pymzcbor 0.0.2__py3-none-any.whl

pymzcbor/__init__.py

@@ -0,0 +1,6 @@
+from .harvestmzcbor import HarvestMzCbor
+from .model.mzspectrum import MzSpectrum
+from .mzcborindex import MzCborIdx
+from .mzcborreader import MzCborReader
+from .mzml.mz_reader import MzReader
+from .mzml.mzmlparser import MzMlParser

pymzcbor/cli/__init__.py

@@ -0,0 +1,3 @@
+from .mzcbor2scan import mzcbor2scan
+from .mzcbortic import mzcbortic
+from .mzmltic import mzmltic

pymzcbor/cli/mz2scan.py

@@ -0,0 +1,101 @@
+import json as json_ns
+import os
+import tempfile
+
+import click
+import importlib_resources as resources
+import typst
+
+from pymzcbor import MzReader
+from pymzcbor.model.mzspectrum import MzSpectrum
+
+
+def get_typst_cmd():
+    ref = resources.files("pymzcbor") / "data/typst/scan_report.typ"
+    return ref.read_text(encoding="utf-8")
+
+
+@click.command()
+@click.argument("input", nargs=1)
+@click.option(
+    "--index",
+    prompt="list of scan index to extract",
+    help="list of scan index to extract.",
+)
+@click.option("--json", help="The JSON file containing scans.")
+@click.option("--mgf", help="The MGF file containing scans.")
+@click.option(
+    "--pdf",
+    help="The PDF output to display scans.",
+    default="scans.pdf",
+)
+def mzcbor2scan(input, index, json, pdf, mgf):
+    """MassChroQ CBOR data file extractor to JSON."""
+
+    scan_json = []
+    index_num_list = []
+    precursor_scan_json = {}
+
+    for str_num in index.split():
+        index_num_list.append(int(str_num))
+    mz_reader = MzReader(input)
+
+    mgf_data_file = None
+
+    if mgf is not None:
+        # print(json_string)
+        print("write MGF output file : ", mgf)
+        mgf_data_file = open(mgf, "w")
+
+    for spectrum_index in index_num_list:
+        mz_spectrum = mz_reader.get_mz_spectrum_by_index(0, spectrum_index)
+        if mz_spectrum is not None:
+            if mgf_data_file is not None:
+                mgf_data_file.write(mz_spectrum.to_mgf())
+            scan_json.append(mz_spectrum.to_dict())
+            precursor_list = mz_spectrum.get_precursor_list()
+            if precursor_list is not None:
+                for precursor_mz in precursor_list:
+                    precursor_id = precursor_mz.spectrum_ref
+                    precursor_spectrum = mz_reader.get_mz_spectrum_by_native_id(
+                        0, precursor_id
+                    )
+                    if precursor_spectrum is not None:
+                        precursor_scan_json[precursor_id] = precursor_spectrum.to_dict()
+
+    if mgf_data_file is not None:
+        mgf_data_file.close()
+
+    json_string = json_ns.dumps(
+        {"precursor_spectrum_map": precursor_scan_json, "scan_list": scan_json},
+        indent=4,
+    )
+    if json is not None:
+        # print(json_string)
+
+        print("write json output file : ", json)
+        with open(json, "w") as json_data_file:
+            json_data_file.write(json_string)
+            json_data_file.close()
+    else:
+        with tempfile.TemporaryDirectory() as tmpdirname:
+            print("created temporary directory", tmpdirname)
+            with open(
+                os.path.join(tmpdirname, "scan_data.json"), "w"
+            ) as json_data_file:
+                json_data_file.write(json_string)
+                json_data_file.close()
+                with open(
+                    os.path.join(tmpdirname, "scan_report.typ"), "w"
+                ) as align_typ_file:
+                    print("write pdf output file : ", pdf)
+                    align_typ_file.write(get_typst_cmd())
+                    align_typ_file.close()
+                    typst.compile(
+                        os.path.join(tmpdirname, "scan_report.typ"),
+                        output=pdf,
+                    )
+
+
+if __name__ == "__main__":
+    mzcbor2scan()

pymzcbor/cli/mzcbor2scan.py

@@ -0,0 +1,101 @@
+import json as json_ns
+import os
+import tempfile
+
+import click
+import importlib_resources as resources
+import typst
+
+from pymzcbor import MzReader
+from pymzcbor.model.mzspectrum import MzSpectrum
+
+
+def get_typst_cmd():
+    ref = resources.files("pymzcbor") / "data/typst/scan_report.typ"
+    return ref.read_text(encoding="utf-8")
+
+
+@click.command()
+@click.argument("input", nargs=1)
+@click.option(
+    "--index",
+    prompt="list of scan index to extract",
+    help="list of scan index to extract.",
+)
+@click.option("--json", help="The JSON file containing scans.")
+@click.option("--mgf", help="The MGF file containing scans.")
+@click.option(
+    "--pdf",
+    help="The PDF output to display scans.",
+    default="scans.pdf",
+)
+def mzcbor2scan(input, index, json, pdf, mgf):
+    """MassChroQ CBOR data file extractor to JSON."""
+
+    scan_json = []
+    index_num_list = []
+    precursor_scan_json = {}
+
+    for str_num in index.split():
+        index_num_list.append(int(str_num))
+    mz_reader = MzReader(input)
+
+    mgf_data_file = None
+
+    if mgf is not None:
+        # print(json_string)
+        print("write MGF output file : ", mgf)
+        mgf_data_file = open(mgf, "w")
+
+    for spectrum_index in index_num_list:
+        mz_spectrum = mz_reader.get_mz_spectrum_by_index(0, spectrum_index)
+        if mz_spectrum is not None:
+            if mgf_data_file is not None:
+                mgf_data_file.write(mz_spectrum.to_mgf())
+            scan_json.append(mz_spectrum.to_dict())
+            precursor_list = mz_spectrum.get_precursor_list()
+            if precursor_list is not None:
+                for precursor_mz in precursor_list:
+                    precursor_id = precursor_mz.spectrum_ref
+                    precursor_spectrum = mz_reader.get_mz_spectrum_by_native_id(
+                        0, precursor_id
+                    )
+                    if precursor_spectrum is not None:
+                        precursor_scan_json[precursor_id] = precursor_spectrum.to_dict()
+
+    if mgf_data_file is not None:
+        mgf_data_file.close()
+
+    json_string = json_ns.dumps(
+        {"precursor_spectrum_map": precursor_scan_json, "scan_list": scan_json},
+        indent=4,
+    )
+    if json is not None:
+        # print(json_string)
+
+        print("write json output file : ", json)
+        with open(json, "w") as json_data_file:
+            json_data_file.write(json_string)
+            json_data_file.close()
+    else:
+        with tempfile.TemporaryDirectory() as tmpdirname:
+            print("created temporary directory", tmpdirname)
+            with open(
+                os.path.join(tmpdirname, "scan_data.json"), "w"
+            ) as json_data_file:
+                json_data_file.write(json_string)
+                json_data_file.close()
+                with open(
+                    os.path.join(tmpdirname, "scan_report.typ"), "w"
+                ) as align_typ_file:
+                    print("write pdf output file : ", pdf)
+                    align_typ_file.write(get_typst_cmd())
+                    align_typ_file.close()
+                    typst.compile(
+                        os.path.join(tmpdirname, "scan_report.typ"),
+                        output=pdf,
+                    )
+
+
+if __name__ == "__main__":
+    mzcbor2scan()

pymzcbor/cli/mzcbortic.py

@@ -0,0 +1,65 @@
+import json as json_ns
+import os
+import tempfile
+
+import click
+import importlib_resources as resources
+import typst
+
+from pymzcbor import MzCborReader
+
+
+def get_typst_cmd():
+    ref = resources.files("pymzcbor") / "data/typst/tic.typ"
+    return ref.read_text(encoding="utf-8")
+
+
+@click.command()
+@click.argument("input", nargs=1)
+@click.option(
+    "--pdf",
+    help="The PDF output to display total ion count chromatogram.",
+    default="tic.pdf",
+)
+def mzcbortic(input, pdf):
+    """MassChroQ CBOR data file extractor to JSON."""
+
+    mz_reader = MzCborReader(input)
+
+    tic_dict = mz_reader.mzcbor_index.get_tic_chromatogram(0)
+
+    source_file_list = mz_reader.get_source_file_list()
+    title = "Total Ion Count"
+    if len(source_file_list) > 0:
+        title = source_file_list[0].get("name")
+
+    json_string = json_ns.dumps(
+        {
+            "title": title,
+            "tic": tic_dict,
+            "rt_units": "minutes",
+            "scan_count": {
+                "MS1": mz_reader.mzcbor_index.count_msn_in_run(0, 1),
+                "MS2": mz_reader.mzcbor_index.count_msn_in_run(0, 2),
+            },
+        },
+        indent=4,
+    )
+    if tic_dict is not None:
+        with tempfile.TemporaryDirectory() as tmpdirname:
+            print("created temporary directory", tmpdirname)
+            with open(os.path.join(tmpdirname, "tic.json"), "w") as json_data_file:
+                json_data_file.write(json_string)
+                json_data_file.close()
+                with open(os.path.join(tmpdirname, "tic.typ"), "w") as tic_file:
+                    print("write pdf output file : ", pdf)
+                    tic_file.write(get_typst_cmd())
+                    tic_file.close()
+                    typst.compile(
+                        os.path.join(tmpdirname, "tic.typ"),
+                        output=pdf,
+                    )
+
+
+if __name__ == "__main__":
+    mzcbortic()

pymzcbor/cli/mzmltic.py

@@ -0,0 +1,91 @@
+import json as json_ns
+import os
+import tempfile
+import xml.etree.ElementTree as ET
+
+import click
+import importlib_resources as resources
+import typst
+from pyteomics import mzml
+
+
+def get_typst_cmd():
+    ref = resources.files("pymzcbor") / "data/typst/tic.typ"
+    return ref.read_text(encoding="utf-8")
+
+
+def get_retention_time_in_second(spectrum: dict) -> float:
+    #    <cvParam cvRef="MS" accession="MS:1000016" value="0.0048758833" name="scan start time" unitAccession="UO:0000031" unitName="minute" unitCvRef="UO" />
+    start_time = spectrum["scanList"]["scan"][0]["scan start time"]
+    if start_time.unit_info == "second":
+        return start_time
+    if start_time.unit_info == "minute":
+        return start_time * 60
+
+
+def get_mzml_sample_name(input: str) -> str:
+    try:
+        context = ET.iterparse(input, events=("start", "end"))
+        for event, elem in context:
+            # print(elem.tag)
+            if event == "start" and elem.tag.endswith("}sourceFile"):
+                return elem.attrib["name"]
+        return ""
+    except:
+        return ""
+
+
+@click.command()
+@click.argument("input", nargs=1)
+@click.option(
+    "--pdf",
+    help="The PDF output to display total ion count chromatogram.",
+    default="tic.pdf",
+)
+def mzmltic(input, pdf):
+    """MassChroQ CBOR data file extractor to JSON.
+    reading mzML using pyteomics"""
+
+    title = get_mzml_sample_name(input)
+    # print(title)
+    tic_dict = {"x": [], "y": []}
+    ms1_count = 0
+    ms2_count = 0
+    with mzml.read(input) as reader:
+        for chromatogram in reader:
+            if chromatogram["ms level"] == 1:
+                ms1_count += 1
+                tic_dict["y"].append(chromatogram["total ion current"])
+                tic_dict["x"].append(get_retention_time_in_second(chromatogram))
+            elif chromatogram["ms level"] == 2:
+                ms2_count += 1
+
+    json_string = json_ns.dumps(
+        {
+            "title": title,
+            "tic": tic_dict,
+            "scan_count": {
+                "MS1": ms1_count,
+                "MS2": ms2_count,
+            },
+        },
+        indent=4,
+    )
+    if tic_dict is not None:
+        with tempfile.TemporaryDirectory() as tmpdirname:
+            print("created temporary directory", tmpdirname)
+            with open(os.path.join(tmpdirname, "tic.json"), "w") as json_data_file:
+                json_data_file.write(json_string)
+                json_data_file.close()
+                with open(os.path.join(tmpdirname, "tic.typ"), "w") as tic_file:
+                    print("write pdf output file : ", pdf)
+                    tic_file.write(get_typst_cmd())
+                    tic_file.close()
+                    typst.compile(
+                        os.path.join(tmpdirname, "tic.typ"),
+                        output=pdf,
+                    )
+
+
+if __name__ == "__main__":
+    mzmltic()

pymzcbor/data/typst/scan_report.typ

@@ -0,0 +1,119 @@
+#import "@preview/proteograph:0.2.2": *
+
+= Display spectra
+
+#let mcq3_json = json("scan_data.json")
+
+
+/// Filter to keep only m/z higher than threshold
+/// -> object
+#let spectra-filter-high-pass(spectra, mz-cutoff) = {
+  let spectra-zip = spectra.intensity.zip(spectra.mz)
+  let new-spectra = (mz: (), intensity: ())
+
+  for (intensity, mz) in spectra-zip {
+    if (mz > mz-cutoff) {
+      new-spectra.intensity.push(intensity)
+      new-spectra.mz.push(mz)
+    }
+  }
+  (new-spectra)
+}
+
+/// Filter to keep only m/z lower than threshold
+/// -> object
+#let spectra-filter-low-pass(spectra, mz-cutoff) = {
+  let spectra-zip = spectra.intensity.zip(spectra.mz)
+  let new-spectra = (mz: (), intensity: ())
+
+  for (intensity, mz) in spectra-zip {
+    if (mz < mz-cutoff) {
+      new-spectra.intensity.push(intensity)
+      new-spectra.mz.push(mz)
+    }
+  }
+  (new-spectra)
+}
+
+
+#let find-cv-param(cv-param-list, accession) = {
+  cv-param-list.find(cv-param => {
+    if (cv-param.accession == accession) {
+      true
+    } else { false }
+  })
+}
+
+#let mzcborjson-get-precursor-isolation-window(one-precursor) = {
+  (
+    "cv-target": find-cv-param(one-precursor.isolationWindow.cvParam, "MS:1000827"),
+    "cv-target-lower": find-cv-param(one-precursor.isolationWindow.cvParam, "MS:1000828"),
+    "cv-target-upper": find-cv-param(one-precursor.isolationWindow.cvParam, "MS:1000829"),
+  )
+}
+#let mz_spectrum2spectrum_array(mz_spectrum) = {
+  let spectra = ("mz": (), "intensity": ())
+  if (mz_spectrum.binaryDataArray.at(0).unit == "MS:1000514") {
+    spectra.mz = mz_spectrum.binaryDataArray.at(0).data
+  } else {
+    spectra.intensity = mz_spectrum.binaryDataArray.at(0).data
+  }
+  if (mz_spectrum.binaryDataArray.at(1).unit == "MS:1000515") {
+    spectra.intensity = mz_spectrum.binaryDataArray.at(1).data
+  } else {
+    spectra.mz = mz_spectrum.binaryDataArray.at(1).data
+  }
+  spectra
+}
+
+
+
+
+#for scan in mcq3_json.scan_list {
+  //[== index=#{ scan.index } #{ scan.id }]
+
+  let precursor-list = scan.at("precursorList", default: none)
+  if (precursor-list != none) {
+    for precursor in precursor-list.precursor {
+      //print precursor isolation window
+      let window = mzcborjson-get-precursor-isolation-window(precursor)
+      let mz-low = window.cv-target.value - window.cv-target-lower.value
+      let mz-up = window.cv-target.value + window.cv-target-upper.value
+
+      let delta_arr = (
+        (
+          "ion": "y",
+          "mz": (mz-low, mz-up),
+          "level": 1,
+          "label": "selection",
+        ),
+      )
+
+      let precursor-id = precursor.spectrumRef
+      let mz_prec_spectrum = mcq3_json.precursor_spectrum_map.at(precursor-id, default: none)
+      if (mz_prec_spectrum != none) {
+        box({
+          mzcborjson-report-spectrum-metadata(mz_prec_spectrum)
+          ms2spectra-plot(
+            width: 15cm,
+            height: 7cm,
+            spectra: spectra-filter-low-pass(
+              spectra-filter-high-pass(mz_spectrum2spectrum_array(mz_prec_spectrum), mz-low - 4),
+              mz-up + 4,
+            ),
+            delta: delta_arr,
+            mz-range: (mz-low - 4, mz-up + 4),
+          )
+        })
+      }
+    }
+  }
+  box({
+    mzcborjson-report-spectrum-metadata(scan)
+    // "binaryDataArray": [
+    //   {
+    //     "unit": "MS:1000514",
+    //     "data": [
+    ms2spectra-plot(width: 15cm, height: 7cm, spectra: mz_spectrum2spectrum_array(scan))
+  })
+}

pymzcbor/data/typst/tic.typ

@@ -0,0 +1,19 @@
+#import "@preview/proteograph:0.2.2": *
+
+
+#let tic_json = json("tic.json")
+
+= #tic_json.title
+
+
+#let xic0 = tic_json.tic
+#xic0.insert("TIC", "TIC")
+
+#xic-plot(
+  height: 10cm,
+  title: "Total Ion Count",
+  xic0,
+)
+
+/ MS1 count: #tic_json.scan_count.MS1
+/ MS2 count: #tic_json.scan_count.MS2

pymzcbor/enums.py

@@ -0,0 +1,52 @@
+# This file is part of pymzcbor.
+#
+# pymzcbor is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# pymzcbor is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with pymzcbor. If not, see <http://www.gnu.org/licenses/>.
+#
+from enum import Enum
+
+
+class MzDataArrayType(Enum):
+    mz = "MS:1000514"  # "MS:1000514"
+    intensity = "MS:1000515"  # "MS:1000514"
+
+
+class MzDataArrayBits(Enum):
+    f64 = "MS:1000523"  # accession="MS:1000523" value="" name="64-bit float"
+
+
+class MzCompressionLib(Enum):
+    zlib = "MS:1000574"
+
+
+class MzSpectrumParam(Enum):
+    ms_level = "MS:1000511"
+    MSn_spectrum = "MS:1000580"
+    positive_scan = "MS:1000130"
+    total_ion_current = "MS:1000285"
+    centroid_spectrum = "MS:1000127"
+    base_peak_mz = "MS:1000504"
+    base_peak_intensity = "MS:1000505"
+    lowest_observed_mz = "MS:1000528"
+    highest_observed_mz = "MS:1000527"
+    scan_start_time = "MS:1000016"
+    uo_minute = "UO:0000031"
+    uo_millisecond = "UO:0000028"
+    ion_injection_time = "MS:1000927"
+    isolation_window_lower_offset = "MS:1000828"
+    isolation_window_upper_offset = "MS:1000829"
+    selected_ion_mz = "MS:1000744"
+    selected_ion_charge_state = "MS:1000041"
+    selected_ion_peak_intensity = "MS:1000042"
+    activation_collision_energy = "MS:1000045"
+    activation_beam_type_collision_induced_dissociation = "MS:1000422"

pymzcbor/harvestmzcbor.py

@@ -0,0 +1,110 @@
+# This file is part of pymzcbor.
+#
+# pymzcbor is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# pymzcbor is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with pymzcbor. If not, see <http://www.gnu.org/licenses/>.
+
+from collections.abc import Generator
+from typing import IO
+
+from pycborstream import CborStreamDec
+
+from .model.mzspectrum import MzSpectrum
+
+
+class HarvestMzCbor:
+    def __init__(self, fp: IO[bytes]):
+        self._cbor_stream_decoder = CborStreamDec(fp)
+        self._cbor_stream_decoder.enter_container()
+
+    def _goto_root_tag(self, tag_name: str):
+        # mzCBOR
+        # mzML
+        # cvList
+        # fileDescription
+        # referenceableParamGroupList
+        # softwareList
+        # instrumentConfigurationList
+        # dataProcessingList
+        # run
+        while self._cbor_stream_decoder.has_next():
+            cbor_value = self._cbor_stream_decoder.value()
+            if cbor_value == tag_name:
+                return
+            print(cbor_value)
+            self._cbor_stream_decoder.next()
+        raise ValueError(f"CBOR stream does not contain {tag_name}")
+
+    def yield_spectrums(self):
+        yield from self.yield_spectrums_if(lambda scan: True)
+
+    def yield_spectrums_if(self, condition_met) -> Generator[MzSpectrum, None, None]:
+        """mzCBOR spectrum harvester"""
+        self._goto_root_tag("run")
+        self._cbor_stream_decoder.enter_container()  # enter run
+        # id
+        # defaultInstrumentConfigurationRef
+        # startTimeStamp
+        # defaultSourceFileRef
+        # spectrumList
+        self._goto_root_tag("spectrumList")
+        self._cbor_stream_decoder.enter_container()  # enter spectrumList
+        # count
+        # defaultDataProcessingRef
+        self._goto_root_tag("spectrum")
+        self._cbor_stream_decoder.enter_container()  # enter spectrum array
+        while self._cbor_stream_decoder.has_next():
+            spectrum = MzSpectrum(self._cbor_stream_decoder.to_dict())
+            if condition_met(spectrum):
+                yield spectrum
+        self._cbor_stream_decoder.leave_container()
+        self._cbor_stream_decoder.leave_container()
+        self._cbor_stream_decoder.leave_container()
+
+    def yield_source_file(self):
+        # <sourceFileList count="1">
+        #   <sourceFile id="RAW1" name="20120906_balliau_extract_1_A01_urnb-1" location="file:///./20120906_balliau_extract_1_A01_urnb-1.raw">
+        #     <cvParam cvRef="MS" accession="MS:1000768" value="" name="Thermo nativeID format" />
+        #     <cvParam cvRef="MS" accession="MS:1000563" value="" name="Thermo RAW format" />
+        #     <cvParam cvRef="MS" accession="MS:1000569" value="69604cb2afac8225c016af24219e66a6845b4f81" name="SHA-1" />
+        #   </sourceFile>
+        #
+        self._cbor_stream_decoder.fp_seek(0)
+        self._cbor_stream_decoder.enter_container()
+        self._goto_root_tag("fileDescription")
+        self._cbor_stream_decoder.enter_container()
+        self._goto_root_tag("sourceFileList")
+        self._cbor_stream_decoder.enter_container()
+        self._goto_root_tag("sourceFile")
+        self._cbor_stream_decoder.enter_container()
+        while self._cbor_stream_decoder.has_next():
+            source_file = self._cbor_stream_decoder.to_dict()
+            yield source_file
+        self._cbor_stream_decoder.leave_container()
+        self._cbor_stream_decoder.leave_container()
+        self._cbor_stream_decoder.leave_container()
+
+    @property
+    def mz_informations(self) -> dict:
+        self._cbor_stream_decoder.fp_seek(0)
+        self._cbor_stream_decoder.enter_container()
+        self._goto_root_tag("mzCBOR")
+        self._cbor_stream_decoder.enter_container()
+        self._goto_root_tag("informations")
+        informations = self._cbor_stream_decoder.to_dict()
+        if informations is not None:
+            return informations
+        raise ValueError("mzCBOR informations not found")
+
+    def mz_spectrum(self, offset: int) -> MzSpectrum:
+        self._cbor_stream_decoder.fp_seek(offset)
+        return MzSpectrum(self._cbor_stream_decoder.to_dict())

pymzcbor/model/__init__.py

@@ -0,0 +1,5 @@
+from .mzcvparam import MzCvParam
+from .mzcvparamlist import MzCvParamList
+from .mzprecursor import MzPrecursor
+from .mzselectedion import MzSelectedIon
+from .mzspectrum import MzSpectrum