Update lipid workflow module and params for cli

Dockerfile

@@ -1,4 +1,4 @@
-FROM corilo/corems:base-mono-pythonnet
+FROM jcarr87/corems-base-py3.10
 WORKDIR /metams
 
 COPY metaMS/ /metams/metaMS/

configuration/lipidomics_metams.toml

@@ -1,4 +1,6 @@
 directory = "data/raw_data/lipid_data"
 output_directory = "output"
-corems_toml_path = "configuration/lipidomics_corems.toml"
+corems_toml_path = "configuration/emsl_lipidomics_corems_params.toml"
+metabref_token_path = "metabref.token"
+scan_translator_path = "configuration/emsl_lipidomics_scan_translator.toml"
 cores = 1

metaMS/cli.py

@@ -159,10 +159,16 @@ def dump_lipidomics_corems_toml_template(toml_file_name):
     type=str,
     help="The directory where the output files will be stored",
 )
+@click.option(
+    "-t", "--token_path", required=False, type=str, help="The path to the metabref token"
+)
+@click.option(
+    "-s", "--scan_translator_path", required=False, type=str, help="The path to the scan translator file"
+)
 @click.option(
     "-j", "--cores", required=False, type=int, help="'cpu's to use for processing"
 )
-def run_lipidomics_workflow(paramaters_file, directory, output_directory, cores):
+def run_lipidomics_workflow(paramaters_file, directory, output_directory, token_path, scan_translator_path, cores):
     """Run the lipidomics workflow
 
     Parameters

metaMS/lcms_lipidomics_workflow.py

@@ -1,5 +1,6 @@
 from dataclasses import dataclass
 import toml
+from pathlib import Path
 
 
 @dataclass
@@ -15,14 +16,21 @@ class LipidomicsWorkflowParameters:
         The directory where the output files will be stored
     corems_toml_path : str
         The path to the corems configuration file
+    metabref_token_path : str
+        The path to the metabref token file
+        See https://metabref.emsl.pnnl.gov/api for more information for how to get a token
+    scan_translator_path : str
+        The path to the scan translator file, optional
     cores : int
-        The number of cores to use for processing
+        The number of cores to use for processing, optional
 
     """
 
     directory: str = "data/..."
     output_directory: str = "output/..."
     corems_toml_path: str = "configuration/lipidomics_corems.toml"
+    metabref_token_path: str = None
+    scan_translator_path: str = None
     cores: int = 1
 
 
@@ -31,6 +39,8 @@ def run_lcms_lipidomics_workflow(
     directory=None,
     output_directory=None,
     corems_toml_path=None,
+    metabref_token_path=None,
+    scan_translator_path=None,
     cores=None,
 ):
     if lipidomics_workflow_paramaters_file is not None:
@@ -41,8 +51,18 @@ def run_lcms_lipidomics_workflow(
         lipid_workflow_params = LipidomicsWorkflowParameters(
             directory=directory,
             output_directory=output_directory,
+            metabref_token_path=metabref_token_path,
+            scan_translator_path=scan_translator_path,
             corems_toml_path=corems_toml_path,
             cores=cores,
         )
+
+    # Make output dir and get list of files to process
+    out_dir = Path(lipid_workflow_params.output_directory)
+    out_dir.mkdir(parents=True, exist_ok=True)
+
+    file_dir = Path(lipid_workflow_params.directory)
+    files_list = list(file_dir.glob("*.raw"))
+    out_paths_list = [out_dir / f.stem for f in files_list]
 
     # TODO KRH: Add full lipidomics workflow here

requirements.txt

@@ -1,4 +1,4 @@
-corems>=1.5.0
+corems>=3.0.0
 Click>=7.1.1
 requests
 nmdc-schema>=7.0.0

wdl/metaMS_lipidomics.wdl

@@ -14,6 +14,8 @@ task runLipidomicsMetaMS {
     }
 
     runtime {
-        docker: "microbiomedata/metams:2.2.2"
+        docker: "local-metams:latest"
+        #TODO KRH: Change to dockerhub version after we've pushed the updated image
     }
-}
+}
+

wdl/metams_input_lipidomics.json

@@ -1,3 +1,3 @@
 {
-    "lcmsLipidomics.runLipidomicsMetaMS.config_file": "configuration/lipidomics_metams.toml"
+    "lcmsLipidomics.runLipidomicsMetaMS.config_file": "lipidomics_metams.toml"
 }