Merge pull request #689 from xchem/m2ms-1512-altlocs

Enable aligned files sdf capture and download (issue 1512, altlocs)

viewer/download_structures.py

@@ -44,7 +44,7 @@
     'apo_desolv_file': ('aligned'),  # SiteObservation: apo_desolv_file
     'bound_file': ('aligned'),  # SiteObservation: bound_file
     'sdf_info': ('aligned'),  # SiteObservation: ligand_mol_file (indirectly)
-    'ligand_mol': ('aligned'),  # SiteObservation: ligand_mol
+    'ligand_sdf': ('aligned'),  # SiteObservation: ligand_sdf
     'ligand_smiles': ('aligned'),  # SiteObservation: ligand_smiles
     'ligand_pdb': ('aligned'),  # SiteObservation: ligand_pdb
     'smiles_info': (''),  # SiteObservation: smiles_info (indirectly)
@@ -87,7 +87,7 @@ class ArchiveFile:
         'diff_file': {},
         'sigmaa_file': {},
         'ligand_pdb': {},
-        'ligand_mol': {},
+        'ligand_sdf': {},
         'ligand_smiles': {},
         # additional ccp4 files, issue 1448
         'event_file_crystallographic': {},
@@ -755,7 +755,7 @@ def _create_structures_dict(site_obvs, protein_params, other_params):
                     'artefacts_file',
                     'pdb_header_file',
                     'ligand_pdb',
-                    'ligand_mol',
+                    'ligand_sdf',
                     'ligand_smiles',
                     'diff_file',
                 ]:
@@ -825,12 +825,12 @@ def _create_structures_dict(site_obvs, protein_params, other_params):
         num_molecules_collected = 0
         num_missing_sd_files = 0
         for so in site_obvs:
-            if so.ligand_mol:
+            if so.ligand_sdf:
                 # There is an SD file (normal)
                 archive_path = str(
                     Path('aligned_files').joinpath(so.code).joinpath(f'{so.code}.sdf')
                 )
-                file_path = str(Path(settings.MEDIA_ROOT).joinpath(so.ligand_mol.name))
+                file_path = str(Path(settings.MEDIA_ROOT).joinpath(so.ligand_sdf.name))
                 # path is ignored when writing sdfs but mandatory field
                 zip_contents['molecules']['sdf_files'].update(
                     {
@@ -845,7 +845,7 @@ def _create_structures_dict(site_obvs, protein_params, other_params):
             else:
                 # No file value (odd).
                 logger.warning(
-                    "SiteObservation record's 'ligand_mol' isn't set (%s)", so
+                    "SiteObservation record's 'ligand_sdf' isn't set (%s)", so
                 )
                 num_missing_sd_files += 1
 
@@ -899,7 +899,7 @@ def get_download_params(request):
         'apo_solv_file': serializer.validated_data['all_aligned_structures'],
         'apo_desolv_file': serializer.validated_data['all_aligned_structures'],
         'ligand_pdb': serializer.validated_data['all_aligned_structures'],
-        'ligand_mol': serializer.validated_data['all_aligned_structures'],
+        'ligand_sdf': serializer.validated_data['all_aligned_structures'],
         'ligand_smiles': serializer.validated_data['all_aligned_structures'],
         'cif_info': serializer.validated_data['cif_info'],
         'mtz_info': serializer.validated_data['mtz_info'],

viewer/migrations/0084_auto_20241108_1119.py

@@ -0,0 +1,28 @@
+# Generated by Django 3.2.25 on 2024-11-08 11:19
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('viewer', '0083_merge_20241105_1101'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='historicalsiteobservation',
+            name='ligand_sdf',
+            field=models.TextField(max_length=255, null=True),
+        ),
+        migrations.AddField(
+            model_name='siteobservation',
+            name='ligand_sdf',
+            field=models.FileField(max_length=255, null=True, upload_to='target_loader_data/'),
+        ),
+        migrations.AlterField(
+            model_name='compoundidentifier',
+            name='name',
+            field=models.TextField(),
+        ),
+    ]

viewer/models.py

@@ -556,6 +556,9 @@ class SiteObservation(Versionable, models.Model):
     ligand_pdb = models.FileField(
         upload_to="target_loader_data/", null=True, max_length=255
     )
+    ligand_sdf = models.FileField(
+        upload_to="target_loader_data/", null=True, max_length=255
+    )
     objects = models.Manager()
     history = HistoricalRecords()
     filter_manager = SiteObservationDataManager()

viewer/target_loader.py

@@ -1311,6 +1311,7 @@ def process_site_observation(
           pdb_apo_solv:  <file path>,
           pdb_apo_desolv:  <file path>,
           ligand_mol:  <file path>,
+          ligand_mol:  <file path>,
           ligand_pdb:  <file path>,
           ligand_smiles: <smiles>,
         }
@@ -1387,6 +1388,7 @@ def process_site_observation(
             ligand_pdb_t,
             ligand_mol_t,
             ligand_smiles_t,
+            ligand_sdf_t,
         ) = self.validate_files(
             obj_identifier=experiment_id,
             file_struct=data,
@@ -1404,6 +1406,7 @@ def process_site_observation(
                 "ligand_pdb",
                 "ligand_mol",
                 "ligand_smiles",
+                "ligand_sdf",
             ),
             validate_files=validate_files,
         )
@@ -1419,6 +1422,7 @@ def process_site_observation(
         ligand_pdb = ligand_pdb_t[0]
         ligand_mol = ligand_mol_t[0]
         ligand_smiles = ligand_smiles_t[0]
+        ligand_sdf = ligand_sdf_t[0]
 
         fields = {
             # Code for this protein (e.g. Mpro_Nterm-x0029_A_501_0)
@@ -1445,7 +1449,8 @@ def process_site_observation(
             "ligand_pdb": str(self._get_final_path(ligand_pdb)),
             "ligand_mol": str(self._get_final_path(ligand_mol)),
             "ligand_smiles": str(self._get_final_path(ligand_smiles)),
-            "pdb_header_file": "currently missing",
+            "ligand_sdf": str(self._get_final_path(ligand_sdf)),
+            "pdb_header_file": None,
         }
 
         return ProcessedObject(