merged ms2_recal fixed scientific annotation bug for peaks and some code cleanup

Pipfile

@@ -0,0 +1,27 @@
+[[source]]
+name = "pypi"
+url = "https://pypi.org/simple"
+verify_ssl = true
+
+[dev-packages]
+
+[packages]
+kiwisolver = ">=1.0.1"
+lxml = ">=4.2.3"
+matplotlib = ">=2.2.2"
+numpy = ">=1.14.5"
+pandas = ">=0.23.3"
+pyopenms = ">=2.3.0.4"
+pyparsing = ">=2.2.0"
+pyteomics = ">=3.5.1"
+python-dateutil = ">=2.7.3"
+pytz = ">=2018.5"
+scipy = ">=1.1.0"
+seaborn = ">=0.9.0"
+six = ">=1.11.0"
+subprocess32 = ">=3.5.2"
+"backports.functools_lru_cache" = ">=1.5"
+Cycler = ">=0.10.0"
+
+[requires]
+python_version = "3.7"

ProteoFileReader.py

@@ -13,6 +13,125 @@
 import numpy as np
 import sys
 import pyopenms as oms
+import io
+import os
+
+
+def read_mgf(mgf_file):
+    mgf_reader = io.open(mgf_file, "r")
+
+    spectra = []
+    peaks = []
+    RT, pep_mz, pep_int, charge, scanID, ms2id = -1, -1, -1, -1, -1, -1
+    title, detector, fragmethod = "", "", ""
+    peak_re = re.compile(r'^([0-9.e+\-]+)\s([0-9.e+\-]+)')
+
+    for line in mgf_reader:
+        if len(line.strip()) == 0:
+            continue
+        if re.match(peak_re, line):
+            mz_int_list = re.match(peak_re, line).groups()
+            peaks.append([float(x) for x in mz_int_list])
+        elif line.startswith("TITLE"):
+            title = line.replace('TITLE=', '').strip()
+            # scan_match = re.search("^TITLE=[^.]*.([0-9]+).", line)
+            # ms2id_scan_match = re.search("ms2_scanId=([0-9]+)", line)
+            # scanID = int(scan_match.groups()[0])
+            # if ms2id_scan_match:
+            #     ms2id = int(ms2id_scan_match.groups()[0])
+            # else:
+            #     ms2id = -1
+
+        elif line.startswith("RTINSECONDS"):
+            RT = float(re.search("RTINSECONDS=(.*)", line).groups()[0])
+
+        elif line.startswith("PEPMASS"):
+            precursor = re.search("PEPMASS=(.*)", line).groups()[0].split()
+            pep_mz = float(precursor[0])
+            try:
+                pep_int = float(precursor[1])
+            except:
+                pep_int = -1.0
+
+        elif line.startswith("CHARGE"):
+            charge = float(re.search("CHARGE=(-?\d)", line).groups()[0])
+
+        elif line.startswith("DETECTOR"):
+            detector = re.search("DETECTOR=(.*)", line).groups()[0].strip()
+
+        elif line.startswith("FRAGMETHOD"):
+            fragmethod = re.search("FRAGMETHOD=(.*)", line).groups()[0].strip()
+
+        elif "END IONS" in line:
+            spectra.append(
+                MS2_spectrum(title, RT, pep_mz, pep_int, charge, peaks, detector=detector, fragmethod=fragmethod)
+            )
+            peaks = []
+            title, detector, fragmethod = "", "", ""
+            RT, pep_mz, pep_int, charge, scanID, ms2id = -1, -1, -1, -1, -1, -1
+
+    return spectra
+
+
+def write_mgf(spectra, outfile):
+    out_writer = open(os.path.join(outfile), "w")
+    out_writer.write('MASS=Monoisotopic\n')
+    for spectrum in spectra:
+        title = spectrum.getTitle()
+        # scan = re.search('scan=[0-9]*', title).group(0)[5:]
+        # try:
+        #     title = re.match('([A-Z])[0-9]{6}_[0-9]{2}.+?( )', title).group(0)[:-1]
+        # except AttributeError:
+        #     title = re.match('[0-9]{8}_[0-9]{2}.+?( )', title).group(0)[:-1]
+        # title = '.'.join([title, scan, scan, str(int(spectrum.charge))])
+        if 'ms2_scanId' in spectrum.getTitle():
+            try:
+                ms2_parent = re.search('ms2_scanId=.*scan=([0-9]+)', spectrum.getTitle()).groups()[0]
+            except AttributeError:
+                ms2_parent = 0
+            title += ' ms2_scanId=%s' % ms2_parent
+        stavrox_mgf = """
+BEGIN IONS
+TITLE={}
+PEPMASS={} {}
+CHARGE={}+
+RTINSECONDS={}
+DETECTOR={}
+FRAGMETHOD={}
+{}
+END IONS""".format(
+                title,
+                spectrum.getPrecursorMZ(),
+                spectrum.getPrecursorIntensity() if spectrum.getPrecursorIntensity() > 0 else 0,
+                int(spectrum.charge),
+                spectrum.getRT(),
+                spectrum.getDetector(),
+                spectrum.getFragMethod(),
+                "\n".join([f"{mz} {i}" for mz, i in spectrum.peaks if i > 0])
+            )
+        out_writer.write(stavrox_mgf)
+
+
+def split_mgf_methods(mgf_in_file):
+    ms2_spectra = read_mgf(mgf_in_file)
+
+    methods = [
+        "CID",
+        "HCD",
+        "ETD",
+        "ETciD",
+        "EThcD"
+    ]
+
+    for method in methods:
+        split_spectra = [spectrum for spectrum in ms2_spectra if spectrum.getFragMethod() == method]
+
+        if len(split_spectra) > 0:
+            out_file_name = '%s_%s' % (method, os.path.split(mgf_in_file)[1])
+            out_file_path = os.path.join(os.path.split(mgf_in_file)[0], out_file_name)
+
+            write_mgf(split_spectra, out_file_path)
+
 
 def mzMLReader(in_file):
     """
@@ -26,7 +145,8 @@ def mzMLReader(in_file):
     file = oms.MzMLFile()
     exp = oms.MSExperiment()
     file.load(in_file, exp)
-    return(exp)
+    return exp
+
 
 class MS2_spectrum():
     """
@@ -50,64 +170,71 @@ class MS2_spectrum():
                 charge array for the peaks
 
     """
-    def __init__(self, title, RT, pepmass, pepint, charge, peaks, peakcharge=[]):
+    def __init__(self, title, RT, pepmz, pepint, charge, peaks, peakcharge=[], fragmethod='', detector=''):
         self.title = title
         self.RT = RT
-        self.pepmz = pepmass
+        self.pepmz = pepmz
         self.pepint = pepint
         self.charge = charge
         self.peaks = peaks
         self.peakcharge = peakcharge
+        self.fragMethod = fragmethod
+        self.detector = detector
 
     def getPrecursorMZ(self):
         """
         Returns the precursor mass
         """
-        return(self.pepmz)
+        return self.pepmz
 
     def getPrecursorIntensity(self):
         """
         Returns the precursor intensity
         """
-        return(self.pepint)
+        return self.pepint
 
     def getRT(self):
         """
         Returns the precursor RT
         """
-        return(self.RT)
+        return self.RT
 
     def getTitle(self):
         """
         Returns the precursor mass
         """
-        return(self.title)
+        return self.title
 
     def getPeaks(self):
         """
         Returns the spectrum peaks
         """
-        return(self.peaks)
+        return self.peaks
 
     def getMZ(self):
         """
         Returns the mz of the MS2
         """
-        return(self.peaks[:,0])
+        return self.peaks[:, 0]
 
     def getIntensities(self):
         """
         Returns the MS2 peak intensities
         """
-        return(self.peaks[:,1])
+        return self.peaks[:, 1]
 
     def getUnchargedMass(self):
         """
         Computs the uncharged mass of a fragment:
-        uncharged_mass = (mz * z ) - z
-        TODO: fix Hydrogen mass!
+        uncharged_mass = (mz - hydrogen mass) * z
         """
-        return( (self.pepmass * self.charge) -  self.charge)
+        return (self.pepmz - 1.007276466879) * self.charge
+
+    def getFragMethod(self):
+        return self.fragMethod
+
+    def getDetector(self):
+        return self.detector
 
     def printf(self):
         print ("Title, RT, PEPMASS, PEPINT, CHARGE")
@@ -117,7 +244,7 @@ def to_mgf(self):
         # need dummy values in case no peak charges are in the data
         if len(self.peakcharge) == 0:
             self.peakcharge = [""]*self.peaks.shape[0]
-        mgf_str="""
+        mgf_str = """
 BEGIN IONS
 TITLE=%s
 RTINSECONDS=%s
@@ -126,7 +253,7 @@ def to_mgf(self):
 %s
 END IONS
         """ % (self.title, self.RT, self.pepmz, self.pepint, self.charge, "\r\n".join(["%s %s %s" % (i[0], i[1], j, ) for i,j in zip(self.peaks, self.peakcharge)]))
-        return(mgf_str)
+        return mgf_str
 
 
 #==============================================================================
@@ -343,6 +470,6 @@ def store(self, out_file, ms_list):
 charge=%s
 %s
 peaklist end
-""" % (ms.title, ms.pepmass, ms.charge, "\r\n".join(["%s %s" % (i, j ) for i,j in ms.peaks]))
+""" % (ms.title, ms.pepmass, ms.charge, "\r\n".join(["%s %s" % (i, j) for i,j in ms.peaks]))
             out_mgf.write(mgf_str)
         out_mgf.close()