nmdc-runtime 2.4.0__py3-none-any.whl → 2.5.0__py3-none-any.whl

nmdc_runtime/site/ops.py

@@ -1100,7 +1100,12 @@ def materialize_alldocs(context) -> int:
         write_operations = []
         documents_processed_counter = 0
         for doc in mdb[coll_name].find():
-            doc_type = doc["type"][5:]  # lop off "nmdc:" prefix
+            try:
+                doc_type = doc["type"][5:]  # lop off "nmdc:" prefix
+            except KeyError:
+                raise Exception(
+                    f"doc {doc['id']} in collection {coll_name} has no 'type'!"
+                )
             slots_to_include = ["id", "type"] + document_reference_ranged_slots[
                 doc_type
             ]

nmdc_runtime/site/repair/database_updater.py

@@ -199,8 +199,20 @@ class DatabaseUpdater:
             if gbs.get("biosampleGoldId") not in nmdc_gold_ids
         ]
 
+        # use the GOLD study id to fetch all sequencing project records associated with the study
+        gold_sequencing_projects_for_study = (
+            self.gold_api_client.fetch_projects_by_study(gold_study_id)
+        )
+
+        # use the GOLD study id to fetch all analysis project records associated with the study
+        gold_analysis_projects_for_study = (
+            self.gold_api_client.fetch_analysis_projects_by_study(gold_study_id)
+        )
+
         gold_study_translator = GoldStudyTranslator(
             biosamples=missing_gold_biosamples,
+            projects=gold_sequencing_projects_for_study,
+            analysis_projects=gold_analysis_projects_for_study,
             gold_nmdc_instrument_map_df=self.gold_nmdc_instrument_map_df,
         )
 

nmdc_runtime/site/repository.py

@@ -744,7 +744,7 @@ def biosample_submission_ingest():
                         "config": {
                             "benthic_data_product": {
                                 "product_id": "DP1.20279.001",
-                                "product_tables": "mms_benthicMetagenomeSequencing, mms_benthicMetagenomeDnaExtraction, mms_benthicRawDataFiles, amb_fieldParent",
+                                "product_tables": "mms_benthicMetagenomeSequencing, mms_benthicMetagenomeDnaExtraction, mms_benthicRawDataFiles, amb_fieldParent, mms_mms_benthicRawDataFiles",
                             }
                         }
                     },
@@ -771,7 +771,7 @@ def biosample_submission_ingest():
                         "config": {
                             "benthic_data_product": {
                                 "product_id": "DP1.20279.001",
-                                "product_tables": "mms_benthicMetagenomeSequencing, mms_benthicMetagenomeDnaExtraction, mms_benthicRawDataFiles, amb_fieldParent",
+                                "product_tables": "mms_benthicMetagenomeSequencing, mms_benthicMetagenomeDnaExtraction, mms_benthicRawDataFiles, amb_fieldParent, mms_mms_benthicRawDataFiles",
                             }
                         }
                     },

nmdc_runtime/site/translation/neon_benthic_translator.py

@@ -1,6 +1,6 @@
 import re
 import sqlite3
-from typing import Union
+from typing import Optional, Union
 
 import pandas as pd
 import requests_cache
@@ -61,6 +61,7 @@ class NeonBenthicDataTranslator(Translator):
             "mms_benthicMetagenomeSequencing",
             "mms_benthicMetagenomeDnaExtraction",
             "amb_fieldParent",
+            "mms_benthicRawDataFiles",  # <--- ensure this is present
         )
 
         if all(k in benthic_data for k in neon_amb_data_tables):
@@ -79,6 +80,12 @@ class NeonBenthicDataTranslator(Translator):
             benthic_data["amb_fieldParent"].to_sql(
                 "amb_fieldParent", self.conn, if_exists="replace", index=False
             )
+            benthic_data["mms_benthicRawDataFiles"].to_sql(
+                "mms_benthicRawDataFiles",
+                self.conn,
+                if_exists="replace",
+                index=False,
+            )
         else:
             raise ValueError(
                 f"You are missing one of the aquatic benthic microbiome tables: {neon_amb_data_tables}"
@@ -88,14 +95,19 @@ class NeonBenthicDataTranslator(Translator):
             "neonEnvoTerms", self.conn, if_exists="replace", index=False
         )
 
-        self.neon_raw_data_file_mappings_df = neon_raw_data_file_mappings_file
-        self.neon_raw_data_file_mappings_df.to_sql(
-            "neonRawDataFile", self.conn, if_exists="replace", index=False
-        )
+        self.neon_raw_data_file_mappings_df = benthic_data["mms_benthicRawDataFiles"]
 
         self.site_code_mapping = site_code_mapping
+
         self.neon_nmdc_instrument_map_df = neon_nmdc_instrument_map_df
 
+    def _translate_manifest(self, manifest_id: str) -> nmdc.Manifest:
+        return nmdc.Manifest(
+            id=manifest_id,
+            manifest_category=nmdc.ManifestCategoryEnum.poolable_replicates,
+            type="nmdc:Manifest",
+        )
+
     def _translate_biosample(
         self, neon_id: str, nmdc_id: str, biosample_row: pd.DataFrame
     ) -> nmdc.Biosample:
@@ -313,7 +325,7 @@ class NeonBenthicDataTranslator(Translator):
         )
 
     def _translate_data_object(
-        self, do_id: str, url: str, do_type: str, checksum: str
+        self, do_id: str, url: str, do_type: str, manifest_id: str
     ) -> nmdc.DataObject:
         """Create nmdc DataObject which is the output of a NucleotideSequencing process. This
         object mainly contains information about the sequencing file that was generated as
@@ -324,7 +336,6 @@ class NeonBenthicDataTranslator(Translator):
         :param url: URL of zipped FASTQ file on NEON file server. Retrieved from file provided
         by Hugh Cross at NEON.
         :param do_type: Indicate whether it is FASTQ for Read 1 or Read 2 (paired end sequencing).
-        :param checksum: Checksum value for FASTQ in zip file, once again provided by Hugh Cross
         at NEON.
         :return: DataObject with all the sequencing file metadata.
         """
@@ -337,14 +348,14 @@ class NeonBenthicDataTranslator(Translator):
             url=url,
             description=f"sequencing results for {basename}",
             type="nmdc:DataObject",
-            md5_checksum=checksum,
             data_object_type=do_type,
+            in_manifest=manifest_id,
         )
 
-    def get_database(self):
+    def get_database(self) -> nmdc.Database:
         database = nmdc.Database()
 
-        query = """
+        join_query = """
             SELECT
                 merged.laboratoryName,
                 merged.sequencingFacilityID,
@@ -372,202 +383,190 @@ class NeonBenthicDataTranslator(Translator):
                 afp.siteID,
                 afp.sampleID,
                 afp.collectDate
-            FROM 
-                (
-                    SELECT
-                        bs.collectDate,
-                        bs.laboratoryName,
-                        bs.sequencingFacilityID,
-                        bs.processedDate,
-                        bs.dnaSampleID,
-                        bs.dnaSampleCode,
-                        bs.internalLabID,
-                        bs.instrument_model,
-                        bs.sequencingMethod,
-                        bs.investigation_type,
-                        bs.qaqcStatus,
-                        bs.ncbiProjectID,
-                        bd.genomicsSampleID,
-                        bd.sequenceAnalysisType,
-                        bd.sampleMass,
-                        bd.nucleicAcidConcentration
-                    FROM 
-                        mms_benthicMetagenomeSequencing AS bs
-                    JOIN 
-                        mms_benthicMetagenomeDnaExtraction AS bd
-                    ON 
-                        bs.dnaSampleID = bd.dnaSampleID
-                ) AS merged
+            FROM (
+                SELECT
+                    bs.collectDate,
+                    bs.laboratoryName,
+                    bs.sequencingFacilityID,
+                    bs.processedDate,
+                    bs.dnaSampleID,
+                    bs.dnaSampleCode,
+                    bs.internalLabID,
+                    bs.instrument_model,
+                    bs.sequencingMethod,
+                    bs.investigation_type,
+                    bs.qaqcStatus,
+                    bs.ncbiProjectID,
+                    bd.genomicsSampleID,
+                    bd.sequenceAnalysisType,
+                    bd.sampleMass,
+                    bd.nucleicAcidConcentration
+                FROM mms_benthicMetagenomeSequencing AS bs
+                JOIN mms_benthicMetagenomeDnaExtraction AS bd
+                ON bs.dnaSampleID = bd.dnaSampleID
+            ) AS merged
             LEFT JOIN amb_fieldParent AS afp
-            ON
-                merged.genomicsSampleID = afp.geneticSampleID
+            ON merged.genomicsSampleID = afp.geneticSampleID
         """
-        benthic_samples = pd.read_sql_query(query, self.conn)
+        benthic_samples = pd.read_sql_query(join_query, self.conn)
         benthic_samples.to_sql(
             "benthicSamples", self.conn, if_exists="replace", index=False
         )
 
-        neon_biosample_ids = benthic_samples["sampleID"]
-        nmdc_biosample_ids = self._id_minter("nmdc:Biosample", len(neon_biosample_ids))
-        neon_to_nmdc_biosample_ids = dict(zip(neon_biosample_ids, nmdc_biosample_ids))
+        sample_ids = benthic_samples["sampleID"]
+        nmdc_biosample_ids = self._id_minter("nmdc:Biosample", len(sample_ids))
+        neon_to_nmdc_biosample_ids = dict(zip(sample_ids, nmdc_biosample_ids))
 
-        neon_extraction_ids = benthic_samples["sampleID"]
-        nmdc_extraction_ids = self._id_minter(
-            "nmdc:Extraction", len(neon_extraction_ids)
-        )
-        neon_to_nmdc_extraction_ids = dict(
-            zip(neon_extraction_ids, nmdc_extraction_ids)
-        )
+        nmdc_extraction_ids = self._id_minter("nmdc:Extraction", len(sample_ids))
+        neon_to_nmdc_extraction_ids = dict(zip(sample_ids, nmdc_extraction_ids))
 
-        neon_extraction_processed_ids = benthic_samples["sampleID"]
         nmdc_extraction_processed_ids = self._id_minter(
-            "nmdc:ProcessedSample", len(neon_extraction_processed_ids)
+            "nmdc:ProcessedSample", len(sample_ids)
         )
         neon_to_nmdc_extraction_processed_ids = dict(
-            zip(neon_extraction_processed_ids, nmdc_extraction_processed_ids)
+            zip(sample_ids, nmdc_extraction_processed_ids)
         )
 
-        neon_lib_prep_ids = benthic_samples["sampleID"]
-        nmdc_lib_prep_ids = self._id_minter(
-            "nmdc:LibraryPreparation", len(neon_lib_prep_ids)
-        )
-        neon_to_nmdc_lib_prep_ids = dict(zip(neon_lib_prep_ids, nmdc_lib_prep_ids))
+        nmdc_libprep_ids = self._id_minter("nmdc:LibraryPreparation", len(sample_ids))
+        neon_to_nmdc_libprep_ids = dict(zip(sample_ids, nmdc_libprep_ids))
 
-        neon_lib_prep_processed_ids = benthic_samples["sampleID"]
-        nmdc_lib_prep_processed_ids = self._id_minter(
-            "nmdc:ProcessedSample", len(neon_lib_prep_processed_ids)
+        nmdc_libprep_processed_ids = self._id_minter(
+            "nmdc:ProcessedSample", len(sample_ids)
         )
-        neon_to_nmdc_lib_prep_processed_ids = dict(
-            zip(neon_lib_prep_processed_ids, nmdc_lib_prep_processed_ids)
+        neon_to_nmdc_libprep_processed_ids = dict(
+            zip(sample_ids, nmdc_libprep_processed_ids)
         )
 
-        neon_omprc_ids = benthic_samples["sampleID"]
-        nmdc_omprc_ids = self._id_minter(
-            "nmdc:NucleotideSequencing", len(neon_omprc_ids)
-        )
-        neon_to_nmdc_omprc_ids = dict(zip(neon_omprc_ids, nmdc_omprc_ids))
+        nmdc_ntseq_ids = self._id_minter("nmdc:NucleotideSequencing", len(sample_ids))
+        neon_to_nmdc_ntseq_ids = dict(zip(sample_ids, nmdc_ntseq_ids))
 
-        neon_raw_data_file_mappings_df = self.neon_raw_data_file_mappings_df
-        neon_raw_file_paths = neon_raw_data_file_mappings_df["rawDataFilePath"]
-        nmdc_data_object_ids = self._id_minter(
-            "nmdc:DataObject", len(neon_raw_file_paths)
-        )
-        neon_to_nmdc_data_object_ids = dict(
-            zip(neon_raw_file_paths, nmdc_data_object_ids)
-        )
+        raw_df = self.neon_raw_data_file_mappings_df
+        raw_file_paths = raw_df["rawDataFilePath"]
+        dataobject_ids = self._id_minter("nmdc:DataObject", len(raw_file_paths))
+        neon_to_nmdc_dataobject_ids = dict(zip(raw_file_paths, dataobject_ids))
 
-        for neon_id, nmdc_id in neon_to_nmdc_biosample_ids.items():
-            biosample_row = benthic_samples[benthic_samples["sampleID"] == neon_id]
+        for neon_id, biosample_id in neon_to_nmdc_biosample_ids.items():
+            row = benthic_samples[benthic_samples["sampleID"] == neon_id]
+            if row.empty:
+                continue
 
+            # Example of how you might call _translate_biosample:
             database.biosample_set.append(
-                self._translate_biosample(neon_id, nmdc_id, biosample_row)
+                self._translate_biosample(neon_id, biosample_id, row)
             )
 
-        for neon_id, nmdc_id in neon_to_nmdc_extraction_ids.items():
-            extraction_row = benthic_samples[benthic_samples["sampleID"] == neon_id]
+        for neon_id, extraction_id in neon_to_nmdc_extraction_ids.items():
+            row = benthic_samples[benthic_samples["sampleID"] == neon_id]
+            if row.empty:
+                continue
 
-            extraction_input = neon_to_nmdc_biosample_ids.get(neon_id)
-            processed_sample_id = neon_to_nmdc_extraction_processed_ids.get(neon_id)
+            biosample_id = neon_to_nmdc_biosample_ids.get(neon_id)
+            extraction_ps_id = neon_to_nmdc_extraction_processed_ids.get(neon_id)
 
-            if extraction_input is not None and processed_sample_id is not None:
+            if biosample_id and extraction_ps_id:
                 database.material_processing_set.append(
                     self._translate_extraction_process(
-                        nmdc_id,
-                        extraction_input,
-                        processed_sample_id,
-                        extraction_row,
+                        extraction_id, biosample_id, extraction_ps_id, row
                     )
                 )
-
-                genomics_sample_id = _get_value_or_none(
-                    extraction_row, "genomicsSampleID"
-                )
-
+                genomics_sample_id = _get_value_or_none(row, "genomicsSampleID")
                 database.processed_sample_set.append(
                     self._translate_processed_sample(
-                        processed_sample_id,
+                        extraction_ps_id,
                         f"Extracted DNA from {genomics_sample_id}",
                     )
                 )
 
-        query = """
+        query2 = """
             SELECT dnaSampleID, GROUP_CONCAT(rawDataFilePath, '|') AS rawDataFilePaths
-            FROM neonRawDataFile
+            FROM mms_benthicRawDataFiles
             GROUP BY dnaSampleID
         """
-        neon_raw_data_files = pd.read_sql_query(query, self.conn)
-        neon_raw_data_files_dict = (
-            neon_raw_data_files.set_index("dnaSampleID")["rawDataFilePaths"]
+        raw_data_files_df = pd.read_sql_query(query2, self.conn)
+        dna_files_dict = (
+            raw_data_files_df.set_index("dnaSampleID")["rawDataFilePaths"]
             .str.split("|")
             .to_dict()
         )
-        filtered_neon_raw_data_files_dict = {
-            key: value
-            for key, value in neon_raw_data_files_dict.items()
-            if len(value) <= 2
-        }
 
-        for neon_id, nmdc_id in neon_to_nmdc_lib_prep_ids.items():
-            lib_prep_row = benthic_samples[benthic_samples["sampleID"] == neon_id]
+        dna_sample_to_manifest_id: dict[str, str] = {}
 
-            lib_prep_input = neon_to_nmdc_extraction_processed_ids.get(neon_id)
-            processed_sample_id = neon_to_nmdc_lib_prep_processed_ids.get(neon_id)
+        for neon_id, libprep_id in neon_to_nmdc_libprep_ids.items():
+            row = benthic_samples[benthic_samples["sampleID"] == neon_id]
+            if row.empty:
+                continue
 
-            if lib_prep_input is not None and processed_sample_id is not None:
-                database.material_processing_set.append(
-                    self._translate_library_preparation(
-                        nmdc_id,
-                        lib_prep_input,
-                        processed_sample_id,
-                        lib_prep_row,
-                    )
+            extr_ps_id = neon_to_nmdc_extraction_processed_ids.get(neon_id)
+            libprep_ps_id = neon_to_nmdc_libprep_processed_ids.get(neon_id)
+            if not extr_ps_id or not libprep_ps_id:
+                continue
+
+            database.material_processing_set.append(
+                self._translate_library_preparation(
+                    libprep_id, extr_ps_id, libprep_ps_id, row
                 )
+            )
 
-                dna_sample_id = _get_value_or_none(lib_prep_row, "dnaSampleID")
+            dna_sample_id = _get_value_or_none(row, "dnaSampleID")
+            database.processed_sample_set.append(
+                self._translate_processed_sample(
+                    libprep_ps_id,
+                    f"Library preparation for {dna_sample_id}",
+                )
+            )
 
-                database.processed_sample_set.append(
-                    self._translate_processed_sample(
-                        processed_sample_id,
-                        f"Library preparation for {dna_sample_id}",
+            filepaths_for_dna: list[str] = dna_files_dict.get(dna_sample_id, [])
+            if not filepaths_for_dna:
+                # no raw files => skip
+                ntseq_id = neon_to_nmdc_ntseq_ids.get(neon_id)
+                if ntseq_id:
+                    continue
+                continue
+
+            # If multiple => we create a Manifest
+            manifest_id: Optional[str] = None
+            if len(filepaths_for_dna) > 2:
+                if dna_sample_id not in dna_sample_to_manifest_id:
+                    new_man_id = self._id_minter("nmdc:Manifest", 1)[0]
+                    dna_sample_to_manifest_id[dna_sample_id] = new_man_id
+                    database.manifest_set.append(self._translate_manifest(new_man_id))
+                manifest_id = dna_sample_to_manifest_id[dna_sample_id]
+
+            has_input_value = self.samp_procsm_dict.get(neon_id)
+            if not has_input_value:
+                continue
+
+            dataobject_ids_for_run: list[str] = []
+            for fp in filepaths_for_dna:
+                if fp not in neon_to_nmdc_dataobject_ids:
+                    continue
+                do_id = neon_to_nmdc_dataobject_ids[fp]
+
+                do_type = None
+                if "_R1.fastq.gz" in fp:
+                    do_type = "Metagenome Raw Read 1"
+                elif "_R2.fastq.gz" in fp:
+                    do_type = "Metagenome Raw Read 2"
+
+                database.data_object_set.append(
+                    self._translate_data_object(
+                        do_id=do_id,
+                        url=fp,
+                        do_type=do_type,
+                        manifest_id=manifest_id,
                     )
                 )
-
-                has_output = None
-                has_output_do_ids = []
-
-                if dna_sample_id in filtered_neon_raw_data_files_dict:
-                    has_output = filtered_neon_raw_data_files_dict[dna_sample_id]
-                    for item in has_output:
-                        if item in neon_to_nmdc_data_object_ids:
-                            has_output_do_ids.append(neon_to_nmdc_data_object_ids[item])
-
-                        checksum = None
-                        do_type = None
-
-                        checksum = neon_raw_data_file_mappings_df[
-                            neon_raw_data_file_mappings_df["rawDataFilePath"] == item
-                        ]["checkSum"].values[0]
-                        if "_R1.fastq.gz" in item:
-                            do_type = "Metagenome Raw Read 1"
-                        elif "_R2.fastq.gz" in item:
-                            do_type = "Metagenome Raw Read 2"
-
-                        database.data_object_set.append(
-                            self._translate_data_object(
-                                neon_to_nmdc_data_object_ids.get(item),
-                                item,
-                                do_type,
-                                checksum,
-                            )
-                        )
-
-                    database.data_generation_set.append(
-                        self._translate_nucleotide_sequencing(
-                            neon_to_nmdc_omprc_ids.get(neon_id),
-                            processed_sample_id,
-                            has_output_do_ids,
-                            lib_prep_row,
-                        )
+                dataobject_ids_for_run.append(do_id)
+
+            ntseq_id = neon_to_nmdc_ntseq_ids.get(neon_id)
+            if ntseq_id:
+                database.data_generation_set.append(
+                    self._translate_nucleotide_sequencing(
+                        ntseq_id,
+                        has_input_value,  # <--- from self.samp_procsm_dict
+                        dataobject_ids_for_run,
+                        row,
                     )
+                )
 
         return database

{nmdc_runtime-2.4.0.dist-info → nmdc_runtime-2.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: nmdc_runtime
-Version: 2.4.0
+Version: 2.5.0
 Summary: A runtime system for NMDC data management and orchestration
 Home-page: https://github.com/microbiomedata/nmdc-runtime
 Author: Donny Winston
@@ -17,6 +17,7 @@ Dynamic: classifier
 Dynamic: description
 Dynamic: description-content-type
 Dynamic: home-page
+Dynamic: license-file
 Dynamic: requires-python
 Dynamic: summary
 
@@ -37,8 +38,7 @@ houses the LinkML schema specification, as well as generated artifacts (e.g. JSO
 * [nmdc-server](https://github.com/microbiomedata/nmdc-server)
 houses code specific to the data portal -- its database, back-end API, and front-end application.
 
-* [workflow_documentation](https://docs.microbiomedata.org/workflows/)
-references workflow code spread across several repositories, that take source data and produce computed data.
+* Workflows — documented in the [workflows](https://docs.microbiomedata.org/workflows/) section of the NMDC documentation website — take source data and produce computed data.
 
 * This repo (nmdc-runtime)
    * houses code that takes source data and computed data, and transforms it
@@ -156,6 +156,9 @@ Tests can be found in `tests` and are run with the following commands:
 ```bash
 make up-test
 make test
+
+# Run a Specific test file eg. tests/test_api/test_endpoints.py
+make test ARGS="tests/test_api/test_endpoints.py"
 ```
 
 As you create Dagster solids and pipelines, add tests in `tests/` to check that your code behaves as
@@ -164,6 +167,16 @@ desired and does not break over time.
 [For hints on how to write tests for solids and pipelines in Dagster, see their documentation
 tutorial on Testing](https://docs.dagster.io/tutorial/testable).
 
+### RAM usage
+
+The `dagster-daemon` and `dagster-dagit` containers can consume a lot of RAM. If tests are failing and the console of
+the `test` container shows "Error 137," here is something you can try as a workaround: In Docker Desktop, go to 
+"Settings > Resources > Advanced," and increase the memory limit. One of our team members has
+found **12 GB** to be sufficient for running the tests.
+
+> Dedicating 12 GB of RAM to Docker may be prohibitive for some prospective developers.
+> There is an open [issue](https://github.com/microbiomedata/nmdc-runtime/issues/928) about the memory requirement.
+
 ## Publish to PyPI
 
 This repository contains a GitHub Actions workflow that publishes a Python package to [PyPI](https://pypi.org/project/nmdc-runtime/).

{nmdc_runtime-2.4.0.dist-info → nmdc_runtime-2.5.0.dist-info}/RECORD

@@ -37,8 +37,8 @@ nmdc_runtime/minter/entrypoints/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm
 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=SA4Ibb1TenVgiYD4wNrMiOCwkMKrv6BTcQ8mbG4VXPs,15666
-nmdc_runtime/site/ops.py,sha256=p4F5SrDbFdKOrAHu1TUhWQA33QB7hdoQmCCuU-00Eqo,46445
-nmdc_runtime/site/repository.py,sha256=pfx7WAVgdNaPhtfF2pak-tllqPMf4-yUeOXSpr4hu30,43861
+nmdc_runtime/site/ops.py,sha256=tg-zRlVSUSJ7B0cJbBsUwmMRmpIUmK5tsL8ABnY0wnY,46626
+nmdc_runtime/site/repository.py,sha256=kVCoIMF2rgAMUAf9a6jk0WbejFpmWgxh6nN4U37Mgc8,43919
 nmdc_runtime/site/resources.py,sha256=sqtRWb4ewU61U-JZTphsC4wBvYT5B0wj33WU70vjq_k,19677
 nmdc_runtime/site/util.py,sha256=-DnNv15r6XmFZrDG3d3Z-bFn2pFo0xpyyudhKlYPJKc,1559
 nmdc_runtime/site/backup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -57,13 +57,13 @@ nmdc_runtime/site/export/study_metadata.py,sha256=yR5pXL6JG8d7cAtqcF-60Hp7bLD3dJ
 nmdc_runtime/site/normalization/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/site/normalization/gold.py,sha256=iISDD4qs4d6uLhv631WYNeQVOzY5DO201ZpPtxHdkVk,1311
 nmdc_runtime/site/repair/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/site/repair/database_updater.py,sha256=EMuY8MfwQEfdejJHp0Y-Gb1eb1zOgKgfJxbtm6wM3YU,10943
+nmdc_runtime/site/repair/database_updater.py,sha256=eTNAPtgAc_xQodADBfgomwow9-14j5rBqQWF8R7BheY,11525
 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=Zw4IjxMWJ1wdLyxX44-faq-Nfmr42-Na1gw-Xn4tg6I,32272
 nmdc_runtime/site/translation/jgi.py,sha256=qk878KhIw674TkrVfbl2x1QJrKi3zlvE0vesIpe9slM,876
-nmdc_runtime/site/translation/neon_benthic_translator.py,sha256=QIDqYLuf-NlGY9_88gy_5qTswkei3OfgJ5AOFpEXzJo,23985
+nmdc_runtime/site/translation/neon_benthic_translator.py,sha256=VxN7yCziQE-ZP9mtrzqI-yaS9taEgTy0EnIEattYeKo,23727
 nmdc_runtime/site/translation/neon_soil_translator.py,sha256=Rol0g67nVBGSBySUzpfdW4Fwes7bKtvnlv2g5cB0aTI,38550
 nmdc_runtime/site/translation/neon_surface_water_translator.py,sha256=k06eULMTYx0sQ00UlyeNJvCJMcX-neClnES1G6zpPKg,30517
 nmdc_runtime/site/translation/neon_utils.py,sha256=d00o7duKKugpLHmsEifNbp4WjeC4GOqcgw0b5qlCg4I,5549
@@ -75,9 +75,9 @@ 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-2.4.0.dist-info/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
-nmdc_runtime-2.4.0.dist-info/METADATA,sha256=CeZZbucd3jrD0ZqGdreH2x7ALrM9pt4ksGV2olkkpPI,7401
-nmdc_runtime-2.4.0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-nmdc_runtime-2.4.0.dist-info/entry_points.txt,sha256=JxdvOnvxHK_8046cwlvE30s_fV0-k-eTpQtkKYA69nQ,224
-nmdc_runtime-2.4.0.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
-nmdc_runtime-2.4.0.dist-info/RECORD,,
+nmdc_runtime-2.5.0.dist-info/licenses/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
+nmdc_runtime-2.5.0.dist-info/METADATA,sha256=tli66QKJC-48TzLXbI9iHMzTLyugbRBKj9CJEeKHXLY,8139
+nmdc_runtime-2.5.0.dist-info/WHEEL,sha256=DK49LOLCYiurdXXOXwGJm6U4DkHkg4lcxjhqwRa0CP4,91
+nmdc_runtime-2.5.0.dist-info/entry_points.txt,sha256=JxdvOnvxHK_8046cwlvE30s_fV0-k-eTpQtkKYA69nQ,224
+nmdc_runtime-2.5.0.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
+nmdc_runtime-2.5.0.dist-info/RECORD,,

{nmdc_runtime-2.4.0.dist-info → nmdc_runtime-2.5.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.0)
+Generator: setuptools (78.0.2)
 Root-Is-Purelib: true
 Tag: py3-none-any