mtbls-mhd-integration 0.0.11__tar.gz → 0.0.13__tar.gz

{mtbls_mhd_integration-0.0.11/mtbls_mhd_integration.egg-info → mtbls_mhd_integration-0.0.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mtbls-mhd-integration
-Version: 0.0.11
+Version: 0.0.13
 Summary: MetaboLights - MetabolomicsHub Integration
 Author-email: MetaboLights Team <metabolights-help@ebi.ac.uk>
 License-Expression: Apache-2.0
@@ -9,7 +9,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: asyncpg>=0.30.0
 Requires-Dist: metabolights-utils>=1.4.16
-Requires-Dist: mhd-model>=0.1.39
+Requires-Dist: mhd-model>=0.1.43
 Requires-Dist: psycopg[binary,pool]>=3.3.2
 Requires-Dist: pydantic>=2.12.4
 Requires-Dist: pydantic-settings>=2.10.1

{mtbls_mhd_integration-0.0.11 → mtbls_mhd_integration-0.0.13}/mtbls2mhd/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "v0.0.11"
+__version__ = "v0.0.13"
 
 import pathlib
 import sys

{mtbls_mhd_integration-0.0.11 → mtbls_mhd_integration-0.0.13}/mtbls2mhd/v0_1/legacy/builder.py

@@ -53,11 +53,7 @@ logger = logging.getLogger(__name__)
 MTBLS_ASSAY_TYPES = {
     "LC-MS": COMMON_ASSAY_TYPES["OBI:0003097S"],
     "GC-MS": COMMON_ASSAY_TYPES["OBI:0003110"],
-    "CE-MS": CvTerm(
-        source="OBI",
-        accession="OBI:0003741",
-        name="capillary electrophoresis mass spectrometry assay",
-    ),
+    "CE-MS": COMMON_ASSAY_TYPES["OBI:0003741"],
     "GCxGC-MS": COMMON_ASSAY_TYPES["OBI:0003110"],
     "FIA-MS": COMMON_ASSAY_TYPES["OBI:0000470"],
     "MALDI-MS": COMMON_ASSAY_TYPES["OBI:0000470"],
@@ -594,7 +590,7 @@ class MhdLegacyDatasetBuilder:
         data: MetabolightsStudyModel,
         config: Mtbls2MhdConfiguration,
     ):
-        result_file_map = {}
+        result_file_map: dict[str, mhd_domain.ResultFile] = {}
         tsv_format = create_cv_term_object(
             type_="descriptor", accession="EDAM:3475", source="EDAM", name="TSV"
         )
@@ -1433,7 +1429,10 @@ class MhdLegacyDatasetBuilder:
         return protocols
 
     def add_keywords(
-        self, mhd_builder: MhDatasetBuilder, mhd_study: mhd_domain.Study, study: Study
+        self,
+        mhd_builder: MhDatasetBuilder,
+        mhd_study: mhd_domain.Study,
+        study: Study,
     ):
         for item in study.study_design_descriptors.design_types:
             keyword = create_cv_term_object(
@@ -1447,12 +1446,62 @@ class MhdLegacyDatasetBuilder:
                 name=item.term or "",
             )
             mhd_builder.add_node(keyword)
-            mhd_builder.link(
-                mhd_study,
-                "has-submitter-keyword",
-                keyword,
-                reverse_relationship_name="keyword-of",
-            )
+
+            if item.source and item.source.lower() in ("data-curation", "workflows"):
+                mhd_builder.link(
+                    mhd_study,
+                    "has-repository-keyword",
+                    keyword,
+                    reverse_relationship_name="keyword-of",
+                )
+            else:
+                mhd_builder.link(
+                    mhd_study,
+                    "has-submitter-keyword",
+                    keyword,
+                    reverse_relationship_name="keyword-of",
+                )
+
+    def add_assay_keywords(
+        self,
+        mhd_builder: MhDatasetBuilder,
+        assays: dict[str, mhd_domain.Assay],
+        study: Study,
+    ):
+        for assay in study.study_assays.assays:
+            mhd_assay = assays.get(assay.file_name)
+            if not mhd_assay:
+                continue
+            for item in assay.assay_descriptors:
+                keyword = create_cv_term_object(
+                    type_="descriptor",
+                    source=item.term_source_ref or "",
+                    accession=self.convert_to_curie(
+                        item.term_source_ref,
+                        item.term_accession_number,
+                    )
+                    or "",
+                    name=item.term or "",
+                )
+                mhd_builder.add_node(keyword)
+
+                if item.source and item.source.lower() in (
+                    "data-curation",
+                    "workflows",
+                ):
+                    mhd_builder.link(
+                        mhd_assay,
+                        "has-repository-keyword",
+                        keyword,
+                        reverse_relationship_name="keyword-of",
+                    )
+                else:
+                    mhd_builder.link(
+                        mhd_assay,
+                        "has-submitter-keyword",
+                        keyword,
+                        reverse_relationship_name="keyword-of",
+                    )
 
     def find_file_format(
         self,
@@ -1650,54 +1699,103 @@ class MhdLegacyDatasetBuilder:
         mhd_builder: MhDatasetBuilder,
         mhd_study: mhd_domain.Study,
         data: MetabolightsStudyModel,
+        result_files: dict[str, mhd_domain.ResultFile],
     ):
-        for file_name, maf_file in data.metabolite_assignments.items():
-            if maf_file.table.data.get("metabolite_identification"):
-                identifiers = maf_file.table.data.get("database_identifier")
-                for idx, name in enumerate(
-                    maf_file.table.data["metabolite_identification"]
-                ):
-                    if not name:
-                        continue
-                    met = mhd_domain.Metabolite(
-                        name=name,
-                    )
-                    if identifiers and identifiers[idx]:
-                        value = identifiers[idx]
-                        identifier = None
-                        if value.startswith("CHEBI"):
-                            identifier = create_cv_term_value_object(
-                                type_="metabolite-identifier",
-                                source="CHEMINF",
-                                accession="CHEMINF:000407",
-                                name="ChEBI identifier",
-                                value=value,
-                            )
-                        elif value.startswith("HMDB"):
-                            identifier = create_cv_term_value_object(
-                                type_="metabolite-identifier",
-                                source="CHEMINF",
-                                accession="CHEMINF:000408",
-                                name="HMDB identifier",
-                                value=value.replace(":", ""),
-                            )
+        for maf_filename, maf_file in data.metabolite_assignments.items():
+            if not maf_file.table.data.get("metabolite_identification"):
+                continue
+            result_file = result_files.get(maf_filename)
+            for idx, name in enumerate(
+                maf_file.table.data["metabolite_identification"]
+            ):
+                if not name or not name.strip():
+                    continue
+                met = mhd_domain.Metabolite(name=name)
+                assignments = {}
+                data: dict[str, str] = maf_file.table.data
+                submitted_identifiers = []
+                assigned_chebi_identifiers = []
+                assigned_refmet_identifiers = []
+                if maf_file.table.data.get("database_identifier"):
+                    submitted_identifiers = [
+                        x.strip()
+                        for x in data["database_identifier"][idx].split("|")
+                        if x
+                    ]
+                if maf_file.table.data.get("assigned_chebi_identifier"):
+                    assigned_chebi_identifiers = [
+                        x.strip()
+                        for x in data["assigned_chebi_identifier"][idx].split("|")
+                        if x
+                    ]
+                if maf_file.table.data.get("assigned_refmet_identifier"):
+                    assigned_refmet_identifiers = [
+                        x.strip()
+                        for x in data["assigned_refmet_identifier"][idx].split("|")
+                        if x
+                    ]
 
-                        if identifier:
-                            mhd_builder.add(identifier)
-                            # met.identifier_refs = [identifier.id_]
-                            mhd_builder.link(
-                                met,
-                                "identified-as",
-                                identifier,
-                                reverse_relationship_name="reported-identifier-of",
-                            )
-                    mhd_builder.add(met)
+                for identifiers in [
+                    (submitted_identifiers, ""),
+                    (assigned_chebi_identifiers, "CHEBI"),
+                    (assigned_refmet_identifiers, "REFMET"),
+                ]:
+                    for identifiers, compound_source in assignments:
+                        if not identifiers:
+                            continue
+                        for identifier_value in identifiers:
+                            identifier = None
+                            if (
+                                compound_source == "CHEBI"
+                                or identifier_value.upper().startswith("CHEBI")
+                            ):
+                                identifier = create_cv_term_value_object(
+                                    type_="metabolite-identifier",
+                                    source="CHEMINF",
+                                    accession="CHEMINF:000407",
+                                    name="ChEBI identifier",
+                                    value=identifier_value,
+                                )
+                            elif identifier_value.upper().startswith("HMDB"):
+                                identifier = create_cv_term_value_object(
+                                    type_="metabolite-identifier",
+                                    source="CHEMINF",
+                                    accession="CHEMINF:000408",
+                                    name="HMDB identifier",
+                                    value=identifier_value,
+                                )
+                            elif compound_source == "REFMET":
+                                identifier = create_cv_term_value_object(
+                                    type_="metabolite-identifier",
+                                    source="REFMET",
+                                    accession="",
+                                    name="RefMet identifier",
+                                    value=identifier_value,
+                                )
+
+                            if identifier:
+                                mhd_builder.add(identifier)
+                                mhd_builder.link(
+                                    met,
+                                    "identified-as",
+                                    identifier,
+                                    reverse_relationship_name="reported-identifier-of",
+                                )
+                mhd_builder.add(met)
+                if result_file:
                     mhd_builder.link(
-                        mhd_study,
+                        result_file,
                         "reports",
                         met,
                         reverse_relationship_name="reported-in",
                     )
+                result_file
+                mhd_builder.link(
+                    mhd_study,
+                    "reports",
+                    met,
+                    reverse_relationship_name="reported-in",
+                )
 
     def add_assays(
         self,
@@ -1708,9 +1806,9 @@ class MhdLegacyDatasetBuilder:
         metadata_files: dict[str, mhd_domain.CvTermObject],
         samples: dict[str, mhd_domain.Sample],
         files_map,
-    ) -> mhd_domain.Assay:
+    ) -> dict[str, mhd_domain.Assay]:
         protocol_summaries: OrderedDict[str, ProtocolRunSummary] = OrderedDict()
-        assays: list[mhd_domain.Assay] = []
+        assays = dict[str, mhd_domain.Assay] = OrderedDict()
         for assay in selected_assays:
             if assay.file_name not in data.assays:
                 continue
@@ -1724,7 +1822,7 @@ class MhdLegacyDatasetBuilder:
             )
 
             mhd_builder.add(mhd_assay)
-            assays.append(mhd_assay)
+            assays[assay.file_name] = mhd_assay
             mhd_builder.link(
                 mhd_study, "has-assay", mhd_assay, reverse_relationship_name="part-of"
             )
@@ -1833,8 +1931,7 @@ class MhdLegacyDatasetBuilder:
                 samples,
                 protocol_summaries,
             )
-
-        for mhd_assay in assays:
+        for _, mhd_assay in assays.items():
             self.add_assay_protocols(mhd_builder, mhd_study, data, mhd_assay)
         return assays
 
@@ -1971,20 +2068,28 @@ class MhdLegacyDatasetBuilder:
                 data.study_db_metadata.release_date,
             )
         # actual or estimated
-        public_release_date_str = (
-            db_metadata.first_public_date or db_metadata.release_date or None
-        )
+        submission_date_str = None
+        public_release_date_str = None
+        if db_metadata:
+            if db_metadata.first_private_date:
+                submission_date_str = db_metadata.first_private_date
+            elif db_metadata.submission_date:
+                submission_date_str = db_metadata.submission_date
+            if db_metadata.first_public_date:
+                public_release_date_str = db_metadata.first_public_date
+            elif db_metadata.release_date:
+                public_release_date_str = db_metadata.release_date
+
         public_release_date = (
             datetime.datetime.strptime(public_release_date_str, "%Y-%m-%d")
             if public_release_date_str
             else None
         )
         submission_date = (
-            datetime.datetime.strptime(db_metadata.first_private_date, "%Y-%m-%d")
-            if db_metadata and db_metadata.first_private_date
+            datetime.datetime.strptime(submission_date_str, "%Y-%m-%d")
+            if submission_date_str
             else None
         )
-
         mhd_study = mhd_domain.Study(
             repository_identifier=study.identifier,
             created_by_ref=dataset_provider.id_,
@@ -2029,12 +2134,11 @@ class MhdLegacyDatasetBuilder:
             self.add_publications(data, mhd_builder, mhd_study)
             self.add_protocols(mhd_builder, mhd_study, study)
 
-            self.add_keywords(mhd_builder, mhd_study, study)
-            self.add_reported_metabolites(mhd_builder, mhd_study, data)
-
             result_files = self.add_result_files(
                 mhd_builder, mhd_study, data, config=config
             )
+            self.add_reported_metabolites(mhd_builder, mhd_study, data, result_files)
+
             files_map = self.add_data_files(
                 mhd_builder,
                 mhd_study,
@@ -2043,7 +2147,7 @@ class MhdLegacyDatasetBuilder:
                 result_files,
                 config=config,
             )
-            self.add_assays(
+            mhd_assays = self.add_assays(
                 mhd_builder,
                 mhd_study,
                 data,
@@ -2052,6 +2156,8 @@ class MhdLegacyDatasetBuilder:
                 samples,
                 files_map,
             )
+            self.add_keywords(mhd_builder, mhd_study, study)
+            self.add_assay_keywords(mhd_builder, mhd_assays, study)
 
         mhd_dataset: MhDatasetBaseProfile = mhd_builder.create_dataset(
             start_item_refs=[mhd_study.id_], dataset_class=MhDatasetLegacyProfile

{mtbls_mhd_integration-0.0.11 → mtbls_mhd_integration-0.0.13}/mtbls2mhd/v0_1/legacy/convertor.py

@@ -38,7 +38,7 @@ class LegacyProfileV01Convertor(BaseMhdConvertor):
         )
         try:
             success, message = mhd_dataset_builder.build(
-                mhd_id=mhd_identifier,
+                mhd_id=None,
                 mtbls_study_id=repository_identifier,
                 mtbls_study_path=mtbls_study_path,
                 mtbls_study_repository_url=mtbls_study_repository_url,

{mtbls_mhd_integration-0.0.11 → mtbls_mhd_integration-0.0.13/mtbls_mhd_integration.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mtbls-mhd-integration
-Version: 0.0.11
+Version: 0.0.13
 Summary: MetaboLights - MetabolomicsHub Integration
 Author-email: MetaboLights Team <metabolights-help@ebi.ac.uk>
 License-Expression: Apache-2.0
@@ -9,7 +9,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: asyncpg>=0.30.0
 Requires-Dist: metabolights-utils>=1.4.16
-Requires-Dist: mhd-model>=0.1.39
+Requires-Dist: mhd-model>=0.1.43
 Requires-Dist: psycopg[binary,pool]>=3.3.2
 Requires-Dist: pydantic>=2.12.4
 Requires-Dist: pydantic-settings>=2.10.1

{mtbls_mhd_integration-0.0.11 → mtbls_mhd_integration-0.0.13}/mtbls_mhd_integration.egg-info/requires.txt

@@ -1,6 +1,6 @@
 asyncpg>=0.30.0
 metabolights-utils>=1.4.16
-mhd-model>=0.1.39
+mhd-model>=0.1.43
 psycopg[binary,pool]>=3.3.2
 pydantic>=2.12.4
 pydantic-settings>=2.10.1

{mtbls_mhd_integration-0.0.11 → mtbls_mhd_integration-0.0.13}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mtbls-mhd-integration"
-version = "0.0.11"
+version = "0.0.13"
 description = "MetaboLights - MetabolomicsHub Integration"
 authors = [{"name" = "MetaboLights Team", "email" = "metabolights-help@ebi.ac.uk"}]
 license = "Apache-2.0"
@@ -9,7 +9,7 @@ requires-python = ">=3.12,<4.0"
 dependencies = [
     "asyncpg>=0.30.0",
     "metabolights-utils>=1.4.16",
-    "mhd-model>=0.1.39",
+    "mhd-model>=0.1.43",
     "psycopg[binary,pool]>=3.3.2",
     "pydantic>=2.12.4",
     "pydantic-settings>=2.10.1",
@@ -31,6 +31,10 @@ test = [
     "pytest-cov>=6.2.1",
 ]
 
+[tool.uv]
+default-groups = []
+
+
 [project.scripts]
 mtbls-mhd-cli = "mtbls2mhd.commands.cli:cli"
 
@@ -50,7 +54,7 @@ exclude = ["tests*", "docs*"]
 [tool.commitizen]
 name = "cz_conventional_commits"
 version_provider = "uv"
-version = "0.0.113"
+version = "0.0.133"
 tag_format = "v$major.$minor.$patch"
 version_files = [
     "pyproject.toml:version",