mtbls-mhd-integration 0.0.12__tar.gz → 0.0.14__tar.gz

{mtbls_mhd_integration-0.0.12/mtbls_mhd_integration.egg-info → mtbls_mhd_integration-0.0.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mtbls-mhd-integration
-Version: 0.0.12
+Version: 0.0.14
 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>=0.1.41
+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-0.0.12 → mtbls_mhd_integration-0.0.14}/mtbls2mhd/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "v0.0.12"
+__version__ = "v0.0.14"
 
 import pathlib
 import sys

{mtbls_mhd_integration-0.0.12 → mtbls_mhd_integration-0.0.14}/mtbls2mhd/convertor_factory.py

@@ -6,6 +6,7 @@ from mhd_model.model.definitions import (
 )
 
 from mtbls2mhd.v0_1.legacy.convertor import LegacyProfileV01Convertor
+from mtbls2mhd.v0_1.ms.convertor import MsProfileConvertor
 
 
 class Mtbls2MhdConvertorFactory(BaseMhdConvertorFactory):
@@ -21,7 +22,10 @@ class Mtbls2MhdConvertorFactory(BaseMhdConvertorFactory):
                     target_mhd_model_profile_uri=target_mhd_model_profile_uri,
                 )
             elif target_mhd_model_profile_uri == MHD_MODEL_V0_1_MS_PROFILE_NAME:
-                raise NotImplementedError()
+                return MsProfileConvertor(
+                    target_mhd_model_schema_uri=target_mhd_model_schema_uri,
+                    target_mhd_model_profile_uri=target_mhd_model_profile_uri,
+                )
             raise NotImplementedError()
         else:
             raise NotImplementedError()

{mtbls_mhd_integration-0.0.12 → mtbls_mhd_integration-0.0.14}/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"],
@@ -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,
@@ -1757,9 +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: OrderedDict[str, mhd_domain.Assay] = OrderedDict()
         for assay in selected_assays:
             if assay.file_name not in data.assays:
                 continue
@@ -1773,7 +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"
             )
@@ -1882,8 +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
 
@@ -2020,20 +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_,
@@ -2078,8 +2134,6 @@ 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)
-
             result_files = self.add_result_files(
                 mhd_builder, mhd_study, data, config=config
             )
@@ -2093,7 +2147,7 @@ class MhdLegacyDatasetBuilder:
                 result_files,
                 config=config,
             )
-            self.add_assays(
+            mhd_assays = self.add_assays(
                 mhd_builder,
                 mhd_study,
                 data,
@@ -2102,6 +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-0.0.14/mtbls2mhd/v0_1/ms/convertor.py

@@ -0,0 +1,59 @@
+from pathlib import Path
+
+from mhd_model.convertors.mhd.convertor import BaseMhdConvertor
+from mhd_model.shared.model import Revision
+
+from mtbls2mhd.config import Mtbls2MhdConfiguration, get_default_config
+from mtbls2mhd.v0_1.legacy.builder import BuildType, MhdLegacyDatasetBuilder
+
+
+class MsProfileConvertor(BaseMhdConvertor):
+    def __init__(
+        self,
+        target_mhd_model_schema_uri: str,
+        target_mhd_model_profile_uri: str,
+    ):
+        self.target_mhd_model_schema_uri = target_mhd_model_schema_uri
+        self.target_mhd_model_profile_uri = target_mhd_model_profile_uri
+
+    def convert(
+        self,
+        repository_name: str,
+        repository_identifier: str,
+        mhd_identifier: None | str,
+        repository_revision: None | Revision = None,
+        config: None | Mtbls2MhdConfiguration = None,  # noqa: F821
+        cached_mtbls_model_file_path: None | str = None,
+        **kwargs,
+    ):
+        if not config:
+            config = get_default_config()
+        mhd_dataset_builder = MhdLegacyDatasetBuilder()
+        mtbls_study_repository_url = (
+            f"{config.study_http_base_url}/{repository_identifier}"
+        )
+
+        mtbls_study_path = Path(config.mtbls_studies_root_path) / Path(
+            repository_identifier
+        )
+        try:
+            success, message = mhd_dataset_builder.build(
+                mhd_id=mhd_identifier,
+                mtbls_study_id=repository_identifier,
+                mtbls_study_path=mtbls_study_path,
+                mtbls_study_repository_url=mtbls_study_repository_url,
+                target_mhd_model_schema_uri=self.target_mhd_model_schema_uri,
+                target_mhd_model_profile_uri=self.target_mhd_model_profile_uri,
+                config=config,
+                cached_mtbls_model_file_path=cached_mtbls_model_file_path,
+                revision=repository_revision,
+                repository_name=repository_name,
+                build_type=BuildType.FULL_AND_CUSTOM_NODES,
+                **kwargs,
+            )
+            return success, message
+        except Exception as ex:
+            import traceback
+
+            traceback.print_exc()
+            return False, str(ex)

{mtbls_mhd_integration-0.0.12 → mtbls_mhd_integration-0.0.14/mtbls_mhd_integration.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mtbls-mhd-integration
-Version: 0.0.12
+Version: 0.0.14
 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>=0.1.41
+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-0.0.12 → mtbls_mhd_integration-0.0.14}/mtbls_mhd_integration.egg-info/requires.txt

@@ -1,6 +1,6 @@
 asyncpg>=0.30.0
 metabolights-utils>=1.4.16
-mhd-model>=0.1.41
+mhd-model>=0.1.43
 psycopg[binary,pool]>=3.3.2
 pydantic>=2.12.4
 pydantic-settings>=2.10.1

{mtbls_mhd_integration-0.0.12 → mtbls_mhd_integration-0.0.14}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mtbls-mhd-integration"
-version = "0.0.12"
+version = "0.0.14"
 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>=0.1.41",
+    "mhd-model>=0.1.43",
     "psycopg[binary,pool]>=3.3.2",
     "pydantic>=2.12.4",
     "pydantic-settings>=2.10.1",
@@ -54,7 +54,7 @@ exclude = ["tests*", "docs*"]
 [tool.commitizen]
 name = "cz_conventional_commits"
 version_provider = "uv"
-version = "0.0.123"
+version = "0.0.143"
 tag_format = "v$major.$minor.$patch"
 version_files = [
     "pyproject.toml:version",

mtbls_mhd_integration-0.0.12/mtbls2mhd/v0_1/ms/convertor.py

@@ -1,3 +0,0 @@
-class Mtbs2MhdMsProfileConvertor:
-    def convert():
-        raise NotImplementedError()