Merge branch 'corems2' into 'lipid_dev'

Update GC/MS workflow to be CoreMS 3.0 and MetabRef API compatible

See merge request mass-spectrometry/metams!10

.github/workflows/wdl_checker.yml

@@ -40,4 +40,3 @@ jobs:
       run: |
         # Add the commands to run your MiniWDL workflow
         miniwdl run wdl/metaMS_gcms.wdl -i wdl/metams_input_gcms.json --verbose --no-cache --copy-input-files
-  

Dockerfile

@@ -1,7 +1,7 @@
+# Python base image
 FROM python:3.11.1-bullseye
 
 # Mono: 6.12
-
 RUN apt-key adv --keyserver hkp://keyserver.ubuntu.com:80 --recv-keys 3FA7E0328081BFF6A14DA29AA6A19B38D3D831EF \
   && echo "deb http://download.mono-project.com/repo/debian buster/snapshots/6.12 main" > /etc/apt/sources.list.d/mono-official.list \
   && apt-get update \
@@ -12,17 +12,14 @@ RUN apt-key adv --keyserver hkp://keyserver.ubuntu.com:80 --recv-keys 3FA7E03280
 
 # Pythonnet: 3.0.1 (from PyPI)
 # Note: pycparser must be installed before pythonnet can be built
-
 RUN pip install pycparser \
   && pip install pythonnet==3.0.1
 
+# Copy MetaMS contents
 WORKDIR /metams
-
 COPY metaMS/ /metams/metaMS/
 COPY README.md disclaimer.txt Makefile requirements.txt setup.py /metams/
 COPY db/ /metams/db/
 
 # Install the MetaMS package in editable mode
 RUN pip3 install --editable .
-
-

configuration/gcms_corems.toml

@@ -1,12 +1,25 @@
 [MolecularSearch]
-url_database = "sqlite:////metams/db/pnnl_lowres_gcms_compounds.sqlite"
-ri_search_range = 35
+ri_search_range = 35.0
 rt_search_range = 1.0
 correlation_threshold = 0.5
 score_threshold = 0.0
 ri_spacing = 200.0
 ri_std = 3.0
-ri_calibration_compound_names = [ " [C8] Methyl Caprylate [7.812]", " [C10] Methyl Caprate [10.647]", " [C9] Methyl Pelargonate [9.248]", " [C12] Methyl Laurate [13.250]", " [C14] Methyl Myristate [15.597]", " [C16] Methyl Palmitate [17.723]", " [C18] Methyl Stearate [19.663]", " [C20] Methyl Eicosanoate [21.441]", " [C22] Methyl Docosanoate [23.082]", " [C24] Methyl Linocerate [24.603]", " [C26] Methyl Hexacosanoate [26.023]", " [C28] Methyl Octacosanoate [27.349]", " [C30] Methyl Triacontanoate [28.72]",]
+ri_calibration_compound_names = [
+    "Methyl Caprylate",
+    "Methyl Caprate",
+    "Methyl Pelargonate",
+    "Methyl Laurate",
+    "Methyl Myristate", 
+    "Methyl Palmitate", 
+    "Methyl Stearate", 
+    "Methyl Eicosanoate", 
+    "Methyl Docosanoate", 
+    "Methyl Linocerate", 
+    "Methyl Hexacosanoate", 
+    "Methyl Octacosanoate", 
+    "Methyl Triacontanoate",
+]
 exploratory_mode = false
 score_methods = [ "highest_sim_score", "highest_ss",]
 output_score_method = "All"
@@ -17,12 +30,13 @@ implemented_smooth_method = [ "savgol", "hanning", "blackman", "bartlett", "flat
 smooth_window = 5
 smooth_method = "savgol"
 savgol_pol_order = 2
+peak_derivative_threshold = 0.0005
 peak_height_max_percent = 10.0
 peak_max_prominence_percent = 1.0
 min_peak_datapoints = 5.0
 max_peak_width = 0.1
 noise_threshold_method = "manual_relative_abundance"
-implemented_noise_threshold_methods = [ "auto_relative_abundance", "manual_relative_abundance", "second_derivative",]
+noise_threshold_methods_implemented = [ "auto_relative_abundance", "manual_relative_abundance", "second_derivative",]
 std_noise_threshold = 3
 peak_height_min_percent = 0.1
 peak_min_prominence_percent = 0.1

configuration/gcms_metams.toml

@@ -1,7 +1,8 @@
 file_paths = [  "data/raw_data/GCMS_FAMES_01_GCMS-01_20191023.cdf", "data/raw_data/GCMS_FAMES_01_GCMS-01_20191023.cdf"]
 calibration_file_path = "data/raw_data/GCMS_FAMES_01_GCMS-01_20191023.cdf"
-corems_toml_path = "configuration/corems.toml"
+corems_toml_path = "configuration/gcms_corems.toml"
 nmdc_metadata_path = "configuration/nmdc_metadata.json"
 output_directory = "output"
 output_filename = "output"
 output_type = "csv"
+metabref_token_path = "configuration/metabref.token"

metaMS/cli.py

@@ -1,9 +1,7 @@
-from multiprocessing import Pool
 from pathlib import Path
 
 import click
 import toml
-
 from corems.encapsulation.output.parameter_to_json import dump_gcms_settings_toml
 
 from metaMS.gcmsWorkflow import (
@@ -12,6 +10,7 @@
     run_gcms_metabolomics_workflow_wdl,
     run_nmdc_metabolomics_workflow,
 )
+
 from metaMS.lcms_lipidomics_workflow import (
     LipidomicsWorkflowParameters,
     run_lcms_lipidomics_workflow,
@@ -32,6 +31,7 @@ def cli():
 @click.argument("output_type", required=True, type=str)
 @click.argument("corems_toml_path", required=True, type=str)
 @click.argument("nmdc_metadata_path", required=True, type=str)
+@click.argument("metabref_token_path", required=True, type=str)
 @click.option("--jobs", "-j", default=4, help="'cpu's'")
 def run_gcms_wdl_workflow(
     file_paths,
@@ -41,6 +41,7 @@ def run_gcms_wdl_workflow(
     output_type,
     corems_toml_path,
     nmdc_metadata_path,
+    metabref_token_path,
     jobs,
 ):
     """Run the GCMS workflow\n
@@ -57,6 +58,7 @@ def run_gcms_wdl_workflow(
         output_filename,
         output_type,
         corems_toml_path,
+        metabref_token_path,
         jobs,
     )