From 382034776f3ae6061f0dd7cb78a295ae22e55a2a Mon Sep 17 00:00:00 2001
From: Cunliang Geng <c.geng@esciencecenter.nl>
Date: Tue, 5 Dec 2023 14:49:17 +0100
Subject: [PATCH] update logics of loading metabolomics data

---
 src/nplinker/loader.py | 31 ++++++++++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

diff --git a/src/nplinker/loader.py b/src/nplinker/loader.py
index 7c0ab98c..4642d788 100644
--- a/src/nplinker/loader.py
+++ b/src/nplinker/loader.py
@@ -17,6 +17,13 @@
 from nplinker.globals import PFAM_PATH
 from nplinker.globals import STRAIN_MAPPINGS_FILENAME
 from nplinker.logconfig import LogConfig
+from nplinker.metabolomics import add_annotation_to_spectrum
+from nplinker.metabolomics import add_spectrum_to_mf
+from nplinker.metabolomics import add_strains_to_spectrum
+from nplinker.metabolomics import get_spectra_from_mfs
+from nplinker.metabolomics.gnps import GNPSAnnotationLoader
+from nplinker.metabolomics.gnps import GNPSMolecularFamilyLoader
+from nplinker.metabolomics.gnps import GNPSSpectrumLoader
 from nplinker.pairedomics.downloader import PODPDownloader
 from nplinker.pairedomics.runbigscape import run_bigscape
 from nplinker.pairedomics.strain_mappings_generator import podp_generate_strain_mappings
@@ -399,8 +406,30 @@ def _load_strain_mappings(self):
 
         return True
 
-    # TODO CG: rewrite the loading process using GPNSLoader
     def _load_metabolomics(self):
+        """Loads metabolomics data to Spectrum and MolecularFamily objects."""
+        logger.debug("\nLoading metabolomics data starts...")
+
+        # Step 1: load all Spectrum objects
+        raw_spectra = GNPSSpectrumLoader(self.mgf_file).spectra
+        # Step 2: load all GNPS annotations
+        raw_annotations = GNPSAnnotationLoader(self.annotations_config_file).annotations
+        # Step 3: load all MolecularFamily objects
+        raw_molfams = GNPSMolecularFamilyLoader(self.edges_file).get_mfs(keep_singleton=False)
+
+        # Step 4: add GNPS annotations to Spectrum.gnps_annotations
+        add_annotation_to_spectrum(raw_annotations, raw_spectra)
+        # Step 5: add strains to Spectrum.strains
+        spectra_with_strains, _ = add_strains_to_spectrum(self.strains, raw_spectra)
+
+        # Step 6: add Spectrum objects to MolecularFamily
+        mf_with_spec, _, _ = add_spectrum_to_mf(spectra_with_strains, raw_molfams)
+
+        # Step 7: get MolecularFamily objects and their Spectrum members
+        self.molfams = mf_with_spec
+        self.spectra = get_spectra_from_mfs(self.molfams)
+
+        logger.debug("Loading metabolomics data completed\n")
         return True
 
     def _load_genomics(self):