Merge branch 'gcms-workflow' into 'master'

Update GC-MS workflow to leverage MetabRef API functionality

See merge request mass-spectrometry/corems!148

Author: corilo

examples/scripts/GC-MS MetabRef.py

@@ -1,43 +1,31 @@
 import warnings
+
 warnings.filterwarnings("ignore")
 
 import os
-from pathlib import Path
-from multiprocessing import Pool
 import sys
+from multiprocessing import Pool
 
-import corems
+from corems.mass_spectra.calc.GC_RI_Calibration import get_rt_ri_pairs
 from corems.mass_spectra.input.andiNetCDF import ReadAndiNetCDF
 from corems.molecular_id.search.compoundSearch import LowResMassSpectralMatch
-from corems.mass_spectra.calc.GC_RI_Calibration import get_rt_ri_pairs
-
-import metabrefapi
-
-
-def start_gcms_metabref_sql(normalize=False, url='sqlite://'):
-    # Get MetabRef GCMS library
-    metabref_lib = metabrefapi.get_metabref_gcms_library()
-
-    # Convert to CoreMS format
-    corems_lib = metabrefapi.metabref_to_corems(metabref_lib, normalize=normalize)
-
-    # Convert to SQLite
-    corems_lib = metabrefapi.corems_to_sqlite(corems_lib, url=url)
+from corems.molecular_id.search.database_interfaces import MetabRefGCInterface
 
-    return corems_lib
 
+def start_gcms_metabref_sql(normalize=False, url="sqlite://"):
+    # Initialize MetabRef interface
+    metabref = MetabRefGCInterface()
 
-def start_fames_metabref_sql(normalize=False, url='sqlite://'):
-    # Get MetabRef GCMS library
-    metabref_lib = metabrefapi.get_metabref_fames_library()
+    # Pull contents into SQLite
+    return metabref.get_library(format="sql")
 
-    # Convert to CoreMS format
-    corems_lib = metabrefapi.metabref_to_corems(metabref_lib, normalize=normalize)
 
-    # Convert to SQLite
-    corems_lib = metabrefapi.corems_to_sqlite(corems_lib, url=url)
+def start_fames_metabref_sql(normalize=False, url="sqlite://"):
+    # Initialize MetabRef interface
+    metabref = MetabRefGCInterface()
 
-    return corems_lib
+    # Pull contents into SQLite
+    return metabref.get_fames(format="sql")
 
 
 def get_gcms(filepath):
@@ -55,6 +43,7 @@ def get_gcms(filepath):
 
     return gcms
 
+
 def stand_alone():
     # Determine filename
     filepath = get_filename()
@@ -73,15 +62,17 @@ def stand_alone():
 
 
 def get_reference_dict(calibration_filepath=False):
-    from PySide2.QtWidgets import QFileDialog, QApplication
     from PySide2.QtCore import Qt
+    from PySide2.QtWidgets import QApplication, QFileDialog
 
     # Open dialog to select calibration file
     if not calibration_filepath:
         app = QApplication(sys.argv)
         file_dialog = QFileDialog()
         file_dialog.setWindowFlags(Qt.WindowStaysOnTopHint)
-        filepath = file_dialog.getOpenFileName(None, "FAMES REF FILE", filter="*.cdf")[0]
+        filepath = file_dialog.getOpenFileName(None, "FAMES REF FILE", filter="*.cdf")[
+            0
+        ]
         file_dialog.close()
         app.exit()
 
@@ -92,7 +83,7 @@ def get_reference_dict(calibration_filepath=False):
     # No filepath
     if not filepath:
         raise ValueError("Must supply calibration file.")
-        
+
     # Parse supplied calibration data
     gcms_ref_obj = get_gcms(filepath)
 
@@ -130,8 +121,12 @@ def run(args):
     return gcms
 
 
-def auto_calibrate_and_search(file_locations, output_filename, jobs, calibration_filepath):
-    ref_dict, cal_filepath = get_reference_dict(calibration_filepath=calibration_filepath)
+def auto_calibrate_and_search(
+    file_locations, output_filename, jobs, calibration_filepath
+):
+    ref_dict, cal_filepath = get_reference_dict(
+        calibration_filepath=calibration_filepath
+    )
 
     if ref_dict:
         # run in multiprocessing mode
@@ -147,35 +142,38 @@ def auto_calibrate_and_search(file_locations, output_filename, jobs, calibration
 
 
 def calibrate_and_search(filename, jobs):
-    from PySide2.QtWidgets import QFileDialog, QApplication
-    from PySide2.QtCore import Qt
-    
     import csv
-    
+
+    from PySide2.QtCore import Qt
+    from PySide2.QtWidgets import QApplication, QFileDialog
+
     ref_dict, cal_filepath = get_reference_dict()
-    
+
     if ref_dict:
         file_dialog = QFileDialog()
         file_dialog.setWindowFlags(Qt.WindowStaysOnTopHint)
-    
+
         if file_dialog:
-            file_locations = file_dialog.getOpenFileNames(None, "Standard Compounds Files", filter="*.cdf")
+            file_locations = file_dialog.getOpenFileNames(
+                None, "Standard Compounds Files", filter="*.cdf"
+            )
             file_dialog.close()
-    
+
             # run in multiprocessing mode
             pool = Pool(jobs)
-            args = [(filepath, ref_dict, cal_filepath) for filepath in file_locations[0]]
+            args = [
+                (filepath, ref_dict, cal_filepath) for filepath in file_locations[0]
+            ]
             gcmss = pool.map(run, args)
             pool.close()
             pool.join()
             for gcms in gcmss:
-    
                 gcms.to_csv(filename)
                 gcms.to_hdf()
 
 
 def worker(args):
-    cProfile.runctx('run(args)', globals(), locals(), 'gc-ms.prof')
+    cProfile.runctx("run(args)", globals(), locals(), "gc-ms.prof")
 
 
 def auto_process(jobs):
@@ -188,21 +186,28 @@ def auto_process(jobs):
         # print(output_filename)
 
         file_locations = glob.glob(str((rootdir / output_filename)) + "/*.cdf")
-        calibration_filepath = ''
+        calibration_filepath = ""
         for filepath in file_locations:
             if "FAME" in filepath:
                 calibration_filepath = filepath
         if calibration_filepath:
-            auto_calibrate_and_search(file_locations, output_filename, jobs, calibration_filepath)
+            auto_calibrate_and_search(
+                file_locations, output_filename, jobs, calibration_filepath
+            )
         else:
-            print("Could not find a calibration experimental file for {}".format(output_filename))
+            print(
+                "Could not find a calibration experimental file for {}".format(
+                    output_filename
+                )
+            )
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
+    # Set token
     TOKEN_PATH = "metabref.token"
-    metabrefapi.set_token(TOKEN_PATH)
+    MetabRefGCInterface().set_token(TOKEN_PATH)
 
     jobs = 6
-    filename = 'json_test'
+    filename = "json_test"
 
     calibrate_and_search(filename, jobs)