inference of some Submission and BioProject fields from existing meta…

…data

nmdc_runtime/site/export/ncbi_xml.py

@@ -3,6 +3,7 @@
 import xml.etree.ElementTree as ET
 import xml.dom.minidom
 
+from typing import Any
 from urllib.parse import urlparse
 from nmdc_runtime.site.export.ncbi_xml_utils import (
     handle_controlled_identified_term_value,
@@ -19,10 +20,19 @@
 
 
 class NCBISubmissionXML:
-    def __init__(self, nmdc_study_id: str, ncbi_submission_metadata: dict):
+    def __init__(self, nmdc_study: Any, ncbi_submission_metadata: dict):
         self.root = ET.Element("Submission")
 
-        self.nmdc_study_id = nmdc_study_id
+        self.nmdc_study_id = nmdc_study.get("id")
+        self.nmdc_study_title = nmdc_study.get("title")
+        self.nmdc_study_description = nmdc_study.get("description")
+        self.ncbi_bioproject_id = nmdc_study.get("insdc_bioproject_identifiers")
+        self.nmdc_pi_email = nmdc_study.get("principal_investigator", {}).get("email")
+        nmdc_study_pi_name = (
+            nmdc_study.get("principal_investigator", {}).get("name").split()
+        )
+        self.first_name = nmdc_study_pi_name[0]
+        self.last_name = nmdc_study_pi_name[1] if len(nmdc_study_pi_name) > 1 else None
 
         self.nmdc_ncbi_attribute_mapping_file_url = ncbi_submission_metadata.get(
             "nmdc_ncbi_attribute_mapping_file_url"
@@ -357,18 +367,18 @@ def set_fastq(
 
     def get_submission_xml(self, biosamples_list: list, data_objects_list: list):
         self.set_description(
-            email=self.ncbi_submission_metadata.get("email", ""),
-            user=self.ncbi_submission_metadata.get("user", ""),
-            first=self.ncbi_submission_metadata.get("first", ""),
-            last=self.ncbi_submission_metadata.get("last", ""),
+            email=self.nmdc_pi_email,
+            user="National Microbiome Data Collaborative (NMDC)",
+            first=self.first_name,
+            last=self.last_name,
             org=self.ncbi_submission_metadata.get("organization", ""),
         )
 
         if not self.ncbi_bioproject_metadata.get("exists"):
             self.set_bioproject(
-                title=self.ncbi_bioproject_metadata.get("title", ""),
+                title=self.nmdc_study_title,
                 project_id=self.ncbi_bioproject_metadata.get("project_id", ""),
-                description=self.ncbi_bioproject_metadata.get("description", ""),
+                description=self.nmdc_study_description,
                 data_type=self.ncbi_bioproject_metadata.get("data_type", ""),
                 org=self.ncbi_submission_metadata.get("organization", ""),
             )

nmdc_runtime/site/export/study_metadata.py

@@ -131,7 +131,7 @@ def export_study_biosamples_metadata():
 
 
 @op(required_resource_keys={"runtime_api_site_client"})
-def get_biosamples_by_study_id(context: OpExecutionContext, nmdc_study_id: str):
+def get_biosamples_by_study_id(context: OpExecutionContext, nmdc_study: dict):
     client: RuntimeApiSiteClient = context.resources.runtime_api_site_client
-    biosamples = get_all_docs(client, "biosamples", f"part_of:{nmdc_study_id}")
+    biosamples = get_all_docs(client, "biosamples", f"part_of:{nmdc_study['id']}")
     return biosamples

nmdc_runtime/site/graphs.py

@@ -49,7 +49,7 @@
     get_neon_pipeline_inputs,
     get_df_from_url,
     site_code_mapping,
-    get_ncbi_export_pipeline_study_id,
+    get_ncbi_export_pipeline_study,
     get_data_objects_from_biosamples,
     get_ncbi_export_pipeline_inputs,
     ncbi_submission_xml_from_nmdc_study,
@@ -391,11 +391,11 @@ def ingest_neon_surface_water_metadata():
 
 @graph
 def nmdc_study_to_ncbi_submission_export():
-    nmdc_study_id = get_ncbi_export_pipeline_study_id()
+    nmdc_study = get_ncbi_export_pipeline_study()
     ncbi_submission_metadata = get_ncbi_export_pipeline_inputs()
-    biosamples = get_biosamples_by_study_id(nmdc_study_id)
+    biosamples = get_biosamples_by_study_id(nmdc_study)
     data_objects = get_data_objects_from_biosamples(biosamples)
     xml_data = ncbi_submission_xml_from_nmdc_study(
-        nmdc_study_id, ncbi_submission_metadata, biosamples, data_objects
+        nmdc_study, ncbi_submission_metadata, biosamples, data_objects
     )
     ncbi_submission_xml_asset(xml_data)

nmdc_runtime/site/ops.py

@@ -48,6 +48,7 @@
 )
 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 (
@@ -1014,9 +1015,12 @@ def site_code_mapping() -> dict:
         )
 
 
-@op(config_schema={"nmdc_study_id": str})
-def get_ncbi_export_pipeline_study_id(context: OpExecutionContext) -> str:
-    return context.op_config["nmdc_study_id"]
+@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(
@@ -1025,10 +1029,6 @@ def get_ncbi_export_pipeline_study_id(context: OpExecutionContext) -> str:
         "ncbi_submission_metadata": Field(
             Permissive(
                 {
-                    "email": String,
-                    "first": String,
-                    "last": String,
-                    "user": String,
                     "organization": String,
                 }
             ),
@@ -1038,9 +1038,7 @@ def get_ncbi_export_pipeline_study_id(context: OpExecutionContext) -> str:
         "ncbi_bioproject_metadata": Field(
             Permissive(
                 {
-                    "title": String,
                     "project_id": String,
-                    "description": String,
                     "data_type": String,
                     "exists": Bool,
                 }
@@ -1090,11 +1088,11 @@ def get_data_objects_from_biosamples(context: OpExecutionContext, biosamples: li
 @op
 def ncbi_submission_xml_from_nmdc_study(
     context: OpExecutionContext,
-    nmdc_study_id: str,
+    nmdc_study: Any,
     ncbi_exporter_metadata: dict,
     biosamples: list,
     data_objects: list,
 ) -> str:
-    ncbi_exporter = NCBISubmissionXML(nmdc_study_id, ncbi_exporter_metadata)
+    ncbi_exporter = NCBISubmissionXML(nmdc_study, ncbi_exporter_metadata)
     ncbi_xml = ncbi_exporter.get_submission_xml(biosamples, data_objects)
     return ncbi_xml

nmdc_runtime/site/repository.py

@@ -882,7 +882,7 @@ def biosample_export():
                     },
                 ),
                 "ops": {
-                    "get_ncbi_export_pipeline_study_id": {
+                    "get_ncbi_export_pipeline_study": {
                         "config": {
                             "nmdc_study_id": "",
                         }
@@ -891,16 +891,10 @@ def biosample_export():
                         "config": {
                             "nmdc_ncbi_attribute_mapping_file_url": "",
                             "ncbi_submission_metadata": {
-                                "email": "",
-                                "first": "",
-                                "last": "",
-                                "user": "",
                                 "organization": "",
                             },
                             "ncbi_bioproject_metadata": {
-                                "title": "",
                                 "project_id": "",
-                                "description": "",
                                 "data_type": "",
                                 "exists": False,
                             },