def check_file(filename):
if (not os.access(filename, os.R_OK)):
print "%s is not accessible." % filename
print usage_mesg
sys.exit(1)
filename_mzXML = sys.argv[1]
filename_hit_list = sys.argv[2]
check_file(filename_mzXML)
check_file(filename_hit_list)
ms1_mz2i = dict()
mzXML = MzXML()
mzXML.parse_file(filename_mzXML)
for tmp_ms1 in mzXML.MS1_list:
scan_id = tmp_ms1.id
ms1_mz2i[scan_id] = dict()
for i in range(0, len(tmp_ms1.mz_list)):
tmp_mz = tmp_ms1.mz_list[i]
tmp_i = tmp_ms1.intensity_list[i]
ms1_mz2i[scan_id][tmp_mz] = tmp_i
ms2_precursor_i = dict()
for tmp_ms2 in mzXML.MS2_list:
scan_id = tmp_ms2.id
ms2_precursor_i[scan_id] = tmp_ms2.precursor_intensity
mz2scan = dict()
import sys
import os
# from MSScan import MS1Scan, MS2Scan
from MzXML import MzXML
usage_mesg = "mzxml2ms1.py <mzXML file>"
if len(sys.argv) != 2:
print usage_mesg
sys.exit(1)
filename_mzXML = sys.argv[1]
if not os.access(filename_mzXML, os.R_OK):
print "%s is not accessible." % filename_mzXML
print usage_mesg
sys.exit(1)
mzXML = MzXML()
mzXML.parse_file(filename_mzXML)
sys.stderr.write("Write %s.ms1 ... " % filename_mzXML)
f_out = open(filename_mzXML + ".ms1", "w")
for tmp_ms1 in mzXML.MS1_list:
f_out.write("S\t%06d\t%06d\n" % (tmp_ms1.id, tmp_ms1.id))
f_out.write("I\tRetTime\t%.2f\n" % (tmp_ms1.retention_time))
for i in range(0, len(tmp_ms1.mz_list)):
f_out.write("%f\t%.2f\t0\n" % (tmp_ms1.mz_list[i], tmp_ms1.intensity_list[i]))
f_out.close()
sys.stderr.write("Done\n")
t_flag = True
except:
threshold_input = raw_input("\nIncorrect input, please enter just a number.\nThreshold: ")
try:
outputName = str(raw_input("What would you like to call this data set? (No spaces please.) Name: "))
except:
outputName = raw_input("Enter name: ")
# Sets up book keeping lists and then processes it depending on if it's an mzXML file or mzML file .
neg_pos_mz_sets = [[], []]
# Use correct processing based on filetype
for f in files:
if ".mzXML" in f:
mzXML = MzXML()
mzXML.parse_file(f)
neg_pos_mz_sets_temp = XML_process(mzXML, threshold=threshold)
neg_pos_mz_sets[0] = neg_pos_mz_sets[0] + neg_pos_mz_sets_temp[0]
neg_pos_mz_sets[1] = neg_pos_mz_sets[1] + neg_pos_mz_sets_temp[1]
elif ".mzML" in f:
# Use ML processing
print "Reading %s ..." % f
neg_pos_mz_sets_temp = ML_process(f, threshold=threshold)
neg_pos_mz_sets[0] = neg_pos_mz_sets[0] + neg_pos_mz_sets_temp[0]
neg_pos_mz_sets[1] = neg_pos_mz_sets[1] + neg_pos_mz_sets_temp[1]
# Removes all duplicates from both neg and pos lists
neg_pos_mz_sets[0] = list(set(neg_pos_mz_sets[0]))
neg_pos_mz_sets[1] = list(set(neg_pos_mz_sets[1]))