nmdc-runtime 1.10.0__py3-none-any.whl → 2.0.0__py3-none-any.whl

nmdc_runtime/site/translation/submission_portal_translator.py

@@ -64,9 +64,9 @@ class SubmissionPortalTranslator(Translator):
     def __init__(
         self,
         metadata_submission: JSON_OBJECT = {},
-        omics_processing_mapping: Optional[list] = None,
-        data_object_mapping: Optional[list] = None,
         *args,
+        nucleotide_sequencing_mapping: Optional[list] = None,
+        data_object_mapping: Optional[list] = None,
         # Additional study-level metadata not captured by the submission portal currently
         # See: https://github.com/microbiomedata/submission-schema/issues/162
         study_doi_category: Optional[str] = None,
@@ -84,7 +84,7 @@ class SubmissionPortalTranslator(Translator):
         super().__init__(*args, **kwargs)
 
         self.metadata_submission = metadata_submission
-        self.omics_processing_mapping = omics_processing_mapping
+        self.nucleotide_sequencing_mapping = nucleotide_sequencing_mapping
         self.data_object_mapping = data_object_mapping
 
         self.study_doi_category = (
@@ -127,6 +127,7 @@ class SubmissionPortalTranslator(Translator):
             email=study_form.get("piEmail"),
             orcid=study_form.get("piOrcid"),
             profile_image_url=self.study_pi_image_url,
+            type=nmdc.PersonValue.class_class_curie,
         )
 
     def _get_doi(self, metadata_submission: JSON_OBJECT) -> Union[List[nmdc.Doi], None]:
@@ -147,6 +148,7 @@ class SubmissionPortalTranslator(Translator):
                 doi_value=dataset_doi,
                 doi_provider=self.study_doi_provider,
                 doi_category=self.study_doi_category,
+                type="nmdc:Doi",
             )
         ]
 
@@ -167,8 +169,10 @@ class SubmissionPortalTranslator(Translator):
                 applies_to_person=nmdc.PersonValue(
                     name=contributor.get("name"),
                     orcid=contributor.get("orcid"),
+                    type="nmdc:PersonValue",
                 ),
                 applied_roles=contributor.get("roles"),
+                type="nmdc:CreditAssociation",
             )
             for contributor in contributors
         ]
@@ -217,7 +221,10 @@ class SubmissionPortalTranslator(Translator):
         if not match:
             return None
 
-        qv = nmdc.QuantityValue(has_raw_value=raw_value)
+        qv = nmdc.QuantityValue(
+            has_raw_value=raw_value,
+            type="nmdc:QuantityValue",
+        )
         if match.group(2):
             # having group 2 means the value is a range like "0 - 1". Either
             # group 1 or group 2 might be the minimum especially when handling
@@ -264,6 +271,7 @@ class SubmissionPortalTranslator(Translator):
         return nmdc.OntologyClass(
             name=match.group(1).strip(),
             id=match.group(2).strip(),
+            type="nmdc:OntologyClass",
         )
 
     def _get_controlled_identified_term_value(
@@ -285,7 +293,9 @@ class SubmissionPortalTranslator(Translator):
             return None
 
         return nmdc.ControlledIdentifiedTermValue(
-            has_raw_value=raw_value, term=ontology_class
+            has_raw_value=raw_value,
+            term=ontology_class,
+            type="nmdc:ControlledIdentifiedTermValue",
         )
 
     def _get_controlled_term_value(
@@ -302,7 +312,10 @@ class SubmissionPortalTranslator(Translator):
         if not raw_value:
             return None
 
-        value = nmdc.ControlledTermValue(has_raw_value=raw_value)
+        value = nmdc.ControlledTermValue(
+            has_raw_value=raw_value,
+            type="nmdc:ControlledTermValue",
+        )
         ontology_class = self._get_ontology_class(raw_value)
         if ontology_class is not None:
             value.term = ontology_class
@@ -332,7 +345,10 @@ class SubmissionPortalTranslator(Translator):
             return None
 
         return nmdc.GeolocationValue(
-            has_raw_value=raw_value, latitude=match.group(1), longitude=match.group(2)
+            has_raw_value=raw_value,
+            latitude=match.group(1),
+            longitude=match.group(2),
+            type="nmdc:GeolocationValue",
         )
 
     def _get_float(self, raw_value: Optional[str]) -> Union[float, None]:
@@ -425,6 +441,7 @@ class SubmissionPortalTranslator(Translator):
             principal_investigator=self._get_pi(metadata_submission),
             study_category=self.study_category,
             title=self._get_from(metadata_submission, ["studyForm", "studyName"]),
+            type="nmdc:Study",
             websites=self._get_from(
                 metadata_submission, ["studyForm", "linkOutWebpage"]
             ),
@@ -435,15 +452,24 @@ class SubmissionPortalTranslator(Translator):
     ):
         transformed_value = None
         if slot.range == "TextValue":
-            transformed_value = nmdc.TextValue(has_raw_value=value)
+            transformed_value = nmdc.TextValue(
+                has_raw_value=value,
+                type="nmdc:TextValue",
+            )
         elif slot.range == "QuantityValue":
-            transformed_value = self._get_quantity_value(value, unit=unit)
+            transformed_value = self._get_quantity_value(
+                value,
+                unit=unit,
+            )
         elif slot.range == "ControlledIdentifiedTermValue":
             transformed_value = self._get_controlled_identified_term_value(value)
         elif slot.range == "ControlledTermValue":
             transformed_value = self._get_controlled_term_value(value)
         elif slot.range == "TimestampValue":
-            transformed_value = nmdc.TimestampValue(has_raw_value=value)
+            transformed_value = nmdc.TimestampValue(
+                has_raw_value=value,
+                type="nmdc:TimestampValue",
+            )
         elif slot.range == "GeolocationValue":
             transformed_value = self._get_geolocation_value(value)
         elif slot.range == "float":
@@ -531,9 +557,12 @@ class SubmissionPortalTranslator(Translator):
         biosample_key = sample_data[0].get(BIOSAMPLE_UNIQUE_KEY_SLOT, "").strip()
         slots = {
             "id": nmdc_biosample_id,
-            "part_of": nmdc_study_id,
+            "associated_studies": [nmdc_study_id],
+            "type": "nmdc:Biosample",
             "name": sample_data[0].get("samp_name", "").strip(),
-            "env_package": nmdc.TextValue(has_raw_value=default_env_package),
+            "env_package": nmdc.TextValue(
+                has_raw_value=default_env_package, type="nmdc:TextValue"
+            ),
         }
         for tab in sample_data:
             transformed_tab = self._transform_dict_for_class(tab, "Biosample")
@@ -590,18 +619,18 @@ class SubmissionPortalTranslator(Translator):
             if sample_data
         ]
 
-        if self.omics_processing_mapping:
-            # If there is data from an OmicsProcessing mapping file, process it now. This part
+        if self.nucleotide_sequencing_mapping:
+            # If there is data from an NucleotideSequencing mapping file, process it now. This part
             # assumes that there is a column in that file with the header __biosample_samp_name
             # that can be used to join with the sample data from the submission portal. The
             # biosample identified by that `samp_name` will be referenced in the `has_input`
-            # slot of the OmicsProcessing object. If a DataObject mapping file was also provided,
-            # those objects will also be generated and referenced in the `has_output` slot of the
-            # OmicsProcessing object. By keying off of the `samp_name` slot of the submission's
-            # sample data there is an implicit 1:1 relationship between Biosample objects and
-            # OmicsProcessing objects generated here.
+            # slot of the NucleotideSequencing object. If a DataObject mapping file was also
+            # provided, those objects will also be generated and referenced in the `has_output` slot
+            # of the NucleotideSequencing object. By keying off of the `samp_name` slot of the
+            # submission's sample data there is an implicit 1:1 relationship between Biosample
+            # objects and NucleotideSequencing objects generated here.
             join_key = f"__biosample_{BIOSAMPLE_UNIQUE_KEY_SLOT}"
-            database.omics_processing_set = []
+            database.data_generation_set = []
             database.data_object_set = []
             data_objects_by_sample_data_id = {}
             today = datetime.now().strftime("%Y-%m-%d")
@@ -617,10 +646,10 @@ class SubmissionPortalTranslator(Translator):
                     grouped,
                 )
 
-            for omics_processing_row in self.omics_processing_mapping:
-                # For each row in the OmicsProcessing mapping file, first grab the minted Biosample
-                # id that corresponds to the sample ID from the submission
-                sample_data_id = omics_processing_row.pop(join_key)
+            for nucleotide_sequencing_row in self.nucleotide_sequencing_mapping:
+                # For each row in the NucleotideSequencing mapping file, first grab the minted
+                # Biosample id that corresponds to the sample ID from the submission
+                sample_data_id = nucleotide_sequencing_row.pop(join_key)
                 if (
                     not sample_data_id
                     or sample_data_id not in sample_data_to_nmdc_biosample_ids
@@ -631,31 +660,33 @@ class SubmissionPortalTranslator(Translator):
                     continue
                 nmdc_biosample_id = sample_data_to_nmdc_biosample_ids[sample_data_id]
 
-                # Transform the raw row data according to the OmicsProcessing class's slots, and
-                # generate an instance. A few key slots do not come from the mapping file, but
+                # Transform the raw row data according to the NucleotideSequencing class's slots,
+                # and generate an instance. A few key slots do not come from the mapping file, but
                 # instead are defined here.
-                omics_processing_slots = {
-                    "id": self._id_minter("nmdc:OmicsProcessing", 1)[0],
+                nucleotide_sequencing_slots = {
+                    "id": self._id_minter("nmdc:NucleotideSequencing", 1)[0],
                     "has_input": [nmdc_biosample_id],
                     "has_output": [],
-                    "part_of": nmdc_study_id,
+                    "associated_studies": [nmdc_study_id],
                     "add_date": today,
                     "mod_date": today,
-                    "type": "nmdc:OmicsProcessing",
+                    "type": "nmdc:NucleotideSequencing",
                 }
-                omics_processing_slots.update(
+                nucleotide_sequencing_slots.update(
                     self._transform_dict_for_class(
-                        omics_processing_row, "OmicsProcessing"
+                        nucleotide_sequencing_row, "NucleotideSequencing"
                     )
                 )
-                omics_processing = nmdc.OmicsProcessing(**omics_processing_slots)
+                nucleotide_sequencing = nmdc.NucleotideSequencing(
+                    **nucleotide_sequencing_slots
+                )
 
                 for data_object_row in data_objects_by_sample_data_id.get(
                     sample_data_id, []
                 ):
                     # For each row in the DataObject mapping file that corresponds to the sample ID,
                     # transform the raw row data according to the DataObject class's slots, generate
-                    # an instance, and connect that instance's minted ID to the OmicsProcessing
+                    # an instance, and connect that instance's minted ID to the NucleotideSequencing
                     # instance
                     data_object_id = self._id_minter("nmdc:DataObject", 1)[0]
                     data_object_slots = {
@@ -667,10 +698,10 @@ class SubmissionPortalTranslator(Translator):
                     )
                     data_object = nmdc.DataObject(**data_object_slots)
 
-                    omics_processing.has_output.append(data_object_id)
+                    nucleotide_sequencing.has_output.append(data_object_id)
 
                     database.data_object_set.append(data_object)
 
-                database.omics_processing_set.append(omics_processing)
+                database.data_generation_set.append(nucleotide_sequencing)
 
         return database

{nmdc_runtime-1.10.0.dist-info → nmdc_runtime-2.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nmdc_runtime
-Version: 1.10.0
+Version: 2.0.0
 Summary: A runtime system for NMDC data management and orchestration
 Home-page: https://github.com/microbiomedata/nmdc-runtime
 Author: Donny Winston

{nmdc_runtime-1.10.0.dist-info → nmdc_runtime-2.0.0.dist-info}/RECORD

@@ -28,7 +28,7 @@ nmdc_runtime/lib/nmdc_etl_class.py,sha256=tVh3rKVMkBHQE65_LhKeIjCsaCZQk_HJzbc9K4
 nmdc_runtime/lib/transform_nmdc_data.py,sha256=hij4lR3IMQRJQdL-rsP_I-m_WyFPsBMchV2MNFUkh0M,39906
 nmdc_runtime/minter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/minter/bootstrap.py,sha256=5Ej6pJVBRryRIi0ZwEloY78Zky7iE2okF6tPwRI2axM,822
-nmdc_runtime/minter/config.py,sha256=mq_s0xjLZK-zwjwk3IGgnk9ZIvvejyyZ7_qZkLt3V-c,1409
+nmdc_runtime/minter/config.py,sha256=WrxX9WmyN7Ft4INRAQbd31jmlm5qwaDDaNS9AktieYA,4112
 nmdc_runtime/minter/adapters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/minter/adapters/repository.py,sha256=I-jmGP38-9kPhkogrwUht_Ir0CfHA9_5ZImw5I_wbcw,8323
 nmdc_runtime/minter/domain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -36,9 +36,9 @@ nmdc_runtime/minter/domain/model.py,sha256=WMOuKub3dVzkOt_EZSRDLeTsJPqFbKx01SMQ5
 nmdc_runtime/minter/entrypoints/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/minter/entrypoints/fastapi_app.py,sha256=JC4thvzfFwRc1mhWQ-kHy3yvs0SYxF6ktE7LXNCwqlI,4031
 nmdc_runtime/site/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/site/graphs.py,sha256=jqfwhrCVUBszt9168au_DVvZBtgIfpUf1OXFiyPHI6U,12304
-nmdc_runtime/site/ops.py,sha256=Rey3H7q7hITI4xsXZ-rWNSGWgtt-65WAVCo4GLqLn3U,39826
-nmdc_runtime/site/repository.py,sha256=ge3LW_5izCgL6x1Ios8z2Hrt--aY6LXqhGjnAjcIJkI,37422
+nmdc_runtime/site/graphs.py,sha256=ZHglSPwVHfXzdgR2CGvmbzLLbmsijloU58XvIe9Thjs,13996
+nmdc_runtime/site/ops.py,sha256=EOR4VjRoFoaI2odKRgcgtGxngPsx2U0H45zzWrvQzf8,44603
+nmdc_runtime/site/repository.py,sha256=rDtwUjozhyOxlkuF9HvaheOQDQWkgZYqVtsB50BcUp4,39121
 nmdc_runtime/site/resources.py,sha256=ZSH1yvA-li0R7Abc22_v0XLbjBYf5igETr2G01J3hnc,17557
 nmdc_runtime/site/util.py,sha256=zAY0oIY7GRf63ecqWelmS27N7PVrAXVwEhtnpescBSw,1415
 nmdc_runtime/site/backup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -51,21 +51,21 @@ nmdc_runtime/site/drsobjects/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NM
 nmdc_runtime/site/drsobjects/ingest.py,sha256=pcMP69WSzFHFqHB9JIL55ePFhilnCLRc2XHCQ97w1Ik,3107
 nmdc_runtime/site/drsobjects/registration.py,sha256=D1T3QUuxEOxqKZIvB5rkb_6ZxFZiA-U9SMPajyeWC2Y,3572
 nmdc_runtime/site/export/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/site/export/ncbi_xml.py,sha256=KMKHZJEjTGECI2N2Hp0yDSMGrkjEC7GmlOnptaZCy2E,22297
-nmdc_runtime/site/export/ncbi_xml_utils.py,sha256=jY4YJt5P7EMsy8gSOPI33K6VcEfOXaVR_zQINZOBUKU,7561
-nmdc_runtime/site/export/study_metadata.py,sha256=WRU0F1ksWfNX3k9LD91Pn2DuLA-IOpGvYPJd6DnguEs,4819
+nmdc_runtime/site/export/ncbi_xml.py,sha256=bfGnvFO7jQmlNAdzXpQiNBw7DGvWQ3pTPfgbhczb_kM,22561
+nmdc_runtime/site/export/ncbi_xml_utils.py,sha256=71LSFIYioF61xalKgsQ_Po63322dNbfQfYzqo2hZ720,7575
+nmdc_runtime/site/export/study_metadata.py,sha256=yR5pXL6JG8d7cAtqcF-60Hp7bLD3dJ0Rut4AtYc0tXA,4844
 nmdc_runtime/site/normalization/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/site/normalization/gold.py,sha256=iISDD4qs4d6uLhv631WYNeQVOzY5DO201ZpPtxHdkVk,1311
 nmdc_runtime/site/translation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/site/translation/emsl.py,sha256=-aCTJTSCNaK-Koh8BE_4fTf5nyxP1KkquR6lloLEJl0,1245
 nmdc_runtime/site/translation/gold.py,sha256=R3W99sdQb7Pgu_esN7ruIC-tyREQD_idJ4xCzkqWuGw,1622
-nmdc_runtime/site/translation/gold_translator.py,sha256=8i5FxrgAG4rLbM0mcCSBaZEzyReht6xwmpm4xeX4HwI,26451
+nmdc_runtime/site/translation/gold_translator.py,sha256=ln0BXI2v7pTgui3uNbl8tU1iOkfDZH4Z8SCaFLuuTI8,29438
 nmdc_runtime/site/translation/jgi.py,sha256=qk878KhIw674TkrVfbl2x1QJrKi3zlvE0vesIpe9slM,876
-nmdc_runtime/site/translation/neon_benthic_translator.py,sha256=p91B5o0MkSGaDDZw2jGQoYfJBqVc6pW7k7l7_0aQIaA,22992
-nmdc_runtime/site/translation/neon_soil_translator.py,sha256=Rc2KptRHORY-MZuNYMNtTTmHKD0c0sUMfMxYylLTJn4,37557
-nmdc_runtime/site/translation/neon_surface_water_translator.py,sha256=6LaFwBnVx6TN9v1D-G6LFrDxY0TK05AvMklx0E1tTeQ,26590
-nmdc_runtime/site/translation/neon_utils.py,sha256=mdxJVPb3zbD4DiKW3Fwgk22kjczKMwkcozvy7fwteTE,5203
-nmdc_runtime/site/translation/submission_portal_translator.py,sha256=aNGIXTiJEXGC_29qWeol2C426bAt5VlY3In_YhplPU0,28169
+nmdc_runtime/site/translation/neon_benthic_translator.py,sha256=QIDqYLuf-NlGY9_88gy_5qTswkei3OfgJ5AOFpEXzJo,23985
+nmdc_runtime/site/translation/neon_soil_translator.py,sha256=Rol0g67nVBGSBySUzpfdW4Fwes7bKtvnlv2g5cB0aTI,38550
+nmdc_runtime/site/translation/neon_surface_water_translator.py,sha256=MQgjIfWPgoRe-bhzyfqHSe2mZwFsjcwjdT8tNqpIhlc,27729
+nmdc_runtime/site/translation/neon_utils.py,sha256=d00o7duKKugpLHmsEifNbp4WjeC4GOqcgw0b5qlCg4I,5549
+nmdc_runtime/site/translation/submission_portal_translator.py,sha256=6QkEfz-RN8y_aHckUWLUuQz3DslbvFck2Vyu7funHrQ,29152
 nmdc_runtime/site/translation/translator.py,sha256=xM9dM-nTgSWwu5HFoUVNHf8kqk9iiH4PgWdSx4OKxEk,601
 nmdc_runtime/site/translation/util.py,sha256=w_l3SiExGsl6cXRqto0a_ssDmHkP64ITvrOVfPxmNpY,4366
 nmdc_runtime/site/validation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -73,9 +73,9 @@ nmdc_runtime/site/validation/emsl.py,sha256=OG20mv_3E2rkQqTQtYO0_SVRqFb-Z_zKCiAV
 nmdc_runtime/site/validation/gold.py,sha256=Z5ZzYdjERbrJ2Tu06d0TDTBSfwaFdL1Z23Rl-YkZ2Ow,803
 nmdc_runtime/site/validation/jgi.py,sha256=LdJfhqBVHWCDp0Kzyk8eJZMwEI5NQ-zuTda31BcGwOA,1299
 nmdc_runtime/site/validation/util.py,sha256=GGbMDSwR090sr_E_fHffCN418gpYESaiot6XghS7OYk,3349
-nmdc_runtime-1.10.0.dist-info/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
-nmdc_runtime-1.10.0.dist-info/METADATA,sha256=17FQCxBZadSi9xVhFWBaBhRkCEOSsKMQQmM6A_Av1DQ,7303
-nmdc_runtime-1.10.0.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-nmdc_runtime-1.10.0.dist-info/entry_points.txt,sha256=JxdvOnvxHK_8046cwlvE30s_fV0-k-eTpQtkKYA69nQ,224
-nmdc_runtime-1.10.0.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
-nmdc_runtime-1.10.0.dist-info/RECORD,,
+nmdc_runtime-2.0.0.dist-info/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
+nmdc_runtime-2.0.0.dist-info/METADATA,sha256=e8uam0Dfv0ljsbuFsh-y56HIKpdw0BuQqtG6cJAIus8,7302
+nmdc_runtime-2.0.0.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+nmdc_runtime-2.0.0.dist-info/entry_points.txt,sha256=JxdvOnvxHK_8046cwlvE30s_fV0-k-eTpQtkKYA69nQ,224
+nmdc_runtime-2.0.0.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
+nmdc_runtime-2.0.0.dist-info/RECORD,,