nmdc-runtime 1.6.0__py3-none-any.whl → 1.7.0__py3-none-any.whl

nmdc_runtime/site/graphs.py

@@ -22,7 +22,6 @@ from nmdc_runtime.site.ops import (
     hello,
     mongo_stats,
     submit_metadata_to_db,
-    update_schema,
     filter_ops_undone_expired,
     construct_jobs,
     maybe_post_jobs,
@@ -49,7 +48,14 @@ from nmdc_runtime.site.ops import (
     get_neon_pipeline_inputs,
     get_df_from_url,
     site_code_mapping,
+    get_ncbi_export_pipeline_study,
+    get_data_objects_from_biosamples,
+    get_omics_processing_from_biosamples,
+    get_ncbi_export_pipeline_inputs,
+    ncbi_submission_xml_from_nmdc_study,
+    ncbi_submission_xml_asset,
 )
+from nmdc_runtime.site.export.study_metadata import get_biosamples_by_study_id
 
 
 @graph
@@ -87,17 +93,6 @@ def hello_mongo():
     mongo_stats()
 
 
-@graph
-def update_terminus():
-    """
-    A pipeline definition. This example pipeline has a single solid.
-
-    For more hints on writing Dagster pipelines, see our documentation overview on Pipelines:
-    https://docs.dagster.io/overview/solids-pipelines/pipelines
-    """
-    update_schema()
-
-
 @graph
 def housekeeping():
     delete_operations(list_operations(filter_ops_undone_expired()))
@@ -381,3 +376,20 @@ def ingest_neon_surface_water_metadata():
     )
     run_id = submit_metadata_to_db(database)
     poll_for_run_completion(run_id)
+
+
+@graph
+def nmdc_study_to_ncbi_submission_export():
+    nmdc_study = get_ncbi_export_pipeline_study()
+    ncbi_submission_metadata = get_ncbi_export_pipeline_inputs()
+    biosamples = get_biosamples_by_study_id(nmdc_study)
+    omics_processing_records = get_omics_processing_from_biosamples(biosamples)
+    data_objects = get_data_objects_from_biosamples(biosamples)
+    xml_data = ncbi_submission_xml_from_nmdc_study(
+        nmdc_study,
+        ncbi_submission_metadata,
+        biosamples,
+        omics_processing_records,
+        data_objects,
+    )
+    ncbi_submission_xml_asset(xml_data)

nmdc_runtime/site/ops.py

@@ -9,6 +9,7 @@ from datetime import datetime, timezone
 from io import BytesIO, StringIO
 from typing import Tuple
 from zipfile import ZipFile
+
 import pandas as pd
 import requests
 
@@ -29,10 +30,14 @@ from dagster import (
     String,
     op,
     Optional,
+    Field,
+    Permissive,
+    Bool,
 )
 from gridfs import GridFS
 from linkml_runtime.dumpers import json_dumper
 from linkml_runtime.utils.yamlutils import YAMLRoot
+from nmdc_runtime.api.db.mongo import get_mongo_db
 from nmdc_runtime.api.core.idgen import generate_one_id
 from nmdc_runtime.api.core.metadata import (
     _validate_changesheet,
@@ -42,6 +47,7 @@ from nmdc_runtime.api.core.metadata import (
 )
 from nmdc_runtime.api.core.util import dotted_path_for, hash_from_str, json_clean, now
 from nmdc_runtime.api.endpoints.util import persist_content_and_get_drs_object
+from nmdc_runtime.api.endpoints.find import find_study_by_id
 from nmdc_runtime.api.models.job import Job, JobOperationMetadata
 from nmdc_runtime.api.models.metadata import ChangesheetIn
 from nmdc_runtime.api.models.operation import (
@@ -55,6 +61,11 @@ from nmdc_runtime.api.models.run import (
     _add_run_complete_event,
 )
 from nmdc_runtime.api.models.util import ResultT
+from nmdc_runtime.site.export.ncbi_xml import NCBISubmissionXML
+from nmdc_runtime.site.export.ncbi_xml_utils import (
+    fetch_data_objects_from_biosamples,
+    fetch_omics_processing_from_biosamples,
+)
 from nmdc_runtime.site.drsobjects.ingest import mongo_add_docs_result_as_dict
 from nmdc_runtime.site.resources import (
     NmdcPortalApiClient,
@@ -86,7 +97,6 @@ from nmdc_schema import nmdc
 from pydantic import BaseModel
 from pymongo.database import Database as MongoDatabase
 from starlette import status
-from terminusdb_client.woqlquery import WOQLQuery as WQ
 from toolz import assoc, dissoc, get_in, valfilter, identity
 
 
@@ -111,14 +121,6 @@ def log_env(context):
     context.log.info("\n".join(out))
 
 
-@op(required_resource_keys={"terminus"})
-def list_databases(context) -> List[String]:
-    client = context.resources.terminus.client
-    list_ = client.list_databases()
-    context.log.info(f"databases: {list_}")
-    return list_
-
-
 @op(required_resource_keys={"mongo"})
 def mongo_stats(context) -> List[str]:
     db = context.resources.mongo.db
@@ -127,41 +129,6 @@ def mongo_stats(context) -> List[str]:
     return collection_names
 
 
-@op(required_resource_keys={"terminus"})
-def update_schema(context):
-    with tempfile.TemporaryDirectory() as tmpdirname:
-        try:
-            context.log.info("shallow-cloning nmdc-schema repo")
-            subprocess.check_output(
-                "git clone https://github.com/microbiomedata/nmdc-schema.git"
-                f" --branch main --single-branch {tmpdirname}/nmdc-schema",
-                shell=True,
-            )
-            context.log.info("generating TerminusDB JSON-LD from NMDC LinkML")
-            subprocess.check_output(
-                f"gen-terminusdb {tmpdirname}/nmdc-schema/src/schema/nmdc.yaml"
-                f" > {tmpdirname}/nmdc.terminus.json",
-                shell=True,
-            )
-        except subprocess.CalledProcessError as e:
-            if e.stdout:
-                context.log.debug(e.stdout.decode())
-            if e.stderr:
-                context.log.error(e.stderr.decode())
-            context.log.debug(str(e.returncode))
-            raise e
-
-        with open(f"{tmpdirname}/nmdc.terminus.json") as f:
-            woql_dict = json.load(f)
-
-    context.log.info("Updating terminus schema via WOQLQuery")
-    rv = WQ(query=woql_dict).execute(
-        context.resources.terminus.client, "update schema via WOQL"
-    )
-    context.log.info(str(rv))
-    return rv
-
-
 @op(
     required_resource_keys={"mongo", "runtime_api_site_client"},
     retry_policy=RetryPolicy(max_retries=2),
@@ -768,6 +735,33 @@ def export_json_to_drs(
     return ["/objects/" + drs_object["id"]]
 
 
+@op(
+    description="NCBI Submission XML file rendered in a Dagster Asset",
+    out=Out(description="XML content rendered through Dagit UI"),
+)
+def ncbi_submission_xml_asset(context: OpExecutionContext, data: str):
+    filename = "ncbi_submission.xml"
+    file_path = os.path.join(context.instance.storage_directory(), filename)
+
+    os.makedirs(os.path.dirname(file_path), exist_ok=True)
+
+    with open(file_path, "w") as f:
+        f.write(data)
+
+    context.log_event(
+        AssetMaterialization(
+            asset_key="ncbi_submission_xml",
+            description="NCBI Submission XML Data",
+            metadata={
+                "file_path": MetadataValue.path(file_path),
+                "xml": MetadataValue.text(data),
+            },
+        )
+    )
+
+    return Output(data)
+
+
 def unique_field_values(docs: List[Dict[str, Any]], field: str):
     return {doc[field] for doc in docs if field in doc}
 
@@ -977,3 +971,85 @@ def site_code_mapping() -> dict:
         raise Exception(
             f"Failed to fetch site data from {endpoint}. Status code: {response.status_code}, Content: {response.content}"
         )
+
+
+@op(config_schema={"nmdc_study_id": str}, required_resource_keys={"mongo"})
+def get_ncbi_export_pipeline_study(context: OpExecutionContext) -> Any:
+    nmdc_study = find_study_by_id(
+        context.op_config["nmdc_study_id"], context.resources.mongo.db
+    )
+    return nmdc_study
+
+
+@op(
+    config_schema={
+        "nmdc_ncbi_attribute_mapping_file_url": str,
+        "ncbi_submission_metadata": Field(
+            Permissive(
+                {
+                    "organization": String,
+                }
+            ),
+            is_required=True,
+            description="General metadata about the NCBI submission.",
+        ),
+        "ncbi_biosample_metadata": Field(
+            Permissive(
+                {
+                    "organism_name": String,
+                }
+            ),
+            is_required=True,
+            description="Metadata for one or many NCBI BioSample in the Submission.",
+        ),
+    },
+    out=Out(Dict),
+)
+def get_ncbi_export_pipeline_inputs(context: OpExecutionContext) -> str:
+    nmdc_ncbi_attribute_mapping_file_url = context.op_config[
+        "nmdc_ncbi_attribute_mapping_file_url"
+    ]
+    ncbi_submission_metadata = context.op_config.get("ncbi_submission_metadata", {})
+    ncbi_biosample_metadata = context.op_config.get("ncbi_biosample_metadata", {})
+
+    return {
+        "nmdc_ncbi_attribute_mapping_file_url": nmdc_ncbi_attribute_mapping_file_url,
+        "ncbi_submission_metadata": ncbi_submission_metadata,
+        "ncbi_biosample_metadata": ncbi_biosample_metadata,
+    }
+
+
+@op(required_resource_keys={"mongo"})
+def get_data_objects_from_biosamples(context: OpExecutionContext, biosamples: list):
+    mdb = context.resources.mongo.db
+    alldocs_collection = mdb["alldocs"]
+    biosample_data_objects = fetch_data_objects_from_biosamples(
+        alldocs_collection, biosamples
+    )
+    return biosample_data_objects
+
+
+@op(required_resource_keys={"mongo"})
+def get_omics_processing_from_biosamples(context: OpExecutionContext, biosamples: list):
+    mdb = context.resources.mongo.db
+    alldocs_collection = mdb["alldocs"]
+    biosample_omics_processing = fetch_omics_processing_from_biosamples(
+        alldocs_collection, biosamples
+    )
+    return biosample_omics_processing
+
+
+@op
+def ncbi_submission_xml_from_nmdc_study(
+    context: OpExecutionContext,
+    nmdc_study: Any,
+    ncbi_exporter_metadata: dict,
+    biosamples: list,
+    omics_processing_records: list,
+    data_objects: list,
+) -> str:
+    ncbi_exporter = NCBISubmissionXML(nmdc_study, ncbi_exporter_metadata)
+    ncbi_xml = ncbi_exporter.get_submission_xml(
+        biosamples, omics_processing_records, data_objects
+    )
+    return ncbi_xml

nmdc_runtime/site/repository.py

@@ -42,6 +42,7 @@ from nmdc_runtime.site.graphs import (
     ingest_neon_soil_metadata,
     ingest_neon_benthic_metadata,
     ingest_neon_surface_water_metadata,
+    nmdc_study_to_ncbi_submission_export,
 )
 from nmdc_runtime.site.resources import (
     get_mongo,
@@ -50,7 +51,6 @@ from nmdc_runtime.site.resources import (
     nmdc_portal_api_client_resource,
     gold_api_client_resource,
     neon_api_client_resource,
-    terminus_resource,
     mongo_resource,
 )
 from nmdc_runtime.site.resources import (
@@ -68,7 +68,6 @@ resource_defs = {
     "nmdc_portal_api_client": nmdc_portal_api_client_resource,
     "gold_api_client": gold_api_client_resource,
     "neon_api_client": neon_api_client_resource,
-    "terminus": terminus_resource,
     "mongo": mongo_resource,
 }
 
@@ -515,8 +514,8 @@ def biosample_submission_ingest():
                         "nmdc_portal_api_client": {
                             "config": {
                                 "base_url": {"env": "NMDC_PORTAL_API_BASE_URL"},
-                                "session_cookie": {
-                                    "env": "NMDC_PORTAL_API_SESSION_COOKIE"
+                                "refresh_token": {
+                                    "env": "NMDC_PORTAL_API_REFRESH_TOKEN"
                                 },
                             }
                         }
@@ -555,8 +554,8 @@ def biosample_submission_ingest():
                         "nmdc_portal_api_client": {
                             "config": {
                                 "base_url": {"env": "NMDC_PORTAL_API_BASE_URL"},
-                                "session_cookie": {
-                                    "env": "NMDC_PORTAL_API_SESSION_COOKIE"
+                                "refresh_token": {
+                                    "env": "NMDC_PORTAL_API_REFRESH_TOKEN"
                                 },
                             }
                         }
@@ -852,6 +851,57 @@ def biosample_submission_ingest():
     ]
 
 
+@repository
+def biosample_export():
+    normal_resources = run_config_frozen__normal_env["resources"]
+    return [
+        nmdc_study_to_ncbi_submission_export.to_job(
+            resource_defs=resource_defs,
+            config={
+                "resources": merge(
+                    unfreeze(normal_resources),
+                    {
+                        "mongo": {
+                            "config": {
+                                "host": {"env": "MONGO_HOST"},
+                                "username": {"env": "MONGO_USERNAME"},
+                                "password": {"env": "MONGO_PASSWORD"},
+                                "dbname": {"env": "MONGO_DBNAME"},
+                            },
+                        },
+                        "runtime_api_site_client": {
+                            "config": {
+                                "base_url": {"env": "API_HOST"},
+                                "client_id": {"env": "API_SITE_CLIENT_ID"},
+                                "client_secret": {"env": "API_SITE_CLIENT_SECRET"},
+                                "site_id": {"env": "API_SITE_ID"},
+                            },
+                        },
+                    },
+                ),
+                "ops": {
+                    "get_ncbi_export_pipeline_study": {
+                        "config": {
+                            "nmdc_study_id": "",
+                        }
+                    },
+                    "get_ncbi_export_pipeline_inputs": {
+                        "config": {
+                            "nmdc_ncbi_attribute_mapping_file_url": "",
+                            "ncbi_submission_metadata": {
+                                "organization": "",
+                            },
+                            "ncbi_biosample_metadata": {
+                                "organism_name": "",
+                            },
+                        }
+                    },
+                },
+            },
+        ),
+    ]
+
+
 # @repository
 # def validation():
 #     graph_jobs = [validate_jgi_job, validate_gold_job, validate_emsl_job]

nmdc_runtime/site/resources.py

@@ -19,7 +19,6 @@ from frozendict import frozendict
 from linkml_runtime.dumpers import json_dumper
 from pydantic import BaseModel, AnyUrl
 from pymongo import MongoClient, ReplaceOne, InsertOne
-from terminusdb_client import WOQLClient
 from toolz import get_in
 from toolz import merge
 
@@ -372,16 +371,37 @@ def gold_api_client_resource(context: InitResourceContext):
 
 @dataclass
 class NmdcPortalApiClient:
+
     base_url: str
-    # Using a cookie for authentication is not ideal and should be replaced
-    # when this API has an another authentication method
-    session_cookie: str
+    refresh_token: str
+    access_token: Optional[str] = None
+    access_token_expires_at: Optional[datetime] = None
+
+    def _request(self, method: str, endpoint: str, **kwargs):
+        r"""
+        Submits a request to the specified API endpoint;
+        after refreshing the access token, if necessary.
+        """
+        if self.access_token is None or datetime.now() > self.access_token_expires_at:
+            refresh_response = requests.post(
+                f"{self.base_url}/auth/refresh",
+                json={"refresh_token": self.refresh_token},
+            )
+            refresh_response.raise_for_status()
+            refresh_body = refresh_response.json()
+            self.access_token_expires_at = datetime.now() + timedelta(
+                seconds=refresh_body["expires_in"]
+            )
+            self.access_token = refresh_body["access_token"]
 
-    def fetch_metadata_submission(self, id: str) -> Dict[str, Any]:
-        response = requests.get(
-            f"{self.base_url}/api/metadata_submission/{id}",
-            cookies={"session": self.session_cookie},
+        headers = kwargs.get("headers", {})
+        headers["Authorization"] = f"Bearer {self.access_token}"
+        return requests.request(
+            method, f"{self.base_url}{endpoint}", **kwargs, headers=headers
         )
+
+    def fetch_metadata_submission(self, id: str) -> Dict[str, Any]:
+        response = self._request("GET", f"/api/metadata_submission/{id}")
         response.raise_for_status()
         return response.json()
 
@@ -389,13 +409,13 @@ class NmdcPortalApiClient:
 @resource(
     config_schema={
         "base_url": StringSource,
-        "session_cookie": StringSource,
+        "refresh_token": StringSource,
     }
 )
 def nmdc_portal_api_client_resource(context: InitResourceContext):
     return NmdcPortalApiClient(
         base_url=context.resource_config["base_url"],
-        session_cookie=context.resource_config["session_cookie"],
+        refresh_token=context.resource_config["refresh_token"],
     )
 
 
@@ -512,33 +532,3 @@ def get_mongo(run_config: frozendict):
         )
     )
     return mongo_resource(resource_context)
-
-
-class TerminusDB:
-    def __init__(self, server_url, user, key, account, dbid):
-        self.client = WOQLClient(server_url=server_url)
-        self.client.connect(user=user, key=key, account=account)
-        db_info = self.client.get_database(dbid=dbid, account=account)
-        if db_info is None:
-            self.client.create_database(dbid=dbid, accountid=account, label=dbid)
-            self.client.create_graph(graph_type="inference", graph_id="main")
-        self.client.connect(user=user, key=key, account=account, db=dbid)
-
-
-@resource(
-    config_schema={
-        "server_url": StringSource,
-        "user": StringSource,
-        "key": StringSource,
-        "account": StringSource,
-        "dbid": StringSource,
-    }
-)
-def terminus_resource(context):
-    return TerminusDB(
-        server_url=context.resource_config["server_url"],
-        user=context.resource_config["user"],
-        key=context.resource_config["key"],
-        account=context.resource_config["account"],
-        dbid=context.resource_config["dbid"],
-    )

nmdc_runtime/site/translation/submission_portal_translator.py

@@ -13,6 +13,9 @@ from toolz import get_in, groupby, concat, valmap, dissoc
 from nmdc_runtime.site.translation.translator import JSON_OBJECT, Translator
 
 
+BIOSAMPLE_UNIQUE_KEY_SLOT = "samp_name"
+
+
 @lru_cache
 def _get_schema_view():
     """Return a SchemaView instance representing the NMDC schema"""
@@ -98,7 +101,9 @@ class SubmissionPortalTranslator(Translator):
         self.study_pi_image_url = study_pi_image_url
         self.study_funding_sources = study_funding_sources
 
-        self.biosample_extras = group_dicts_by_key("source_mat_id", biosample_extras)
+        self.biosample_extras = group_dicts_by_key(
+            BIOSAMPLE_UNIQUE_KEY_SLOT, biosample_extras
+        )
         self.biosample_extras_slot_mapping = group_dicts_by_key(
             "subject_id", biosample_extras_slot_mapping
         )
@@ -521,7 +526,7 @@ class SubmissionPortalTranslator(Translator):
         :param default_env_package: Default value for `env_package` slot
         :return: nmdc:Biosample
         """
-        source_mat_id = sample_data[0].get("source_mat_id", "").strip()
+        biosample_key = sample_data[0].get(BIOSAMPLE_UNIQUE_KEY_SLOT, "").strip()
         slots = {
             "id": nmdc_biosample_id,
             "part_of": nmdc_study_id,
@@ -533,7 +538,7 @@ class SubmissionPortalTranslator(Translator):
             slots.update(transformed_tab)
 
         if self.biosample_extras:
-            raw_extras = self.biosample_extras.get(source_mat_id)
+            raw_extras = self.biosample_extras.get(biosample_key)
             if raw_extras:
                 transformed_extras = self._transform_dict_for_class(
                     raw_extras, "Biosample", self.biosample_extras_slot_mapping
@@ -564,7 +569,9 @@ class SubmissionPortalTranslator(Translator):
 
         sample_data = metadata_submission_data.get("sampleData", {})
         package_name = metadata_submission_data["packageName"]
-        sample_data_by_id = groupby("source_mat_id", concat(sample_data.values()))
+        sample_data_by_id = groupby(
+            BIOSAMPLE_UNIQUE_KEY_SLOT, concat(sample_data.values())
+        )
         nmdc_biosample_ids = self._id_minter("nmdc:Biosample", len(sample_data_by_id))
         sample_data_to_nmdc_biosample_ids = dict(
             zip(sample_data_by_id.keys(), nmdc_biosample_ids)
@@ -583,15 +590,15 @@ class SubmissionPortalTranslator(Translator):
 
         if self.omics_processing_mapping:
             # If there is data from an OmicsProcessing mapping file, process it now. This part
-            # assumes that there is a column in that file with the header __biosample_source_mat_id
+            # 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 `source_mat_id` will be referenced in the `has_input`
+            # 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 `source_mat_id` slot of the submission's
+            # 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.
-            join_key = "__biosample_source_mat_id"
+            join_key = f"__biosample_{BIOSAMPLE_UNIQUE_KEY_SLOT}"
             database.omics_processing_set = []
             database.data_object_set = []
             data_objects_by_sample_data_id = {}
@@ -617,7 +624,7 @@ class SubmissionPortalTranslator(Translator):
                     or sample_data_id not in sample_data_to_nmdc_biosample_ids
                 ):
                     logging.warning(
-                        f"Unrecognized biosample source_mat_id: {sample_data_id}"
+                        f"Unrecognized biosample {BIOSAMPLE_UNIQUE_KEY_SLOT}: {sample_data_id}"
                     )
                     continue
                 nmdc_biosample_id = sample_data_to_nmdc_biosample_ids[sample_data_id]

nmdc_runtime/util.py

@@ -16,7 +16,7 @@ import fastjsonschema
 import requests
 from frozendict import frozendict
 from jsonschema.validators import Draft7Validator
-from nmdc_schema.nmdc_schema_accepting_legacy_ids import Database as NMDCDatabase
+from nmdc_schema.nmdc import Database as NMDCDatabase
 from nmdc_schema.get_nmdc_view import ViewGetter
 from pydantic import Field, BaseModel
 from pymongo.database import Database as MongoDatabase

{nmdc_runtime-1.6.0.dist-info → nmdc_runtime-1.7.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nmdc_runtime
-Version: 1.6.0
+Version: 1.7.0
 Summary: A runtime system for NMDC data management and orchestration
 Home-page: https://github.com/microbiomedata/nmdc-runtime
 Author: Donny Winston
@@ -77,18 +77,15 @@ The runtime features:
          - `schedules` trigger recurring pipeline runs based on time
          - `sensors` trigger pipeline runs based on external state
       - Each `pipeline` can declare dependencies on any runtime `resources` or additional
-         configuration. There are TerminusDB and MongoDB `resources` defined, as well as `preset`
+         configuration. There are MongoDB `resources` defined, as well as `preset`
          configuration definitions for both "dev" and "prod" `modes`. The `preset`s tell Dagster to
          look to a set of known environment variables to load resources configurations, depending on
          the `mode`.
-
-2. A [TerminusDB](https://terminusdb.com/) database supporting revision control of schema-validated
-data.
    
-3. A MongoDB database supporting write-once, high-throughput internal
+2. A MongoDB database supporting write-once, high-throughput internal
 data storage by the nmdc-runtime FastAPI instance.
    
-4. A [FastAPI](https://fastapi.tiangolo.com/) service to interface with the orchestrator and
+3. A [FastAPI](https://fastapi.tiangolo.com/) service to interface with the orchestrator and
 database, as a hub for data management and workflow automation.
 
 ## Local Development

{nmdc_runtime-1.6.0.dist-info → nmdc_runtime-1.7.0.dist-info}/RECORD

@@ -1,7 +1,7 @@
 nmdc_runtime/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/containers.py,sha256=8m_S1wiFu8VOWvY7tyqzf-02X9gXY83YGc8FgjWzLGA,418
 nmdc_runtime/main.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/util.py,sha256=o74ZKOmSD79brPFAcQFsYpA6wh9287m0hDhDlIpn9VM,19872
+nmdc_runtime/util.py,sha256=3mHVEUdMOv73XgT6NTuzMuMCL5Gs6NJ4Mk0bkgQQaQU,19844
 nmdc_runtime/client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/core/db/Database.py,sha256=WamgBUbq85A7-fr3p5B9Tk92U__yPdr9pBb4zyQok-4,377
@@ -35,10 +35,10 @@ 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=mOWZvT2Rk4X96RmVAvHQwur-FhNuMWAko3jjRLGygEE,11455
-nmdc_runtime/site/ops.py,sha256=YjaH2zqzd01cRcqV0E93RoaWt8T4ExESx4SSszmczZ8,33620
-nmdc_runtime/site/repository.py,sha256=QI9Gcjr68-DT2MPwOx87Vkxcwp3ZIOVaFZ9uCO13w9U,35502
-nmdc_runtime/site/resources.py,sha256=pQSwg1dRpL_D91gYLzzaOIDZ3qa69rPqSlsq5dS9i_M,17783
+nmdc_runtime/site/graphs.py,sha256=_vCyQnICis4OQGH91i1ZwpvHYcXOG6Nfg04f5DVdy2M,12040
+nmdc_runtime/site/ops.py,sha256=G6X3YgSmDNxOnsMEByLUMfB0peY4o21o0_Ig3V7v6M4,35835
+nmdc_runtime/site/repository.py,sha256=-dOk9BEnLSrmAN6bZoIu_WnFSqriIpO0c5P76PuHW1M,37472
+nmdc_runtime/site/resources.py,sha256=ZSH1yvA-li0R7Abc22_v0XLbjBYf5igETr2G01J3hnc,17557
 nmdc_runtime/site/util.py,sha256=6hyVPpb6ZkWEG8Nm7uQxnZ-QmuPOG9hgWvl0mUBr5JU,1303
 nmdc_runtime/site/backup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/site/backup/nmdcdb_mongodump.py,sha256=H5uosmEiXwLwklJrYJWrNhb_Nuf_ew8dBpZLl6_dYhs,2699
@@ -50,13 +50,11 @@ 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/study_metadata.py,sha256=d3q6RV93B0BA64ZkfCPEHdlrC1P8pm9Sj6SxRDcpB7A,4027
+nmdc_runtime/site/export/ncbi_xml.py,sha256=Z2qsaGIBvY2OdOkf8kJEZl1T_8R_YzhAlXxJ1gMQwnk,16946
+nmdc_runtime/site/export/ncbi_xml_utils.py,sha256=CqrtjwzmUbZXEW8aD-KpnCV_PlXVH-Gqp309nw3vbeo,6464
+nmdc_runtime/site/export/study_metadata.py,sha256=WRU0F1ksWfNX3k9LD91Pn2DuLA-IOpGvYPJd6DnguEs,4819
 nmdc_runtime/site/normalization/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nmdc_runtime/site/normalization/gold.py,sha256=iISDD4qs4d6uLhv631WYNeQVOzY5DO201ZpPtxHdkVk,1311
-nmdc_runtime/site/terminusdb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nmdc_runtime/site/terminusdb/generate.py,sha256=Z3c06LDx3TGw4pvPRO97caQvzc8SuhGmPIr_d5b_E9I,6144
-nmdc_runtime/site/terminusdb/ingest.py,sha256=WE_V4vRRnlL6hIBU1TDSUheYOBWS9d5g6FHPS64jzvM,1245
-nmdc_runtime/site/terminusdb/schema.py,sha256=3e39rHUSZsNbN_F0SHHNsvcEGRWtYa6O9KNj3cH3tUs,77129
 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
@@ -66,7 +64,7 @@ nmdc_runtime/site/translation/neon_benthic_translator.py,sha256=e_7tXFrP0PpdhqUC
 nmdc_runtime/site/translation/neon_soil_translator.py,sha256=cJJ_QPva5G5SIT_7DjCSsqbDvgbiKGqUYrxK3nx7_Lw,37634
 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=lHcrfPR5wk3BcZ0Uw5zUyWu5XRVikgOzdzSb5nFVS9I,27964
+nmdc_runtime/site/translation/submission_portal_translator.py,sha256=KiVO1vohhrJGfwzLJOumRfyHjcbYfswBIBvkYIdFxv8,28097
 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
@@ -74,9 +72,9 @@ 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-1.6.0.dist-info/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
-nmdc_runtime-1.6.0.dist-info/METADATA,sha256=hKgDLZfx14AX3IWIi3C9vHa9YAP-agU7tsmKZ_kg8JY,7424
-nmdc_runtime-1.6.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-nmdc_runtime-1.6.0.dist-info/entry_points.txt,sha256=nfH6-K9tDKv7va8ENfShsBnxVQoYJdEe7HHdwtkbh1Y,289
-nmdc_runtime-1.6.0.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
-nmdc_runtime-1.6.0.dist-info/RECORD,,
+nmdc_runtime-1.7.0.dist-info/LICENSE,sha256=VWiv65r7gHGjgtr3jMJYVmQny5GRpQ6H-W9sScb1x70,2408
+nmdc_runtime-1.7.0.dist-info/METADATA,sha256=FnoXHNgR6o5PEe6XhqRGdqOjbIX_ry-SKY5uMtZJQXY,7302
+nmdc_runtime-1.7.0.dist-info/WHEEL,sha256=mguMlWGMX-VHnMpKOjjQidIo1ssRlCFu4a4mBpz1s2M,91
+nmdc_runtime-1.7.0.dist-info/entry_points.txt,sha256=JxdvOnvxHK_8046cwlvE30s_fV0-k-eTpQtkKYA69nQ,224
+nmdc_runtime-1.7.0.dist-info/top_level.txt,sha256=b0K1s09L_iHH49ueBKaLrB5-lh6cyrSv9vL6x4Qvyz8,13
+nmdc_runtime-1.7.0.dist-info/RECORD,,