buffer, i)
file_names.append(file_n)
print " -> Reading mzML files:"
print file_name
for file_n in file_names:
print file_n
else:
comm.send(file_name, dest=0)
except:
print " -> Reading mzML file '%s'" % (file_name)
scan_list = []
time_list = []
for spectrum in mzml_file:
mass_list = []
intensity_list = []
for mz, i in spectrum.peaks:
mass_list.append(mz)
intensity_list.append(i)
#scan_list.append(Scan(mass_list, intensity_list))
for element in spectrum.xmlTree:
# For some reason there are spectra with no time value,
# Ignore these????????????
if element.get('accession') == "MS:1000016": #time value
# We need time in seconds not minutes
time_list.append(60 * float(element.get('value')))
scan_list.append(Scan(mass_list, intensity_list))
#print "time:", len(time_list)
#print "scan:", len(scan_list)
data = GCMS_data(time_list, scan_list)
return data
def ANDI_reader(file_name):
"""
@summary: A reader for ANDI-MS NetCDF files, returns
a GC-MS data object
@param file_name: The name of the ANDI-MS file
@type file_name: StringType
@author: Qiao Wang
@author: Andrew Isaac
@author: Vladimir Likic
"""
## TODO: use 'point_count' and allow for zero len scans
# the keys used to retrieve certain data from the NetCDF file
__MASS_STRING = "mass_values"
__INTENSITY_STRING = "intensity_values"
__TIME_STRING = "scan_acquisition_time"
if not is_str(file_name):
error("'file_name' must be a string")
try:
file = CDF(file_name)
except CDFError:
error("Cannot open file '%s'" % file_name)
try:# avoid printing from each rank
comm = MPI.COMM_WORLD
rank = comm.Get_rank()
size = comm.Get_size()
if rank ==0:
file_names = []
for i in range(1,size):
recv_buffer = ""
file_n = comm.recv(recv_buffer, i)
file_names.append(file_n)
print " -> Reading netCDF files:"
print file_name
for file_n in file_names:
print file_n
else:
comm.send(file_name, dest=0)
except:
print " -> Reading netCDF file '%s'" % (file_name)
scan_list = []
mass = file.var(__MASS_STRING)
intensity = file.var(__INTENSITY_STRING)
mass_values = mass.get().tolist()
mass_list = []
mass_previous = mass_values[0]
mass_list.append(mass_previous)
intensity_values = intensity.get().tolist()
intensity_list = []
intensity_previous = intensity_values[0]
intensity_list.append(intensity_previous)
if not len(mass_values) == len(intensity_values):
error("length of mass_list is not equal to length of intensity_list !")
for i in range(len(mass_values) - 1):
# assume masses in ascending order until new scan
if mass_previous <= mass_values[i + 1]:
#print mass_values[i+1]
mass_list.append(mass_values[i + 1])
mass_previous = mass_values[i + 1]
intensity_list.append(intensity_values[i + 1])
intensity_previous = intensity_values[i + 1]
# new scan
else:
scan_list.append(Scan(mass_list, intensity_list))
#print "Added scan"
mass_previous = mass_values[i + 1]
intensity_previous = intensity_values[i + 1]
mass_list = []
intensity_list = []
mass_list.append(mass_previous)
intensity_list.append(intensity_previous)
# store final scan
scan_list.append(Scan(mass_list, intensity_list))
time = file.var(__TIME_STRING)
time_list = time.get().tolist()
# sanity check
if not len(time_list) == len(scan_list):
error("number of time points (%d) does not equal the number of scans (%d)"%(len(time_list), len(scan_list)))
data = GCMS_data(time_list, scan_list)
return data
def ANDI_reader(file_name):
"""
@summary: A reader for ANDI-MS NetCDF files, returns
a GC-MS data object
@param file_name: The name of the ANDI-MS file
@type file_name: StringType
@author: Qiao Wang
@author: Andrew Isaac
@author: Vladimir Likic
@author: Tony Chen
"""
__MASS_STRING = "mass_values"
__INTENSITY_STRING = "intensity_values"
__TIME_STRING = "scan_acquisition_time"
if not is_str(file_name):
error("'file_name' must be a string")
try:
dataset = Dataset(file_name, 'r')
except:
error("Cannot open file '%s'" % file_name)
print " -> Reading netCDF file '%s'" % (file_name)
scan_list = list()
# mass = np.array(dataset.variables[__MASS_STRING])
# intensity = np.array(dataset.variables[__INTENSITY_STRING])
mass_values = np.array(dataset.variables[__MASS_STRING])
mass_list = list()
mass_previous = mass_values[0]
mass_list.append(mass_previous)
intensity_values = np.array(dataset.variables[__INTENSITY_STRING])
intensity_list = list()
intensity_previous = intensity_values[0]
intensity_list.append(intensity_previous)
if not len(mass_values) == len(intensity_values):
error("length of mass_list is not equal to length of intensity_list !")
for i in range(len(mass_values) - 1):
# assume masses in ascending order until new scan
if mass_previous <= mass_values[i + 1]:
mass_list.append(mass_values[i + 1])
mass_previous = mass_values[i + 1]
intensity_list.append(intensity_values[i + 1])
intensity_previous = intensity_values[i + 1]
# new scan
else:
scan_list.append(Scan(mass_list, intensity_list))
mass_previous = mass_values[i + 1]
intensity_previous = intensity_values[i + 1]
mass_list = list()
intensity_list = list()
mass_list.append(mass_previous)
intensity_list.append(intensity_previous)
# store final scan
scan_list.append(Scan(mass_list, intensity_list))
time_list = np.array(dataset.variables[__TIME_STRING])
# sanity check
if not len(time_list) == len(scan_list):
error("number of time points does not equal the number of scans")
data = GCMS_data(time_list, scan_list)
return data
def ANDI_reader(file_name):
"""
@summary: A reader for ANDI-MS NetCDF files, returns
a GC-MS data object
@param file_name: The name of the ANDI-MS file
@type file_name: StringType
@author: Qiao Wang
@author: Andrew Isaac
@author: Vladimir Likic
"""
## TODO: use 'point_count' and allow for zero len scans
# the keys used to retrieve certain data from the NetCDF file
__MASS_STRING = "mass_values"
__INTENSITY_STRING = "intensity_values"
__TIME_STRING = "scan_acquisition_time"
if not is_str(file_name):
error("'file_name' must be a string")
try:
#file = CDF(file_name)
rootgrp = Dataset(file_name, "r+", format='NETCDF3_CLASSIC')
except:
raise RuntimeError("Cannot open file '%s'" % file_name)
print " -> Reading netCDF file '%s'" % (file_name)
print rootgrp.variables[__MASS_STRING][:]
scan_list = []
# mass = file.var(__MASS_STRING) # old pycdf way
# intensity = file.var(__INTENSITY_STRING) #old pycdf way
mass = rootgrp.variables[__MASS_STRING][:]
intensity = rootgrp.variables[__INTENSITY_STRING][:]
mass_values = mass.tolist()
mass_list = []
mass_previous = mass_values[0]
mass_list.append(mass_previous)
intensity_values = intensity.tolist()
intensity_list = []
intensity_previous = intensity_values[0]
intensity_list.append(intensity_previous)
if not len(mass_values) == len(intensity_values):
error("length of mass_list is not equal to length of intensity_list !")
for i in range(len(mass_values) - 1):
# assume masses in ascending order until new scan
if mass_previous <= mass_values[i + 1]:
#print mass_values[i+1]
mass_list.append(mass_values[i + 1])
mass_previous = mass_values[i + 1]
intensity_list.append(intensity_values[i + 1])
intensity_previous = intensity_values[i + 1]
# new scan
else:
scan_list.append(Scan(mass_list, intensity_list))
#print "Added scan"
mass_previous = mass_values[i + 1]
intensity_previous = intensity_values[i + 1]
mass_list = []
intensity_list = []
mass_list.append(mass_previous)
intensity_list.append(intensity_previous)
# store final scan
scan_list.append(Scan(mass_list, intensity_list))
# time = file.var(__TIME_STRING) #old pycdf way
time = rootgrp.variables[__TIME_STRING][:]
time_list = time.tolist()
# sanity check
if not len(time_list) == len(scan_list):
raise RuntimeError(
"number of time points does not equal the number of scans")
data = GCMS_data(time_list, scan_list)
return data
def diff(data1: GCMS_data, data2: GCMS_data):
"""
Compares two GCMS_data objects
:param data1: GCMS data set 1
:type data1: pyms.GCMS.Class.GCMS_data
:param data2: GCMS data set 2
:type data2: pyms.GCMS.Class.GCMS_data
:author: Qiao Wang
:author: Andrew Isaac
:author: Vladimir Likic
"""
# get time attributes
time_list1 = data1.get_time_list()
time_list2 = data2.get_time_list()
# First, check if two data sets have the same number of retention times.
if len(time_list1) != len(time_list2):
print(" The number of retention time points differ.")
print(f" First data set: {len(time_list1):d} time points")
print(f" Second data set: {len(time_list2):d} time points")
print(" Data sets are different.")
return
else:
time_rmsd = rmsd(time_list1, time_list2)
print(" Data sets have the same number of time points.")
print(f" Time RMSD: {time_rmsd:.2e}")
# Second, check if each scan has the same number of m/z intensities
print(" Checking for consistency in scan lengths ...", end='')
sys.stdout.flush()
scan_list1 = data1.get_scan_list()
scan_list2 = data2.get_scan_list()
if not len(scan_list1) == len(scan_list2):
# since the number of rention times are the same, this indicated
# some unexpected problem with data
raise ValueError("inconsistency in data detected")
for ii in range(len(scan_list1)):
scan1 = scan_list1[ii]
scan2 = scan_list2[ii]
mass_list1 = scan1.get_mass_list()
mass_list2 = scan2.get_mass_list()
if len(mass_list1) != len(mass_list2):
print(f"\n Different number of points detected in scan no. {ii:d}")
print(" Data sets are different.")
return
print("OK")
# Third, if here, calculate the max RMSD for m/z and intensities
print(" Calculating maximum RMSD for m/z values and intensities ...",
end='')
sys.stdout.flush()
max_mass_rmsd = 0.0
max_intensity_rmsd = 0.0
for ii in range(len(scan_list1)):
scan1 = scan_list1[ii]
scan2 = scan_list2[ii]
mass_list1 = scan1.get_mass_list()
mass_list2 = scan2.get_mass_list()
intensity_list1 = scan1.get_intensity_list()
intensity_list2 = scan2.get_intensity_list()
mass_rmsd = rmsd(mass_list1, mass_list2)
if mass_rmsd > max_mass_rmsd:
max_mass_rmsd = mass_rmsd
intensity_rmsd = rmsd(intensity_list1, intensity_list2)
if intensity_rmsd > max_intensity_rmsd:
max_intensity_rmsd = intensity_rmsd
print(f"\n Max m/z RMSD: {max_mass_rmsd:.2e}")
print(f" Max intensity RMSD: {max_intensity_rmsd:.2e}")
