Merge pull request #340 from pymzml/dev

Release

.github/workflows/tox_ci.yml

@@ -7,7 +7,7 @@ jobs:
   black:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Run black
         uses: actions/setup-python@v4
         with:
@@ -23,7 +23,7 @@ jobs:
       matrix:
         python: ['3.8', '3.9', '3.10']
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Setup Python
         uses: actions/setup-python@v4
         with:

.readthedocs.yml

@@ -1,2 +1,35 @@
+# Read the Docs configuration file for Sphinx projects
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.11"
+    # You can also specify other tool versions:
+    # nodejs: "20"
+    # rust: "1.70"
+    # golang: "1.20"
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+  configuration: docs/source/conf.py
+  # You can configure Sphinx to use a different builder, for instance use the dirhtml builder for simpler URLs
+  # builder: "dirhtml"
+  # Fail on all warnings to avoid broken references
+  # fail_on_warning: true
+
+# Optionally build your docs in additional formats such as PDF and ePub
+# formats:
+#    - pdf
+#    - epub
+
+# Optional but recommended, declare the Python requirements required
+# to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
 python:
-    version: 3
+   install:
+   - requirements: docs/requirements.txt

docs/requirements.txt

@@ -1,3 +1,3 @@
-sphinx==6.1.3
+sphinx==7.2.5
 sphinx_rtd_theme==0.5.0
 regex

pymzml/obo.py

@@ -96,6 +96,8 @@ class OboTranslator(object):
         version (str): obo version
     """
 
+    _obo_instance_cache = {}
+
     def __init__(self, version=None):
         self.version = self.__normalize_version(version)
         self.all_dicts = []
@@ -108,6 +110,15 @@ def __init__(self, version=None):
         # Only parse the OBO when necessary, not upon object construction
         self.__obo_parsed = False
 
+    @classmethod
+    def from_cache(cls, version):
+        version = cls.__normalize_version(version)
+        try:
+            return cls._obo_instance_cache[version]
+        except KeyError:
+            inst = cls._obo_instance_cache[version] = cls(version)
+            return inst
+
     def __setitem__(self, key, value):
         raise TypeError("OBO translator dictionaries only support assignment via .add")
 

pymzml/run.py

@@ -155,24 +155,22 @@ def __next__(self):
             event, element = next(self.iter, ("END", "END"))
             if event == "end":
                 if element.tag.endswith("}spectrum"):
-                    spectrum = spec.Spectrum(element)
+                    spectrum = spec.Spectrum(element, obo_version=self.OT.version)
                     if has_ref_group:
                         spectrum._set_params_from_reference_group(
                             self.info["referenceable_param_group_list_element"]
                         )
                     ms_level = spectrum.ms_level
                     spectrum.measured_precision = self.ms_precisions[ms_level]
-                    spectrum.calling_instance = self
                     return spectrum
                 if element.tag.endswith("}chromatogram"):
                     if self.skip_chromatogram:
                         continue
-                    spectrum = spec.Chromatogram(element)
+                    spectrum = spec.Chromatogram(element, obo_version=self.OT.version)
                     # if has_ref_group:
                     #     spectrum._set_params_from_reference_group(
                     #         self.info['referenceable_param_group_list_element']
                     #     )
-                    spectrum.calling_instance = self
                     return spectrum
             elif event == "END":
                 # reinit iter
@@ -201,7 +199,7 @@ def __getitem__(self, identifier):
         except:
             pass
         spectrum = self.info["file_object"][identifier]
-        spectrum.calling_instance = self
+        spectrum.obo_translator = self.OT
         if isinstance(spectrum, spec.Spectrum):
             spectrum.measured_precision = self.ms_precisions[spectrum.ms_level]
         return spectrum
@@ -273,7 +271,6 @@ def _determine_file_encoding(self, path):
 
     @staticmethod
     def _obo_version_validator(version):
-
         """
         The obo version should fit file names in the obo folder.
         However, some software generate mzML with built in obo version string like:
@@ -347,7 +344,7 @@ def _init_obo_translator(self):
         # required) ...
         if self.info.get("obo_version", None) is None:
             self.info["obo_version"] = "1.1.0"
-        obo_translator = obo.OboTranslator(version=self.info["obo_version"])
+        obo_translator = obo.OboTranslator.from_cache(version=self.info["obo_version"])
 
         return obo_translator
 
@@ -386,9 +383,27 @@ def _init_iter(self):
                     obo_in_mzml = element.attrib.get("version", "1.1.0")
                     self.info["obo_version"] = self._obo_version_validator(obo_in_mzml)
 
+            elif element.tag.endswith("}fileDescription"):
+                self.info["file_description"] = True
+                self.info["file_description_element"] = element
+            elif element.tag.endswith("}sampleList"):
+                self.info["sample_list"] = True
+                self.info["sample_list_element"] = element
+
             elif element.tag.endswith("}referenceableParamGroupList"):
                 self.info["referenceable_param_group_list"] = True
                 self.info["referenceable_param_group_list_element"] = element
+
+            elif element.tag.endswith("}softwareList"):
+                self.info["software_list"] = True
+                self.info["software_list_element"] = element
+            elif element.tag.endswith("}instrumentConfigurationList"):
+                self.info["instrument_configuration_list"] = True
+                self.info["instrument_configuration_list_element"] = element
+            elif element.tag.endswith("}dataProcessingList"):
+                self.info["data_processing_list"] = True
+                self.info["data_processing_list_element"] = element
+
             elif element.tag.endswith("}spectrumList"):
                 spec_cnt = element.attrib.get("count")
                 self.info["spectrum_count"] = int(spec_cnt) if spec_cnt else None
@@ -401,6 +416,7 @@ def _init_iter(self):
             elif element.tag.endswith("}run"):
                 run_id = element.attrib.get("id")
                 start_time = element.attrib.get("startTimeStamp")
+                self.info["run_element"] = element
                 self.info["run_id"] = run_id
                 self.info["start_time"] = start_time
             else:

pymzml/spec.py

@@ -64,6 +64,7 @@
     pass
 from . import regex_patterns
 from .decoder import MSDecoder
+from .obo import OboTranslator
 
 PROTON = 1.00727646677
 ISOTOPE_AVERAGE_DIFFERENCE = 1.002
@@ -74,22 +75,6 @@ class MS_Spectrum(object):
     General spectrum class for data handling.
     """
 
-    # __slots__ = [
-    #     # '_read_accessions',
-    #     # 'get_element_by_name',
-    #     # 'get_element_by_path',
-    #     # '_register',
-    #     # 'precursors',
-    #     # '_get_encoding_parameters',
-    #     # 'measured_precision',
-    #     # '_decode_to_numpy',
-    #     # '_median',
-    #     # 'to_string',
-    # ]
-    def __init__(self):
-        """."""
-        pass
-
     def _read_accessions(self):
         """Set all required variables for this spectrum."""
         self.accessions = {}
@@ -175,8 +160,6 @@ def _get_encoding_parameters(self, array_type):
         """
         numpress_encoding = False
 
-        # array_type_accession = self.calling_instance.OT[array_type]["id"]
-
         b_data_string = "./{ns}binaryDataArrayList/{ns}binaryDataArray/{ns}cvParam[@name='{name}']/..".format(
             ns=self.ns, name=array_type
         )
@@ -204,7 +187,7 @@ def _get_encoding_parameters(self, array_type):
                     d_type = b_data_array.find(
                         float_type_string.format(
                             ns=self.ns,
-                            Acc=self.calling_instance.OT["32-bit float"]["id"],
+                            Acc=self.obo_translator["32-bit float"]["id"],
                         )
                     ).get("name")
                 except:
@@ -213,7 +196,7 @@ def _get_encoding_parameters(self, array_type):
                         d_type = b_data_array.find(
                             float_type_string.format(
                                 ns=self.ns,
-                                Acc=self.calling_instance.OT["64-bit float"]["id"],
+                                Acc=self.obo_translator["64-bit float"]["id"],
                             )
                         ).get("name")
                     except:
@@ -222,9 +205,7 @@ def _get_encoding_parameters(self, array_type):
                             d_type = b_data_array.find(
                                 float_type_string.format(
                                     ns=self.ns,
-                                    Acc=self.calling_instance.OT["32-bit integer"][
-                                        "id"
-                                    ],
+                                    Acc=self.obo_translator["32-bit integer"]["id"],
                                 )
                             ).get("name")
                         except:
@@ -233,17 +214,15 @@ def _get_encoding_parameters(self, array_type):
                                 d_type = b_data_array.find(
                                     float_type_string.format(
                                         ns=self.ns,
-                                        Acc=self.calling_instance.OT["64-bit integer"][
-                                            "id"
-                                        ],
+                                        Acc=self.obo_translator["64-bit integer"]["id"],
                                     )
                                 ).get("name")
                             except:
                                 # null-terminated ASCII string
                                 d_type = b_data_array.find(
                                     float_type_string.format(
                                         ns=self.ns,
-                                        Acc=self.calling_instance.OT[
+                                        Acc=self.obo_translator[
                                             "null-terminated ASCII string"
                                         ]["id"],
                                     )
@@ -302,7 +281,6 @@ def _decode_to_numpy(self, data, d_array_length, data_type, comp):
                 or "MS-Numpress linear prediction compression" in comp
                 or "MS-Numpress short logged float compression" in comp
             ):
-
                 out_data = self._decodeNumpress_to_array(out_data, comp)
             if data_type == "32-bit float":
                 # one character code may be sufficient too (f)
@@ -426,8 +404,13 @@ class Spectrum(MS_Spectrum):
 
     """
 
-    def __init__(self, element=ElementTree.Element(""), measured_precision=5e-6):
-
+    def __init__(
+        self,
+        element=ElementTree.Element(""),
+        measured_precision=5e-6,
+        *,
+        obo_version=None,
+    ):
         __slots__ = [
             "_centroided_peaks",
             "_centroided_peaks_sorted_by_i",
@@ -480,7 +463,7 @@ def __init__(self, element=ElementTree.Element(""), measured_precision=5e-6):
         self._transformed_mass_with_error = None
         self._transformed_mz_with_error = None
         self._transformed_peaks = None
-        self.calling_instance = None
+        self.obo_translator = OboTranslator.from_cache(obo_version)
         self.element = element
         self.measured_precision = measured_precision
         self.noise_level_estimate = {}
@@ -662,7 +645,7 @@ def __getitem__(self, accession):
         else:
             if not accession.startswith("MS:"):
                 try:
-                    accession = self.calling_instance.OT[accession]["id"]
+                    accession = self.obo_translator[accession]["id"]
                 except TypeError:
                     accession = "---"
             search_string = './/*[@accession="{0}"]'.format(accession)
@@ -1003,6 +986,7 @@ def selected_precursors(self):
                     ("i", i_values),
                     ("charge", charges),
                     ("precursor id", ids),
+                    ("element", precursors),
                 ]:
                     try:
                         dict_2_save[key] = list_of_values[pos]
@@ -1246,11 +1230,9 @@ def _centroid_peaks(self):
         """
 
         try:
-            profile_ot = self.calling_instance.OT.name.get("profile spectrum", None)
+            profile_ot = self.obo_translator.name.get("profile spectrum", None)
             if profile_ot is None:
-                profile_ot = self.calling_instance.OT.name.get(
-                    "profile mass spectrum", None
-                )
+                profile_ot = self.obo_translator.name.get("profile mass spectrum", None)
             acc = profile_ot["id"]
             is_profile = (
                 True
@@ -1332,17 +1314,6 @@ def _reprofile_Peaks(self):
         self.set_peaks(None, "centroided")
         return tmp
 
-    def _register(self, decoded_tuple):
-        d_type, array = decoded_tuple
-        if d_type == "mz":
-            self._mz = array
-        elif d_type == "i":
-            self._i = array
-        elif d_type == "time":
-            self._time = array
-        else:
-            raise Exception("Unknown data Type ({0})".format(d_type))
-
     def _mz_2_mass(self, mz, charge):
         """
         Calculate the uncharged mass for a given mz value
@@ -1766,7 +1737,7 @@ class Chromatogram(MS_Spectrum):
     Class for Chromatogram access and handling.
     """
 
-    def __init__(self, element, measured_precision=5e-6, param=None):
+    def __init__(self, element, measured_precision=5e-6, *, obo_version=None):
         """
         Arguments:
             element (xml.etree.ElementTree.Element): spectrum as xml Element
@@ -1775,29 +1746,6 @@ def __init__(self, element, measured_precision=5e-6, param=None):
             measured_precision (float): in ppm, i.e. 5e-6 equals to 5 ppm.
             param (dict): parameter mapping for this spectrum
         """
-
-        __slots__ = [
-            "_measured_precision",
-            "element",
-            "noise_level_estimate",
-            "_time",
-            "_i",
-            "_t_mass_set",
-            "_peaks",
-            "_t_mz_set",
-            "_centroided_peaks",
-            "_reprofiled_peaks",
-            "_deconvoluted_peaks",
-            "_profile",
-            "_extreme_values",
-            "_centroided_peaks_sorted_by_i",
-            "_transformed_mz_with_error",
-            "_transformed_mass_with_error",
-            "_precursors",
-            "_ID",
-            "internal_precision",
-        ]
-
         self._measured_precision = measured_precision
         self.element = element
         self.noise_level_estimate = {}
@@ -1818,6 +1766,7 @@ def __init__(self, element, measured_precision=5e-6, param=None):
         self._transformed_mass_with_error = None
         self._precursors = None
         self._ID = None
+        self.obo_translator = OboTranslator.from_cache(obo_version)
 
         if self.element:
             # self._read_accessions()

pymzml/version.txt

@@ -1 +1 @@
-2.5.2
+2.5.3