def test_load_filename_errors_2(self, filename, expects, datadir):
with pytest.raises(expects):
load_peaks(datadir / filename)
def test_load_peaks(self, filtered_peak_list, datadir, outputdir,
peak_list_filename):
loaded_peak_list = load_peaks(peak_list_filename)
assert loaded_peak_list == filtered_peak_list
def test_load_filename_errors_1(self, filename):
with pytest.raises(TypeError):
load_peaks(filename)
def qualitative_processing(self, sample_name, rt_list, n_peaks=80):
"""
:param sample_name:
:type sample_name:
:param rt_list:
:type rt_list:
:param n_peaks: Number of peaks to include in the report
:type n_peaks: int
:return:
:rtype:
"""
# Initialise variables
time_list = []
intensity_list = []
# Load saved TIC
with open(os.path.join(self.config.expr_dir, "{}_tic.dat".format(sample_name))) as tic_file:
ticreader = csv.reader(tic_file, delimiter=" ")
for row in ticreader:
row = list(filter(None, row))
intensity_list.append(float(row[1]))
time_list.append(float(row[0]))
# tic = IonChromatogram(numpy.array(intensity_list), time_list)
# Load the peak list from file
peak_list = load_peaks(os.path.join(self.config.expr_dir, "{}_peaks.dat".format(sample_name)))
# Obtain area for each peak
peak_area_list = []
for peak in peak_list:
area = peak.get_area()
peak_area_list.append(area)
# Write output to CSV file
combined_csv_file = os.path.join(self.config.csv_dir, "{}_COMBINED.csv".format(sample_name))
with open(combined_csv_file, "w") as combine_csv:
# Sample name and header row
combine_csv.write(f"""{sample_name}
Retention Time;Peak Area;;Lib;Match;R Match;Name;CAS Number;Notes
""")
report_buffer = []
# Filter to those peaks present in all samples, by UID
for peak in peak_list:
# if str(rounders(peak.get_rt()/60,"0.000")) in rt_list:
# print(peak.get_rt()/60.0)
# TODO: there is a simpler way to do this as part of the DPA functions
# DDF 20/11/19
if peak.get_rt() / 60.0 in rt_list:
report_buffer.append([
'',
# rounders(peak.get_rt()/60,"0.000"),
(peak.get_rt() / 60),
'',
peak.get_mass_spectrum(),
# '{:,}'.format(rounders(peak.get_area()/60,"0.0"))
'{:,}'.format(peak.get_area() / 60)
])
# TODO: I thought this was supposed to filter to show the 80 largest peaks,
# but I'm not sure it actually does that
# DDF 20/11/19
# Reverse list order
report_buffer = report_buffer[::-1]
# Get last 80 peaks
report_buffer = report_buffer[:n_peaks]
# Sort by retention time
report_buffer.sort(key=operator.itemgetter(1))
# Iterate over peaks
for row_idx, row in enumerate(report_buffer):
# TODO: some tidying up here; is writing to disk the most efficient?
# DDF 20/11/19
# if row_idx == 19:
# Get mass spectrum
ms = row[3]
# Number of hits to get from NIST MS Search
n_hits = 10
# Create MSP file for the peak
self.create_msp("{}_{}".format(sample_name, row[1]), ms.mass_list, ms.mass_spec)
matches_dict = self.nist_ms_comparison(
"{}_{}".format(sample_name, row[1]),
ms.mass_list, ms.mass_spec, n_hits
)
combine_csv.write("{};{};Page {} of 80;;;;;;{}\n".format(row[1], row[4], row_idx + 1, row[2]))
for hit in range(1, n_hits + 1):
combine_csv.write(';;{};{};{};{};{};{};\n'.format(
hit,
matches_dict["Hit{}".format(hit)]["Lib"],
matches_dict["Hit{}".format(hit)]["MF"],
matches_dict["Hit{}".format(hit)]["RMF"],
matches_dict["Hit{}".format(hit)]["Name"].replace(";", ":"),
matches_dict["Hit{}".format(hit)]["CAS"],
))
time.sleep(2)
return 0
