assert "ProteinName" in header
assert "rt_calibrated" in header
assert "charge" in header
assert "product" in header
assert "library_intensity" in header
# group the csv lines by their group id
tr_group = {}
for line in lines:
if line[header_d["group_id"]] in tr_group:
tr_group[line[header_d["group_id"]]].append(line)
else:
tr_group[line[header_d["group_id"]]] = [line]
# loop through all groups and create a sptxt spectrum for each group
l = speclib_db_lib.Library(1)
cnt = 0
for key in tr_group:
group = tr_group[key]
firstline = group[0]
spectrum = speclib_db_lib.Spectra()
spectrum.name = firstline[header_d["group_id"]].replace('.', '/')
spectrum.LibID = 1
spectrum.MW = firstline[header_d["precursor"]]
spectrum.precursorMZ = firstline[header_d["precursor"]]
spectrum.status = "Normal"
spectrum.full_name = firstline[header_d["group_id"]].replace('.', '/')
spectrum.sequence = firstline[header_d["PeptideSequence"]]
spectrum.number_peaks = len(group)
##### The comment
def main(argv) :
distance = 1.0
algorithm = False
#Get options
try:
opts, args = getopt.getopt(argv, "hd:i:t:a:",["help","distance","algorithm"])
except getopt.GetoptError:
usage()
sys.exit(2)
argsUsed = 0
for opt,arg in opts:
if opt in ("-h","--help") :
usage()
sys.exit()
if opt in ("-d","--distance") :
distance = float(arg)
argsUsed += 2
if opt in ("-a","--algorithm") :
algorithm = arg
argsUsed += 2
sptxtfiles_pat = argv[argsUsed:]
sptxtfiles = []
for pat in sptxtfiles_pat :
sptxtf = glob.glob(pat)
for file in sptxtf : sptxtfiles.append(file)
for sptxtfile in sptxtfiles :
transitions = []
print("Reading : " , sptxtfile)
assert sptxtfile[-6:] == '.sptxt'
if not os.path.exists(sptxtfile):
print("The file: %s does not exist!" % sptxtfile)
sys.exit(2)
library_key = 99
spectrastlib = speclib_db_lib.Library(library_key)
num_spectrum = 0
offset = spectrastlib.get_first_offset(sptxtfile)
last_offset = -100
#Get all the peptide sequences and retention times to cluster them. Keep the spectrum number associated.
peptide_spectra = {} # { "SEQUEN[Pho]CE" : {last_offset1 : RT1 , last_offset2 : RT2 } , "SEQUENCE" : {last_offset3 : RT3 , last_offset4 : RT4 , ... } , ... }
while ( offset - last_offset > 10) :
last_offset = offset
offset , spectrum = spectrastlib.read_sptxt_with_offset(sptxtfile,offset)
#for property, value in vars(spectrum).iteritems():
# if property in ['compress_spectra' ] : continue
# print property, ": ", value
#sys.exit()
sequence = spectrum.name.split('/')[0]
z_parent = float(spectrum.name.split('/')[1])
if spectrum.RetTime_detected:
rt = spectrum.RetTime
if spectrum.iRT_detected:
rt = spectrum.iRT
if not spectrum.RetTime_detected and not spectrum.iRT_detected:
print("No RT/iRT was detected for %s" % spectrum.name)
sys.exit(2)
if sequence in list(peptide_spectra.keys()) :
peptide_spectra[sequence][last_offset] = rt
else :
peptide_spectra[sequence] = { last_offset : rt }
max_num_of_clusters = 0
peptide_spectra_cl = {}
print("cluster spectra by iRTs...")
for sequence, spectra in peptide_spectra.items() :
print(sequence) #, spectra
rt_clusters = clusterRT(list(spectra.values()), distance, algorithm = algorithm)
if len(rt_clusters) > max_num_of_clusters : max_num_of_clusters = len(rt_clusters)
peptide_spectra_cl[sequence] = {}
for spectrum, rt in spectra.items() :
# Determine cluster number for this rt
cl_index = -1
for index, cluster in enumerate(rt_clusters) :
#print index, rt, cluster
cl = cluster
if not isinstance(cluster,list) : cl = [cluster]
if rt in cl : cl_index = index
#store cluster index in a dictionary
peptide_spectra_cl[sequence][spectrum] = cl_index
splitfiles = [ open(sptxtfile[:-6]+"_"+str(x+1)+".sptxt",'w') for x in range(max_num_of_clusters) ]
#init the files by using the original header
print("%s files will be created." % max_num_of_clusters)
original_header = spectrastlib.get_fileheader(sptxtfile)
for file in splitfiles :
for line in original_header : file.write(line)
for sequence, spectra in peptide_spectra_cl.items() :
for spectrum in spectra :
sp = spectrastlib.get_rawspectrum_with_offset(sptxtfile,spectrum) #get the spectrum
for line in sp :
#Add suffix to the protein name
if 'Comment:' in line[:8] :
line_bcp = line
mm = re.search( 'Protein=(.*?)\s', line )
if not mm: break
split_idx = line.index('Protein=') + 8
line_before_split = line[:split_idx]
line_after_split = line[split_idx:]
line = line_before_split + "Subgroup_" + str(peptide_spectra_cl[sequence][spectrum]) + "_" + line_after_split
splitfiles[peptide_spectra_cl[sequence][spectrum]].write(line)
for file in splitfiles :
file.close()
print("done.")