feat: read mzml in simsticher

src/tools/peakStrainer/utils/peakStrainer_util.py

@@ -37,6 +37,8 @@ def decode_mzXML_Peaks(encodedPeaks):
     Note zmass and intensity are together
 
     """
+    if isinstance(encodedPeaks, tuple):  # assume its mzml
+        return decode_mz_ML_Peaks(encodedPeaks[0], encodedPeaks[1])
 
     decoded = b64decode(encodedPeaks)
     peaks = array("f", decoded)
@@ -49,6 +51,21 @@ def decode_mzXML_Peaks(encodedPeaks):
     return mass, intens
 
 
+def decode_mz_ML_Peaks(mass_encoded, inty_encoded):
+
+    mass_decoded = b64decode(mass_encoded)
+    inty_decoded = b64decode(inty_encoded)
+
+    mass_peaks = array("f", mass_decoded)
+    inty_peaks = array("f", inty_decoded)
+
+    if sys.byteorder != "big":
+        mass_peaks.byteswap()
+        inty_peaks.byteswap()
+
+    return mass_peaks, inty_peaks
+
+
 def ThermoRawfile2Scans_sample(file_path):
     log.info("file: %s", file_path)
     rawfile = MSFileReader.ThermoRawfile(file_path)
@@ -145,6 +162,42 @@ def getMZXMLEncondedScans(filePath):
     return list(zip(*rawscans))
 
 
+def getMZ_MLEncondedScans(filePath):
+    #     TODO:handle different namespaces of mzxml
+    ns = {
+        "mzml": "http://psi.hupo.org/ms/mzml",
+        "ms": "http://psi.hupo.org/ms/mzml",
+    }
+
+    tree = ET.parse(filePath)
+    root = tree.getroot()
+
+    spectrums = root.findall(".//mzml:spectrum", namespaces=ns)
+
+    rawscans = []
+    for spectrum in spectrums:
+        mz_array_elem = spectrum.find(
+            './/ms:cvParam[@name="m/z array"]/../ms:binaryDataArray',
+            namespaces=ns,
+        )
+        intensity_array_elem = spectrum.find(
+            './/ms:cvParam[@name="intensity array"]/../ms:binaryDataArray',
+            namespaces=ns,
+        )
+        encodedPeaks = (mz_array_elem, intensity_array_elem)
+        scanNo = int(spectrum.get("id").split("=")[-1])
+        filterLine = spectrum.find(
+            './/ms:cvParam[@name="filter string"]', namespaces=ns
+        ).get("value")
+        retTime = spectrum.find(
+            './/ms:cvParam[@name="scan start time"]', namespaces=ns
+        ).get("value")
+        object = (scanNo, filterLine, encodedPeaks, retTime)
+        rawscans.append(object)
+
+    return list(zip(*rawscans))
+
+
 def write2templateMzXML(newfilename, scanPeaks):
     namespaces = {
         "xmlns": "http://sashimi.sourceforge.net/schema_revision/mzXML_3.0"

src/tools/simStitching/simStitcher.py

@@ -15,6 +15,7 @@
 log = logging.getLogger(os.path.basename(__file__))
 from tools.peakStrainer.utils.peakStrainer_util import (
     getMZXMLEncondedScans,
+    getMZ_MLEncondedScans,
     decode_mzXML_Peaks,
     write2templateMzXML,
     encodePeaks,
@@ -23,7 +24,7 @@
 import numpy as np
 import xml.etree.ElementTree as ET
 import copy
-
+from pathlib import Path
 
 class Scan(object):
     class FilterLine(object):
@@ -628,7 +629,7 @@ def simStitcher(
             filemode="w",
         )
 
-    log.info("getMZXMLEncondedScans from" + filePath)
+    log.info("getMZ_MLEncondedScans from" + filePath)
     scans_mzxml = getMZXMLEncondedScanRows(filePath)
     log.debug("\n".join(map(str, scans_mzxml)))
 
@@ -883,7 +884,15 @@ def outputAdjustedFile(fileName):
 
 
 def getMZXMLEncondedScanRows(filePath):
-    return list(zip(*getMZXMLEncondedScans(filePath)))
+    p = Path(filePath)
+    if p.suffix.lower() == ".mzxml":
+        return list(zip(*getMZXMLEncondedScans(filePath)))
+    if p.suffix.lower() == ".mzml":
+        # object = (scanNo, filterLine, encodedPeaks, retTime)
+        # rawscans = list[objects]
+        return list(zip(*getMZ_MLEncondedScans(filePath)))
+    else:
+        raise NotImplementedError(f" files of type {p.suffix} are not suppported")
 
 
 if __name__ == "__main__":