ENH: automatic addition of MS2 property to output of read-ms-experiment

q2_ms/plugin_setup.py

@@ -64,7 +64,7 @@
     citations=[],
 )
 
-plugin.methods.register_function(
+plugin.pipelines.register_function(
     function=read_ms_experiment,
     inputs={"spectra": SampleData[mzML]},
     outputs=[("xcms_experiment", XCMSExperiment)],

q2_ms/xcms/read_ms_experiment.py

@@ -5,28 +5,23 @@
 #
 # The full license is in the file LICENSE, distributed with this software.
 # ----------------------------------------------------------------------------
-import copy
 import os
 import tempfile
 
-from qiime2 import Metadata
+import pandas as pd
 
 from q2_ms.types import XCMSExperimentDirFmt, mzMLDirFmt
 from q2_ms.utils import run_r_script
 
 
 def read_ms_experiment(
-    spectra: mzMLDirFmt,
-    sample_metadata: Metadata = None,
-) -> XCMSExperimentDirFmt:
-    # Create parameters dict
-    params = copy.copy(locals())
-
-    # Init XCMSExperimentDirFmt
-    xcms_experiment = XCMSExperimentDirFmt()
-
-    # Add output path to params
-    params["output_path"] = str(xcms_experiment)
+    ctx,
+    spectra,
+    sample_metadata=None,
+):
+    xcms_experiment_dir_fmt = XCMSExperimentDirFmt()
+    spectra = spectra.view(mzMLDirFmt)
+    params = {"spectra": str(spectra), "output_path": str(xcms_experiment_dir_fmt)}
 
     with tempfile.TemporaryDirectory() as tmp_dir:
         if sample_metadata is not None:
@@ -42,9 +37,37 @@ def read_ms_experiment(
         # Run R script
         run_r_script("read_ms_experiment", params, "XCMS")
 
+    # Create artifact with correct type
+    xcms_experiment = ctx.make_artifact(
+        _get_type(str(xcms_experiment_dir_fmt)), xcms_experiment_dir_fmt
+    )
+
     return xcms_experiment
 
 
+def _get_type(directory: str) -> str:
+    """
+    Determines the semantic type of an XCMSExperiment based on MS level data.
+
+    Parameters:
+        directory (str): Path to the XCMSExperiment directory.
+
+    Returns:
+        str: The semantic type, either 'XCMSExperiment' or
+             'XCMSExperiment % Properties("MS2")'.
+    """
+    df = pd.read_csv(
+        os.path.join(directory, "ms_backend_data.txt"),
+        sep="\t",
+        usecols=["msLevel"],
+        skiprows=1,
+        index_col=0,
+    )
+    if (df["msLevel"] == 2).any():
+        return 'XCMSExperiment % Properties("MS2")'
+    return "XCMSExperiment"
+
+
 def _validate_metadata(metadata, spectra_path):
     """
     Validates that sample IDs in the metadata match the filenames in the spectra

q2_ms/xcms/tests/data/get_type/ms1/ms_backend_data.txt

@@ -0,0 +1,4 @@
+# MsBackendMzR
+"msLevel"	"rtime"	"acquisitionNum"
+"1"	1	2501.378	1
+"2"	1	2502.943	2

q2_ms/xcms/tests/data/get_type/ms2/ms_backend_data.txt

@@ -0,0 +1,4 @@
+# MsBackendMzR
+"msLevel"	"rtime"	"acquisitionNum"
+"1"	1	2501.378	1
+"2"	2	2502.943	2

q2_ms/xcms/tests/data/ms2_spectra/ms2_simulated.mzML

@@ -0,0 +1,82 @@
+<?xml version="1.0" encoding="ISO-8859-1"?>
+<indexedmzML xmlns="http://psi.hupo.org/ms/mzml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://psi.hupo.org/ms/mzml http://psidev.info/files/ms/mzML/xsd/mzML1.1.0_idx.xsd">
+<mzML xmlns="http://psi.hupo.org/ms/mzml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://psi.hupo.org/ms/mzml http://psidev.info/files/ms/mzML/xsd/mzML1.1.0.xsd" accession="" version="1.1.0">
+	<cvList count="5">
+		<cv id="MS" fullName="Proteomics Standards Initiative Mass Spectrometry Ontology" URI="http://psidev.cvs.sourceforge.net/*checkout*/psidev/psi/psi-ms/mzML/controlledVocabulary/psi-ms.obo"/>
+		<cv id="UO" fullName="Unit Ontology" URI="http://obo.cvs.sourceforge.net/obo/obo/ontology/phenotype/unit.obo"/>
+		<cv id="BTO" fullName="BrendaTissue545" version="unknown" URI="http://www.brenda-enzymes.info/ontology/tissue/tree/update/update_files/BrendaTissueOBO"/>
+		<cv id="GO" fullName="Gene Ontology - Slim Versions" version="unknown" URI="http://www.geneontology.org/GO_slims/goslim_goa.obo"/>
+		<cv id="PATO" fullName="Quality ontology" version="unknown" URI="http://obo.cvs.sourceforge.net/*checkout*/obo/obo/ontology/phenotype/quality.obo"/>
+	</cvList>
+	<fileDescription>
+		<fileContent>
+			<cvParam cvRef="MS" accession="MS:1000294" name="mass spectrum" />
+		</fileContent>
+	</fileDescription>
+	<sampleList count="1">
+		<sample id="sa_0" name="">
+			<cvParam cvRef="MS" accession="MS:1000004" name="sample mass" value="0" unitAccession="UO:0000021" unitName="gram" unitCvRef="UO" />
+			<cvParam cvRef="MS" accession="MS:1000005" name="sample volume" value="0" unitAccession="UO:0000098" unitName="milliliter" unitCvRef="UO" />
+			<cvParam cvRef="MS" accession="MS:1000006" name="sample concentration" value="0" unitAccession="UO:0000175" unitName="gram per liter" unitCvRef="UO" />
+		</sample>
+	</sampleList>
+	<softwareList count="2">
+		<software id="so_in_0" version="" >
+			<cvParam cvRef="MS" accession="MS:1000799" name="custom unreleased software tool" value="" />
+		</software>
+		<software id="so_default" version="" >
+			<cvParam cvRef="MS" accession="MS:1000799" name="custom unreleased software tool" value="" />
+		</software>
+	</softwareList>
+	<instrumentConfigurationList count="1">
+		<instrumentConfiguration id="ic_0">
+			<cvParam cvRef="MS" accession="MS:1000031" name="instrument model" />
+			<softwareRef ref="so_in_0" />
+		</instrumentConfiguration>
+	</instrumentConfigurationList>
+	<dataProcessingList count="1">
+		<dataProcessing id="dp_sp_0">
+			<processingMethod order="0" softwareRef="so_default">
+				<cvParam cvRef="MS" accession="MS:1000544" name="Conversion to mzML" />
+				<userParam name="warning" type="xsd:string" value="fictional processing method used to fulfill format requirements" />
+			</processingMethod>
+		</dataProcessing>
+	</dataProcessingList>
+	<run id="ru_0" defaultInstrumentConfigurationRef="ic_0" sampleRef="sa_0">
+		<spectrumList count="1" defaultDataProcessingRef="dp_sp_0">
+			<spectrum id="spectrum=0" index="0" defaultArrayLength="3" dataProcessingRef="dp_sp_0">
+				<cvParam cvRef="MS" accession="MS:1000525" name="spectrum representation" />
+				<cvParam cvRef="MS" accession="MS:1000511" name="ms level" value="2" />
+				<cvParam cvRef="MS" accession="MS:1000294" name="mass spectrum" />
+				<scanList count="1">
+					<cvParam cvRef="MS" accession="MS:1000795" name="no combination" />
+					<scan>
+						<cvParam cvRef="MS" accession="MS:1000016" name="scan start time" value="-1" unitAccession="UO:0000010" unitName="second" unitCvRef="UO" />
+					</scan>
+				</scanList>
+				<binaryDataArrayList count="2">
+					<binaryDataArray encodedLength="32">
+						<cvParam cvRef="MS" accession="MS:1000514" name="m/z array" unitAccession="MS:1000040" unitName="m/z" unitCvRef="MS" />
+						<cvParam cvRef="MS" accession="MS:1000523" name="64-bit float" />
+						<cvParam cvRef="MS" accession="MS:1000576" name="no compression" />
+						<binary>AAAAAAAAWUAAAAAAAMBiQAAAAAAAAGlA</binary>
+					</binaryDataArray>
+					<binaryDataArray encodedLength="16">
+						<cvParam cvRef="MS" accession="MS:1000515" name="intensity array" unitAccession="MS:1000131" unitName="number of detector counts" unitCvRef="MS"/>
+						<cvParam cvRef="MS" accession="MS:1000521" name="32-bit float" />
+						<cvParam cvRef="MS" accession="MS:1000576" name="no compression" />
+						<binary>AAD6QwAAekQAAEhE</binary>
+					</binaryDataArray>
+				</binaryDataArrayList>
+			</spectrum>
+		</spectrumList>
+	</run>
+</mzML>
+<indexList count="1">
+	<index name="spectrum">
+		<offset idRef="spectrum=0">3028</offset>
+	</index>
+</indexList>
+<indexListOffset>4539</indexListOffset>
+<fileChecksum>0</fileChecksum>
+</indexedmzML>

q2_ms/xcms/tests/test_read_ms_experiment.py

@@ -9,50 +9,54 @@
 
 import pandas as pd
 import qiime2
+from qiime2 import Artifact
 from qiime2.plugin.testing import TestPluginBase
+from qiime2.sdk import parse_type
 
-from q2_ms.types import mzMLDirFmt
-from q2_ms.xcms.read_ms_experiment import _validate_metadata, read_ms_experiment
+from q2_ms.types import XCMSExperimentDirFmt, mzMLDirFmt
+from q2_ms.xcms.read_ms_experiment import _get_type, _validate_metadata
 
 
 class TestReadMsExperiment(TestPluginBase):
     package = "q2_ms.xcms.tests"
 
     def setUp(self):
         super().setUp()
-        self.sample_metadata = pd.read_csv(
-            self.get_data_path("faahKO_sample_data/sample_metadata.tsv"),
-            sep="\t",
-            index_col=0,
+        self.sample_metadata = qiime2.Metadata.load(
+            self.get_data_path("faahKO_sample_data/sample_metadata.tsv")
+        )
+        self.spectra_dir = mzMLDirFmt(self.get_data_path("faahKO"), mode="r")
+        self.spectra = Artifact.import_data("SampleData[mzML]", self.spectra_dir)
+        self.spectra_ms2_dir = mzMLDirFmt(self.get_data_path("ms2_spectra"), mode="r")
+        self.spectra_ms2 = Artifact.import_data(
+            "SampleData[mzML]", self.spectra_ms2_dir
         )
-        self.spectra = mzMLDirFmt(self.get_data_path("faahKO"), mode="r")
+        self.read_ms_experiment = self.plugin.pipelines["read_ms_experiment"]
 
     def test_read_ms_experiment_metadata(self):
-        xcms_experiment = read_ms_experiment(
-            spectra=self.spectra,
-            sample_metadata=qiime2.Metadata(self.sample_metadata),
+        (xcms_experiment,) = self.read_ms_experiment(
+            spectra=self.spectra, sample_metadata=self.sample_metadata
         )
-        sample_data_exp = pd.read_csv(
-            self.get_data_path(
-                "ms_experiment_sample_data/ms_experiment_sample_data_metadata.txt"
-            ),
-            sep="\t",
-            index_col=0,
+        self._test_read_ms_experiment_helper(
+            xcms_experiment, "ms_experiment_sample_data_metadata.txt"
         )
-        sample_data_obs = pd.read_csv(
-            os.path.join(str(xcms_experiment), "ms_experiment_sample_data.txt"),
-            sep="\t",
-            index_col=0,
+
+    def test_read_ms_experiment_no_metadata(self):
+        (xcms_experiment,) = self.read_ms_experiment(
+            spectra=self.spectra,
+        )
+        self._test_read_ms_experiment_helper(
+            xcms_experiment, "ms_experiment_sample_data_default.txt"
         )
-        sample_data_obs.drop(columns=["spectraOrigin"], inplace=True)
 
-        pd.testing.assert_frame_equal(sample_data_exp, sample_data_obs)
+    def _test_read_ms_experiment_helper(self, xcms_experiment, exp_sample_data):
+        self.assertEqual(xcms_experiment.type, parse_type("XCMSExperiment"))
+
+        xcms_experiment = xcms_experiment.view(XCMSExperimentDirFmt)
 
-    def test_read_ms_experiment_without_metadata(self):
-        xcms_experiment = read_ms_experiment(spectra=self.spectra)
         sample_data_exp = pd.read_csv(
             self.get_data_path(
-                "ms_experiment_sample_data/ms_experiment_sample_data_default.txt"
+                os.path.join("ms_experiment_sample_data", exp_sample_data)
             ),
             sep="\t",
             index_col=0,
@@ -66,13 +70,27 @@ def test_read_ms_experiment_without_metadata(self):
 
         pd.testing.assert_frame_equal(sample_data_exp, sample_data_obs)
 
+    def test_read_ms_experiment_ms2(self):
+        (xcms_experiment,) = self.read_ms_experiment(spectra=self.spectra_ms2)
+        self.assertEqual(
+            xcms_experiment.type, parse_type("XCMSExperiment % Properties('MS2')")
+        )
+
     def test_validate_metadata_missing(self):
-        metadata_missing = self.sample_metadata.drop(index="wt22")
+        metadata_missing = self.sample_metadata.to_dataframe().drop(index="wt22")
         with self.assertRaisesRegex(ValueError, "missing in sample-metadata: {'wt22'}"):
-            _validate_metadata(metadata_missing, str(self.spectra))
+            _validate_metadata(metadata_missing, str(self.spectra_dir))
 
     def test_read_ms_experiment_added(self):
-        metadata_added = self.sample_metadata.copy()
+        metadata_added = self.sample_metadata.to_dataframe().copy()
         metadata_added.loc["wt23"] = ["WT", "study"]
         with self.assertRaisesRegex(ValueError, "missing in spectra: {'wt23'}"):
-            _validate_metadata(metadata_added, str(self.spectra))
+            _validate_metadata(metadata_added, str(self.spectra_dir))
+
+    def test_get_type_ms2(self):
+        type = _get_type(self.get_data_path("get_type/ms2"))
+        self.assertEqual(type, 'XCMSExperiment % Properties("MS2")')
+
+    def test_get_type_ms1(self):
+        type = _get_type(self.get_data_path("get_type/ms1"))
+        self.assertEqual(type, "XCMSExperiment")