ENH: Adds find_peaks_xcms action

conda-recipe/meta.yaml

@@ -20,10 +20,12 @@ requirements:
     - versioningit
 
   run:
+    - bioconductor-xcms
     - pymzml
     - qiime2 {{ qiime2_epoch }}.*
     - q2-types {{ qiime2_epoch }}.*
     - q2templates {{ qiime2_epoch }}.*
+    - r-base
 
 test:
   requires:

q2_ms/assets/find_peaks_xcms.R

@@ -0,0 +1,55 @@
+#!/usr/bin/env Rscript
+
+library(xcms)
+library(MsExperiment)
+library(MsIO)
+
+
+update_params <- function(params, opt) {
+  for (key in names(params)) {
+    if (!is.null(opt[[key]])) {
+      params[[key]] <- opt[[key]]
+    }
+  }
+  return(params)
+}
+
+# Define command-line options
+option_list <- list(
+  make_option(opt_str = "--mzml_files", type = "character"),
+  make_option(opt_str = "--ppm", type = "numeric"),
+  make_option(opt_str = "--min_peakwidth", type = "numeric"),
+  make_option(opt_str = "--max_peakwidth", type = "numeric"),
+  make_option(opt_str = "--snthresh", type = "numeric"),
+  make_option(opt_str = "--prefilter_k", type = "numeric"),
+  make_option(opt_str = "--prefilter_i", type = "numeric"),
+  make_option(opt_str = "--mz_center_fun", type = "numeric"),
+  make_option(opt_str = "--integrate", type = "integer"),
+  make_option(opt_str = "--mzdiff", type = "numeric"),
+  make_option(opt_str = "--fitgauss", type = "logical"),
+  make_option(opt_str = "--noise", type = "numeric"),
+  make_option(opt_str = "--first_baseline_check", type = "logical"),
+  make_option(opt_str = "--ms_level", type = "integer"),
+  make_option(opt_str = "--threads", type = "integer"),
+  make_option(opt_str = "--output_path", type = "character")
+)
+
+# Parse arguments
+opt_parser <- OptionParser(option_list = option_list)
+opt <- parse_args(opt_parser)
+
+# Get full paths to mzML files and read them into an MsExperiment object
+mzml_files <- list.files(opt$mzml_files, pattern = "\\.mzML$", full.names = TRUE)
+msexperiment <- readMsExperiment(spectraFiles = mzml_files, sampleData = pd, BPPARAM = SerialParam())
+
+# Load default parameters for CentWave
+CentWaveParams <- CentWaveParam(method="centWave")
+
+# Update params with command-line arguments
+CentWaveParams <- update_params(CentWaveParams, opt)
+
+# Find peaks using the CentWave algorithm
+XCMSExperiment <- findChromPeaks(chr_raw, param = CentWaveParams)
+
+# Export the XCMSExperiment object to the directory format
+saveMsObject(XCMSExperiment, param = PlainTextParam(path = opt$output_path))

q2_ms/plugin_setup.py

@@ -10,6 +10,20 @@
 
 from q2_ms import __version__
 from q2_ms.types import mzML, mzMLDirFmt, mzMLFormat
+from q2_ms.types._format import (
+    MSBackendDataFormat,
+    MSExperimentLinkMColsFormat,
+    MSExperimentSampleDataFormat,
+    MSExperimentSampleDataLinksSpectra,
+    SpectraSlotsFormat,
+    XCMSExperimentChromPeakDataFormat,
+    XCMSExperimentChromPeaksFormat,
+    XCMSExperimentDirFmt,
+    XCMSExperimentFeatureDefinitionsFormat,
+    XCMSExperimentFeaturePeakIndexFormat,
+    XCMSExperimentJSONFormat,
+)
+from q2_ms.types._type import XCMSExperiment
 
 citations = Citations.load("citations.bib", package="q2_ms")
 
@@ -25,11 +39,26 @@
 # Registrations
 plugin.register_semantic_types(
     mzML,
+    XCMSExperiment,
 )
 
 plugin.register_semantic_type_to_format(SampleData[mzML], artifact_format=mzMLDirFmt)
+plugin.register_semantic_type_to_format(
+    XCMSExperiment, artifact_format=XCMSExperimentDirFmt
+)
 
 plugin.register_formats(
     mzMLFormat,
     mzMLDirFmt,
+    MSBackendDataFormat,
+    MSExperimentLinkMColsFormat,
+    MSExperimentSampleDataFormat,
+    MSExperimentSampleDataLinksSpectra,
+    SpectraSlotsFormat,
+    XCMSExperimentChromPeakDataFormat,
+    XCMSExperimentChromPeaksFormat,
+    XCMSExperimentDirFmt,
+    XCMSExperimentFeatureDefinitionsFormat,
+    XCMSExperimentFeaturePeakIndexFormat,
+    XCMSExperimentJSONFormat,
 )

q2_ms/tests/__init__.py

@@ -0,0 +1,7 @@
+# ----------------------------------------------------------------------------
+# Copyright (c) 2024, QIIME 2 development team.
+#
+# Distributed under the terms of the Modified BSD License.
+#
+# The full license is in the file LICENSE, distributed with this software.
+# ----------------------------------------------------------------------------

q2_ms/tests/tests_utils.py

@@ -0,0 +1,47 @@
+from unittest.mock import call, patch
+
+from qiime2.plugin.testing import TestPluginBase
+
+from q2_ms.utils import EXTERNAL_CMD_WARNING, run_command
+
+
+class TestRunCommand(TestPluginBase):
+    package = "q2_ms.tests"
+
+    @patch("subprocess.run")
+    @patch("builtins.print")
+    def test_run_command_verbose(self, mock_print, mock_subprocess_run):
+        # Mock command and working directory
+        cmd = ["echo", "Hello"]
+        cwd = "/test/directory"
+
+        # Run the function with verbose=True
+        run_command(cmd, cwd=cwd, verbose=True)
+
+        # Check if subprocess.run was called with the correct arguments
+        mock_subprocess_run.assert_called_once_with(cmd, check=True, cwd=cwd)
+
+        # Check if the correct print statements were called
+        mock_print.assert_has_calls(
+            [
+                call(EXTERNAL_CMD_WARNING),
+                call("\nCommand:", end=" "),
+                call("echo Hello", end="\n\n"),
+            ]
+        )
+
+    @patch("subprocess.run")
+    @patch("builtins.print")
+    def test_run_command_non_verbose(self, mock_print, mock_subprocess_run):
+        # Mock command and working directory
+        cmd = ["echo", "Hello"]
+        cwd = "/test/directory"
+
+        # Run the function with verbose=False
+        run_command(cmd, cwd=cwd, verbose=False)
+
+        # Check if subprocess.run was called with the correct arguments
+        mock_subprocess_run.assert_called_once_with(cmd, check=True, cwd=cwd)
+
+        # Ensure no print statements were made
+        mock_print.assert_not_called()

q2_ms/types/__init__.py

@@ -5,7 +5,37 @@
 #
 # The full license is in the file LICENSE, distributed with this software.
 # ----------------------------------------------------------------------------
-from q2_ms.types._format import mzMLDirFmt, mzMLFormat
-from q2_ms.types._type import mzML
+from q2_ms.types._format import (
+    MSBackendDataFormat,
+    MSExperimentLinkMColsFormat,
+    MSExperimentSampleDataFormat,
+    MSExperimentSampleDataLinksSpectra,
+    SpectraSlotsFormat,
+    XCMSExperimentChromPeakDataFormat,
+    XCMSExperimentChromPeaksFormat,
+    XCMSExperimentDirFmt,
+    XCMSExperimentFeatureDefinitionsFormat,
+    XCMSExperimentFeaturePeakIndexFormat,
+    XCMSExperimentJSONFormat,
+    mzMLDirFmt,
+    mzMLFormat,
+)
+from q2_ms.types._type import XCMSExperiment, mzML
 
-__all__ = ["mzMLFormat", "mzMLDirFmt", "mzML"]
+__all__ = [
+    "mzMLFormat",
+    "mzMLDirFmt",
+    "mzML",
+    "MSBackendDataFormat",
+    "MSExperimentLinkMColsFormat",
+    "MSExperimentSampleDataFormat",
+    "MSExperimentSampleDataLinksSpectra",
+    "SpectraSlotsFormat",
+    "XCMSExperimentChromPeakDataFormat",
+    "XCMSExperimentChromPeaksFormat",
+    "XCMSExperimentDirFmt",
+    "XCMSExperimentFeatureDefinitionsFormat",
+    "XCMSExperimentFeaturePeakIndexFormat",
+    "XCMSExperimentJSONFormat",
+    "XCMSExperiment",
+]