diff --git a/nmdc_runtime/site/export/ncbi_xml.py b/nmdc_runtime/site/export/ncbi_xml.py
new file mode 100644
index 00000000..27a4371d
--- /dev/null
+++ b/nmdc_runtime/site/export/ncbi_xml.py
@@ -0,0 +1,433 @@
+import os
+import datetime
+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,
+    handle_controlled_term_value,
+    handle_geolocation_value,
+    handle_quantity_value,
+    handle_text_value,
+    handle_timestamp_value,
+    handle_float_value,
+    handle_string_value,
+    load_mappings,
+    validate_xml,
+)
+
+
+class NCBISubmissionXML:
+    def __init__(self, nmdc_study: Any, ncbi_submission_metadata: dict):
+        self.root = ET.Element("Submission")
+
+        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"
+        )
+        self.ncbi_submission_metadata = ncbi_submission_metadata.get(
+            "ncbi_submission_metadata", {}
+        )
+        self.ncbi_biosample_metadata = ncbi_submission_metadata.get(
+            "ncbi_biosample_metadata", {}
+        )
+
+        # dispatcher dictionary capturing handlers for NMDC object to NCBI flat Attribute
+        # type handlers
+        self.type_handlers = {
+            "QuantityValue": handle_quantity_value,
+            "TextValue": handle_text_value,
+            "TimestampValue": handle_timestamp_value,
+            "ControlledTermValue": handle_controlled_term_value,
+            "ControlledIdentifiedTermValue": handle_controlled_identified_term_value,
+            "GeolocationValue": handle_geolocation_value,
+            "float": handle_float_value,
+            "string": handle_string_value,
+        }
+
+    def set_element(self, tag, text="", attrib=None, children=None):
+        attrib = attrib or {}
+        children = children or []
+        element = ET.Element(tag, attrib=attrib)
+        element.text = text
+        for child in children:
+            element.append(child)
+        return element
+
+    def set_description(self, email, user, first, last, org, date=None):
+        date = date or datetime.datetime.now().strftime("%Y-%m-%d")
+        description = self.set_element(
+            "Description",
+            children=[
+                self.set_element(
+                    "Comment", f"NMDC Submission for {self.nmdc_study_id}"
+                ),
+                self.set_element("Submitter", attrib={"user_name": user}),
+                self.set_element(
+                    "Organization",
+                    attrib={"role": "owner", "type": "center"},
+                    children=[
+                        self.set_element("Name", org),
+                        self.set_element(
+                            "Contact",
+                            attrib={"email": email},
+                            children=[
+                                self.set_element(
+                                    "Name",
+                                    children=[
+                                        self.set_element("First", first),
+                                        self.set_element("Last", last),
+                                    ],
+                                )
+                            ],
+                        ),
+                    ],
+                ),
+                self.set_element("Hold", attrib={"release_date": date}),
+            ],
+        )
+        self.root.append(description)
+
+    def set_descriptor(self, title, description):
+        descriptor_elements = []
+        descriptor_elements.append(self.set_element("Title", title))
+        descriptor_elements.append(
+            self.set_element(
+                "Description", children=[self.set_element("p", description)]
+            )
+        )
+
+        return descriptor_elements
+
+    def set_bioproject(self, title, project_id, description, data_type, org):
+        action = self.set_element("Action")
+        add_data = self.set_element("AddData", attrib={"target_db": "BioProject"})
+
+        data_element = self.set_element("Data", attrib={"content_type": "XML"})
+        xml_content = self.set_element("XmlContent")
+        project = self.set_element("Project", attrib={"schema_version": "2.0"})
+
+        project_id_element = self.set_element("ProjectID")
+        spuid = self.set_element("SPUID", project_id, {"spuid_namespace": org})
+        project_id_element.append(spuid)
+
+        descriptor = self.set_descriptor(title, description)
+        project_type = self.set_element("ProjectType")
+        # "sample_scope" is a enumeration feild. Docs: https://www.ncbi.nlm.nih.gov/data_specs/schema/other/bioproject/Core.xsd
+        # scope is "eEnvironment" when "Content of species in a sample is not known, i.e. microbiome,metagenome, etc.."
+        project_type_submission = self.set_element(
+            "ProjectTypeSubmission", attrib={"sample_scope": "eEnvironment"}
+        )
+        intended_data_type_set = self.set_element("IntendedDataTypeSet")
+        data_type_element = self.set_element("DataType", data_type)
+
+        intended_data_type_set.append(data_type_element)
+        project_type_submission.append(intended_data_type_set)
+        project_type.append(project_type_submission)
+
+        project.extend([project_id_element] + descriptor + [project_type])
+
+        xml_content.append(project)
+        data_element.append(xml_content)
+        add_data.append(data_element)
+
+        identifier = self.set_element("Identifier")
+        spuid_identifier = self.set_element(
+            "SPUID", project_id, {"spuid_namespace": org}
+        )
+        identifier.append(spuid_identifier)
+        add_data.append(identifier)
+
+        action.append(add_data)
+        self.root.append(action)
+
+    def set_biosample(
+        self,
+        organism_name,
+        org,
+        bioproject_id,
+        nmdc_biosamples,
+        nmdc_omics_processing,
+    ):
+        attribute_mappings, slot_range_mappings = load_mappings(
+            self.nmdc_ncbi_attribute_mapping_file_url
+        )
+
+        for biosample in nmdc_biosamples:
+            attributes = {}
+            sample_id_value = None
+            env_package = None
+
+            for json_key, value in biosample.items():
+                if isinstance(value, list):
+                    continue  # Skip processing for list values
+
+                if json_key == "env_package":
+                    env_package = f"MIMS.me.{handle_text_value(value)}.6.0"
+
+                # Special handling for NMDC Biosample "id"
+                if json_key == "id":
+                    sample_id_value = value
+                    continue
+
+                if json_key not in attribute_mappings:
+                    continue
+
+                xml_key = attribute_mappings[json_key]
+                value_type = slot_range_mappings.get(json_key, "string")
+                handler = self.type_handlers.get(value_type, handle_string_value)
+
+                formatted_value = handler(value)
+                attributes[xml_key] = formatted_value
+
+            biosample_elements = [
+                self.set_element(
+                    "SampleId",
+                    children=[
+                        self.set_element(
+                            "SPUID", sample_id_value, {"spuid_namespace": org}
+                        )
+                    ],
+                ),
+                self.set_element(
+                    "Descriptor",
+                    children=[
+                        self.set_element(
+                            "Title",
+                            f"NMDC Biosample {sample_id_value} from {organism_name} part of {self.nmdc_study_id} study",
+                        ),
+                    ],
+                ),
+                self.set_element(
+                    "Organism",
+                    children=[self.set_element("OrganismName", organism_name)],
+                ),
+                self.set_element(
+                    "BioProject",
+                    children=[
+                        self.set_element(
+                            "PrimaryId", bioproject_id, {"db": "BioProject"}
+                        )
+                    ],
+                ),
+                self.set_element("Package", env_package),
+                self.set_element(
+                    "Attributes",
+                    children=[
+                        self.set_element(
+                            "Attribute", attributes[key], {"attribute_name": key}
+                        )
+                        for key in sorted(attributes)
+                    ],
+                ),
+            ]
+
+            action = self.set_element(
+                "Action",
+                children=[
+                    self.set_element(
+                        "AddData",
+                        attrib={"target_db": "BioSample"},
+                        children=[
+                            self.set_element(
+                                "Data",
+                                attrib={"content_type": "XML"},
+                                children=[
+                                    self.set_element(
+                                        "XmlContent",
+                                        children=[
+                                            self.set_element(
+                                                "BioSample",
+                                                attrib={"schema_version": "2.0"},
+                                                children=biosample_elements,
+                                            ),
+                                        ],
+                                    ),
+                                ],
+                            ),
+                            self.set_element(
+                                "Identifier",
+                                children=[
+                                    self.set_element(
+                                        "SPUID",
+                                        sample_id_value,
+                                        {"spuid_namespace": org},
+                                    ),
+                                ],
+                            ),
+                        ],
+                    ),
+                ],
+            )
+            self.root.append(action)
+
+    def set_fastq(
+        self,
+        biosample_data_objects: list,
+        bioproject_id: str,
+        org: str,
+    ):
+        for entry in biosample_data_objects:
+            fastq_files = []
+            biosample_ids = []
+
+            for biosample_id, data_objects in entry.items():
+                biosample_ids.append(biosample_id)
+                for data_object in data_objects:
+                    if "url" in data_object:
+                        url = urlparse(data_object["url"])
+                        file_path = os.path.join(
+                            os.path.basename(os.path.dirname(url.path)),
+                            os.path.basename(url.path),
+                        )
+                        fastq_files.append(file_path)
+
+            if fastq_files:
+                files_elements = [
+                    self.set_element(
+                        "File",
+                        "",
+                        {"file_path": f},
+                        [self.set_element("DataType", "generic-data")],
+                    )
+                    for f in fastq_files
+                ]
+
+                attribute_elements = [
+                    self.set_element(
+                        "AttributeRefId",
+                        attrib={"name": "BioProject"},
+                        children=[
+                            self.set_element(
+                                "RefId",
+                                children=[
+                                    self.set_element(
+                                        "SPUID",
+                                        bioproject_id,
+                                        {"spuid_namespace": org},
+                                    )
+                                ],
+                            )
+                        ],
+                    )
+                ]
+
+                for biosample_id in biosample_ids:
+                    attribute_elements.append(
+                        self.set_element(
+                            "AttributeRefId",
+                            attrib={"name": "BioSample"},
+                            children=[
+                                self.set_element(
+                                    "RefId",
+                                    children=[
+                                        self.set_element(
+                                            "SPUID",
+                                            biosample_id,
+                                            {"spuid_namespace": org},
+                                        )
+                                    ],
+                                )
+                            ],
+                        )
+                    )
+
+                identifier_element = self.set_element(
+                    "Identifier",
+                    children=[
+                        self.set_element(
+                            "SPUID", bioproject_id, {"spuid_namespace": org}
+                        )
+                    ],
+                )
+
+                action = self.set_element(
+                    "Action",
+                    children=[
+                        self.set_element(
+                            "AddFiles",
+                            attrib={"target_db": "SRA"},
+                            children=files_elements
+                            + attribute_elements
+                            + [identifier_element],
+                        ),
+                    ],
+                )
+
+                self.root.append(action)
+
+    def get_submission_xml(
+        self,
+        biosamples_list: list,
+        biosample_omics_processing_list: list,
+        biosample_data_objects_list: list,
+    ):
+        data_type = None
+        ncbi_project_id = None
+        for bsm_omprc in biosample_omics_processing_list:
+            for _, omprc_list in bsm_omprc.items():
+                for omprc in omprc_list:
+                    if "omics_type" in omprc:
+                        data_type = handle_text_value(omprc["omics_type"]).capitalize()
+
+                    if "ncbi_project_name" in omprc:
+                        ncbi_project_id = omprc["ncbi_project_name"]
+
+        self.set_description(
+            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 ncbi_project_id:
+            self.set_bioproject(
+                title=self.nmdc_study_title,
+                project_id=ncbi_project_id,
+                description=self.nmdc_study_description,
+                data_type=data_type,
+                org=self.ncbi_submission_metadata.get("organization", ""),
+            )
+
+        self.set_biosample(
+            organism_name=self.ncbi_biosample_metadata.get("organism_name", ""),
+            org=self.ncbi_submission_metadata.get("organization", ""),
+            bioproject_id=ncbi_project_id,
+            nmdc_biosamples=biosamples_list,
+            nmdc_omics_processing=biosample_omics_processing_list,
+        )
+
+        self.set_fastq(
+            biosample_data_objects=biosample_data_objects_list,
+            bioproject_id=ncbi_project_id,
+            org=self.ncbi_submission_metadata.get("organization", ""),
+        )
+
+        rough_string = ET.tostring(self.root, "unicode")
+        reparsed = xml.dom.minidom.parseString(rough_string)
+        submission_xml = reparsed.toprettyxml(indent="    ", newl="\n")
+
+        # ============= Uncomment the following code to validate the XML against NCBI XSDs ============ #
+        # submission_xsd_url = "https://www.ncbi.nlm.nih.gov/viewvc/v1/trunk/submit/public-docs/common/submission.xsd?view=co"
+        # validate_xml(submission_xml, submission_xsd_url)
+
+        # bioproject_xsd_url = "https://www.ncbi.nlm.nih.gov/viewvc/v1/trunk/submit/public-docs/bioproject/bioproject.xsd?view=co"
+        # validate_xml(submission_xml, bioproject_xsd_url)
+
+        # biosample_xsd_url = "https://www.ncbi.nlm.nih.gov/viewvc/v1/trunk/submit/public-docs/biosample/biosample.xsd?view=co"
+        # validate_xml(submission_xml, biosample_xsd_url)
+
+        return submission_xml
diff --git a/nmdc_runtime/site/export/ncbi_xml_utils.py b/nmdc_runtime/site/export/ncbi_xml_utils.py
new file mode 100644
index 00000000..e527245e
--- /dev/null
+++ b/nmdc_runtime/site/export/ncbi_xml_utils.py
@@ -0,0 +1,206 @@
+from io import BytesIO, StringIO
+from nmdc_runtime.minter.config import typecodes
+from lxml import etree
+
+import csv
+import requests
+
+
+def _build_class_map(class_map_data):
+    return {
+        entry["name"]: entry["schema_class"].split(":")[1] for entry in class_map_data
+    }
+
+
+def get_classname_from_typecode(doc_id):
+    class_map_data = typecodes()
+    class_map = _build_class_map(class_map_data)
+
+    typecode = doc_id.split(":")[1].split("-")[0]
+    return class_map.get(typecode)
+
+
+def fetch_data_objects_from_biosamples(all_docs_collection, biosamples_list):
+    biosample_data_objects = []
+
+    for biosample in biosamples_list:
+        current_ids = [biosample["id"]]
+        collected_data_objects = []
+
+        while current_ids:
+            new_current_ids = []
+            for current_id in current_ids:
+                query = {"has_input": current_id}
+                document = all_docs_collection.find_one(query)
+
+                if not document:
+                    continue
+
+                has_output = document.get("has_output")
+                if not has_output:
+                    continue
+
+                for output_id in has_output:
+                    if get_classname_from_typecode(output_id) == "DataObject":
+                        data_object_doc = all_docs_collection.find_one(
+                            {"id": output_id}
+                        )
+                        if data_object_doc:
+                            collected_data_objects.append(data_object_doc)
+                    else:
+                        new_current_ids.append(output_id)
+
+            current_ids = new_current_ids
+
+        if collected_data_objects:
+            biosample_data_objects.append({biosample["id"]: collected_data_objects})
+
+    return biosample_data_objects
+
+
+def fetch_omics_processing_from_biosamples(all_docs_collection, biosamples_list):
+    biosample_data_objects = []
+
+    for biosample in biosamples_list:
+        current_ids = [biosample["id"]]
+        collected_data_objects = []
+
+        while current_ids:
+            new_current_ids = []
+            for current_id in current_ids:
+                query = {"has_input": current_id}
+                document = all_docs_collection.find_one(query)
+
+                if not document:
+                    continue
+
+                has_output = document.get("has_output")
+                if not has_output:
+                    continue
+
+                for output_id in has_output:
+                    if get_classname_from_typecode(output_id) == "DataObject":
+                        omics_processing_doc = all_docs_collection.find_one(
+                            {"id": document["id"]}
+                        )
+                        if omics_processing_doc:
+                            collected_data_objects.append(omics_processing_doc)
+                    else:
+                        new_current_ids.append(output_id)
+
+            current_ids = new_current_ids
+
+        if collected_data_objects:
+            biosample_data_objects.append({biosample["id"]: collected_data_objects})
+
+    return biosample_data_objects
+
+
+def handle_quantity_value(slot_value):
+    if "has_numeric_value" in slot_value and "has_unit" in slot_value:
+        return f"{slot_value['has_numeric_value']} {slot_value['has_unit']}"
+    elif (
+        "has_maximum_numeric_value" in slot_value
+        and "has_minimum_numeric_value" in slot_value
+        and "has_unit" in slot_value
+    ):
+        range_value = (
+            slot_value["has_maximum_numeric_value"]
+            - slot_value["has_minimum_numeric_value"]
+        )
+        return f"{range_value} {slot_value['has_unit']}"
+    elif "has_raw_value" in slot_value:
+        return slot_value["has_raw_value"]
+    return "Unknown format"
+
+
+def handle_text_value(slot_value):
+    return slot_value.get("has_raw_value", "Unknown format")
+
+
+def handle_timestamp_value(slot_value):
+    return slot_value.get("has_raw_value", "Unknown format")
+
+
+def handle_controlled_term_value(slot_value):
+    if "term" in slot_value:
+        term = slot_value["term"]
+        if "name" in term and "id" in term:
+            return f"{term['name']} [{term['id']}]"
+        elif "id" in term:
+            return term["id"]
+        elif "name" in term:
+            return term["name"]
+    elif "has_raw_value" in slot_value:
+        return slot_value["has_raw_value"]
+    return "Unknown format"
+
+
+def handle_controlled_identified_term_value(slot_value):
+    if "term" in slot_value:
+        term = slot_value["term"]
+        if "name" in term and "id" in term:
+            return f"{term['name']} [{term['id']}]"
+        elif "id" in term:
+            return term["id"]
+    elif "has_raw_value" in slot_value:
+        return slot_value["has_raw_value"]
+    return "Unknown format"
+
+
+def handle_geolocation_value(slot_value):
+    if "latitude" in slot_value and "longitude" in slot_value:
+        return f"{slot_value['latitude']} {slot_value['longitude']}"
+    elif "has_raw_value" in slot_value:
+        return slot_value["has_raw_value"]
+    return "Unknown format"
+
+
+def handle_float_value(slot_value):
+    return f"{slot_value:.2f}"
+
+
+def handle_string_value(slot_value):
+    return f"{slot_value}"
+
+
+def load_mappings(url):
+    response = requests.get(url)
+    response.raise_for_status()
+    file_content = response.text
+
+    attribute_mappings = {}
+    slot_range_mappings = {}
+    reader = csv.DictReader(StringIO(file_content), delimiter="\t")
+    for row in reader:
+        if row["ignore"].strip():
+            continue
+
+        json_key = row["nmdc_schema_slot"]
+        # attribute mappings
+        xml_attribute_name = row["ncbi_biosample_attribute_name"]
+        attribute_mappings[json_key] = (
+            xml_attribute_name if xml_attribute_name else json_key
+        )
+
+        # slot range mappings
+        data_type = row["nmdc_schema_slot_range"]
+        slot_range_mappings[json_key] = data_type if data_type else "default"
+
+    return attribute_mappings, slot_range_mappings
+
+
+def validate_xml(xml, xsd_url):
+    response = requests.get(xsd_url)
+    response.raise_for_status()
+    xsd_content = response.text
+
+    xml_schema_doc = etree.parse(BytesIO(xsd_content.encode("utf-8")))
+    xml_schema = etree.XMLSchema(xml_schema_doc)
+
+    xml_doc = etree.parse(BytesIO(xml.encode("utf-8")))
+
+    if not xml_schema.validate(xml_doc):
+        raise ValueError(f"There were errors while validating against: {xsd_url}")
+
+    return True
diff --git a/nmdc_runtime/site/export/study_metadata.py b/nmdc_runtime/site/export/study_metadata.py
index cdcfef8e..d9bb2a97 100644
--- a/nmdc_runtime/site/export/study_metadata.py
+++ b/nmdc_runtime/site/export/study_metadata.py
@@ -5,7 +5,6 @@
 import csv
 from io import StringIO
 
-import requests
 from dagster import (
     op,
     get_dagster_logger,
@@ -26,13 +25,27 @@ def get_all_docs(client, collection, filter_):
     per_page = 200
     url_base = f"/{collection}?filter={filter_}&per_page={per_page}"
     results = []
-    rv = client.request("GET", url_base).json()
+    response = client.request("GET", url_base)
+    if response.status_code != 200:
+        raise Exception(
+            f"Runtime API request failed with status {response.status_code}."
+            f" Check URL: {url_base}"
+        )
+    rv = response.json()
     results.extend(rv.get("results", []))
     page, count = rv["meta"]["page"], rv["meta"]["count"]
     assert count <= 10_000
     while page * per_page < count:
-        rv = requests.get(url_base + f"&page={page + 1}").json()
-        results.extend(rv["results"])
+        page += 1
+        url = f"{url_base}&page={page}"
+        response = client.request("GET", url)
+        if response.status_code != 200:
+            raise Exception(
+                f"Runtime API request failed with status {response.status_code}."
+                f" Check URL: {url}"
+            )
+        rv = response.json()
+        results.extend(rv.get("results", []))
     return results
 
 
@@ -115,3 +128,10 @@ def export_study_biosamples_as_csv(context: OpExecutionContext, study_export_inf
 def export_study_biosamples_metadata():
     outputs = export_study_biosamples_as_csv(get_study_biosamples_metadata())
     add_output_run_event(outputs)
+
+
+@op(required_resource_keys={"runtime_api_site_client"})
+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']}")
+    return biosamples
diff --git a/nmdc_runtime/site/graphs.py b/nmdc_runtime/site/graphs.py
index 5b21ac01..ae3ccd76 100644
--- a/nmdc_runtime/site/graphs.py
+++ b/nmdc_runtime/site/graphs.py
@@ -48,7 +48,14 @@
     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
@@ -369,3 +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)
diff --git a/nmdc_runtime/site/ops.py b/nmdc_runtime/site/ops.py
index f4ff3577..4bd00f3b 100644
--- a/nmdc_runtime/site/ops.py
+++ b/nmdc_runtime/site/ops.py
@@ -9,6 +9,7 @@
 from io import BytesIO, StringIO
 from typing import Tuple
 from zipfile import ZipFile
+
 import pandas as pd
 import requests
 
@@ -29,10 +30,14 @@
     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.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 @@
     _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,
@@ -724,6 +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}
 
@@ -933,3 +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
diff --git a/nmdc_runtime/site/repository.py b/nmdc_runtime/site/repository.py
index c0de4366..98b3dedb 100644
--- a/nmdc_runtime/site/repository.py
+++ b/nmdc_runtime/site/repository.py
@@ -42,6 +42,7 @@
     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,
@@ -850,6 +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]
diff --git a/nmdc_runtime/site/workspace.yaml b/nmdc_runtime/site/workspace.yaml
index e594197e..5da09ab9 100644
--- a/nmdc_runtime/site/workspace.yaml
+++ b/nmdc_runtime/site/workspace.yaml
@@ -11,6 +11,9 @@ load_from:
   - python_package:
       package_name: nmdc_runtime.site.repository
       attribute: biosample_submission_ingest
+  - python_package:
+      package_name: nmdc_runtime.site.repository
+      attribute: biosample_export
 #  - python_package:
 #      package_name: nmdc_runtime.site.repository
 #      attribute: validation
diff --git a/requirements/dev.in b/requirements/dev.in
index dbe7b8e9..601370de 100644
--- a/requirements/dev.in
+++ b/requirements/dev.in
@@ -11,4 +11,5 @@ pytest-cov
 requests-mock
 setuptools
 twine
-requests-cache
\ No newline at end of file
+requests-cache
+pytest-mock
\ No newline at end of file
diff --git a/requirements/dev.txt b/requirements/dev.txt
index 0065d7ae..86cbbaea 100644
--- a/requirements/dev.txt
+++ b/requirements/dev.txt
@@ -45,12 +45,13 @@ exceptiongroup==1.2.0
     #   pytest
 flake8==7.1.0
     # via -r requirements/dev.in
-idna==3.6
+idna==3.7
     # via
     #   -c requirements/main.txt
     #   requests
 importlib-metadata==7.1.0
     # via
+    #   build
     #   keyring
     #   twine
 iniconfig==2.0.0
@@ -67,6 +68,10 @@ jaraco-functools==4.0.1
     # via keyring
 keyring==25.2.1
     # via twine
+lxml==5.2.2
+    # via
+    #   -c requirements/main.txt
+    #   -r requirements/dev.in
 markdown-it-py==3.0.0
     # via
     #   -c requirements/main.txt
@@ -85,7 +90,7 @@ mypy-extensions==1.0.0
     # via black
 nh3==0.2.17
     # via readme-renderer
-packaging==23.2
+packaging==24.0
     # via
     #   -c requirements/main.txt
     #   black
@@ -99,12 +104,12 @@ pip-tools==7.4.1
     # via -r requirements/dev.in
 pkginfo==1.11.1
     # via twine
-platformdirs==4.2.0
+platformdirs==4.2.2
     # via
     #   -c requirements/main.txt
     #   black
     #   requests-cache
-pluggy==1.4.0
+pluggy==1.5.0
     # via
     #   -c requirements/main.txt
     #   pytest
@@ -121,7 +126,7 @@ pyproject-hooks==1.1.0
     # via
     #   build
     #   pip-tools
-pytest==8.0.2
+pytest==8.2.0
     # via
     #   -c requirements/main.txt
     #   -r requirements/dev.in
@@ -131,6 +136,10 @@ pytest-asyncio==0.23.7
     # via -r requirements/dev.in
 pytest-cov==5.0.0
     # via -r requirements/dev.in
+pytest-mock==3.14.0
+    # via
+    #   -c requirements/main.txt
+    #   -r requirements/dev.in
 readme-renderer==43.0
     # via twine
 requests==2.31.0
@@ -170,7 +179,7 @@ tomli==2.0.1
     #   pytest
 twine==5.1.0
     # via -r requirements/dev.in
-typing-extensions==4.10.0
+typing-extensions==4.11.0
     # via
     #   -c requirements/main.txt
     #   black
@@ -179,7 +188,7 @@ url-normalize==1.4.3
     # via
     #   -c requirements/main.txt
     #   requests-cache
-urllib3==2.0.7
+urllib3==2.2.1
     # via
     #   -c requirements/main.txt
     #   requests
@@ -195,7 +204,7 @@ pip==24.0
     # via
     #   -r requirements/dev.in
     #   pip-tools
-setuptools==69.1.1
+setuptools==69.5.1
     # via
     #   -c requirements/main.txt
     #   -r requirements/dev.in
diff --git a/requirements/main.in b/requirements/main.in
index e491c543..2ae359d7 100644
--- a/requirements/main.in
+++ b/requirements/main.in
@@ -20,6 +20,7 @@ jupyter
 jupyterlab
 linkml
 linkml-runtime
+lxml
 mkdocs-jupyter
 mkdocs-material
 mkdocs-mermaid2-plugin
diff --git a/requirements/main.txt b/requirements/main.txt
index eb8eafbe..9facde66 100644
--- a/requirements/main.txt
+++ b/requirements/main.txt
@@ -48,9 +48,9 @@ backoff==2.2.1
     # via gql
 base32-lib==1.0.2
     # via -r requirements/main.in
-bcrypt==4.1.2
+bcrypt==4.1.3
     # via passlib
-beanie==1.25.0
+beanie==1.26.0
     # via -r requirements/main.in
 beautifulsoup4==4.12.3
     # via
@@ -59,9 +59,9 @@ beautifulsoup4==4.12.3
     #   nbconvert
 bleach==6.1.0
     # via nbconvert
-boto3==1.34.54
+boto3==1.34.106
     # via -r requirements/main.in
-botocore==1.34.54
+botocore==1.34.106
     # via
     #   boto3
     #   s3transfer
@@ -104,31 +104,31 @@ comm==0.2.1
     # via
     #   ipykernel
     #   ipywidgets
-croniter==2.0.2
+croniter==2.0.5
     # via dagster
-cryptography==42.0.5
+cryptography==42.0.7
     # via python-jose
-curies==0.7.7
+curies==0.7.9
     # via
     #   linkml-runtime
     #   prefixmaps
-dagit==1.6.8
+dagit==1.7.5
     # via -r requirements/main.in
-dagster==1.6.8
+dagster==1.7.5
     # via
     #   -r requirements/main.in
     #   dagster-graphql
     #   dagster-postgres
     #   dagster-webserver
-dagster-graphql==1.6.8
+dagster-graphql==1.7.5
     # via
     #   -r requirements/main.in
     #   dagster-webserver
-dagster-pipes==1.6.8
+dagster-pipes==1.7.5
     # via dagster
-dagster-postgres==0.22.8
+dagster-postgres==0.23.5
     # via -r requirements/main.in
-dagster-webserver==1.6.8
+dagster-webserver==1.7.5
     # via dagit
 debugpy==1.8.1
     # via ipykernel
@@ -144,19 +144,21 @@ dnspython==2.6.1
     # via
     #   email-validator
     #   pymongo
-docstring-parser==0.15
+docstring-parser==0.16
     # via dagster
 dotted-dict==1.1.3
     # via -r requirements/main.in
-ecdsa==0.18.0
+ecdsa==0.19.0
     # via python-jose
 editorconfig==0.12.4
     # via jsbeautifier
 email-validator==2.1.1
-    # via pydantic
+    # via
+    #   fastapi
+    #   pydantic
 et-xmlfile==1.1.0
     # via openpyxl
-exceptiongroup==1.2.0
+exceptiongroup==1.2.1
     # via
     #   anyio
     #   cattrs
@@ -164,19 +166,25 @@ exceptiongroup==1.2.0
     #   pytest
 executing==2.0.1
     # via stack-data
-fastapi==0.110.0
-    # via -r requirements/main.in
+fastapi==0.111.0
+    # via
+    #   -r requirements/main.in
+    #   fastapi-cli
+fastapi-cli==0.0.3
+    # via fastapi
 fastjsonschema==2.19.1
     # via
     #   -r requirements/main.in
     #   nbformat
+filelock==3.14.0
+    # via dagster
 fnc==0.5.3
     # via -r requirements/main.in
 fqdn==1.5.1
     # via jsonschema
-frozendict==2.4.0
+frozendict==2.4.4
     # via -r requirements/main.in
-fsspec==2024.2.0
+fsspec==2024.5.0
     # via universal-pathlib
 ghp-import==2.1.0
     # via mkdocs
@@ -193,13 +201,15 @@ graphql-core==3.2.3
     #   graphql-relay
 graphql-relay==3.2.0
     # via graphene
-graphviz==0.20.1
+graphviz==0.20.3
     # via linkml
-grpcio==1.62.0
+greenlet==3.0.3
+    # via sqlalchemy
+grpcio==1.63.0
     # via
     #   dagster
     #   grpcio-health-checking
-grpcio-health-checking==1.62.0
+grpcio-health-checking==1.62.2
     # via dagster
 h11==0.14.0
     # via
@@ -210,15 +220,17 @@ hbreader==0.9.1
     #   jsonasobj2
     #   linkml
     #   linkml-runtime
-httpcore==1.0.4
+httpcore==1.0.5
     # via httpx
 httptools==0.6.1
     # via uvicorn
 httpx==0.27.0
-    # via jupyterlab
+    # via
+    #   fastapi
+    #   jupyterlab
 humanfriendly==10.0
     # via coloredlogs
-idna==3.6
+idna==3.7
     # via
     #   anyio
     #   email-validator
@@ -228,14 +240,14 @@ idna==3.6
     #   yarl
 iniconfig==2.0.0
     # via pytest
-ipykernel==6.29.3
+ipykernel==6.29.4
     # via
     #   jupyter
     #   jupyter-console
     #   jupyterlab
     #   mkdocs-jupyter
     #   qtconsole
-ipython==8.22.1
+ipython==8.24.0
     # via
     #   ipykernel
     #   ipywidgets
@@ -250,9 +262,10 @@ isoduration==20.11.0
     # via jsonschema
 jedi==0.19.1
     # via ipython
-jinja2==3.1.3
+jinja2==3.1.4
     # via
     #   dagster
+    #   fastapi
     #   jupyter-server
     #   jupyterlab
     #   jupyterlab-server
@@ -265,13 +278,13 @@ jmespath==1.0.1
     # via
     #   boto3
     #   botocore
-jq==1.6.0
+jq==1.7.0
     # via -r requirements/main.in
 jsbeautifier==1.15.1
     # via mkdocs-mermaid2-plugin
 json-flattener==0.1.9
     # via linkml-runtime
-json5==0.9.18
+json5==0.9.25
     # via jupyterlab-server
 jsonasobj==1.3.1
     # via
@@ -290,7 +303,7 @@ jsonpointer==2.4
     # via
     #   jsonpatch
     #   jsonschema
-jsonschema==4.21.1
+jsonschema==4.22.0
     # via
     #   jupyter-events
     #   jupyterlab-server
@@ -301,7 +314,7 @@ jsonschema-specifications==2023.12.1
     # via jsonschema
 jupyter==1.0.0
     # via -r requirements/main.in
-jupyter-client==8.6.0
+jupyter-client==8.6.1
     # via
     #   ipykernel
     #   jupyter-console
@@ -310,7 +323,7 @@ jupyter-client==8.6.0
     #   qtconsole
 jupyter-console==6.6.3
     # via jupyter
-jupyter-core==5.7.1
+jupyter-core==5.7.2
     # via
     #   ipykernel
     #   jupyter-client
@@ -321,32 +334,32 @@ jupyter-core==5.7.1
     #   nbconvert
     #   nbformat
     #   qtconsole
-jupyter-events==0.9.0
+jupyter-events==0.10.0
     # via jupyter-server
-jupyter-lsp==2.2.3
+jupyter-lsp==2.2.5
     # via jupyterlab
-jupyter-server==2.12.5
+jupyter-server==2.14.0
     # via
     #   jupyter-lsp
     #   jupyterlab
     #   jupyterlab-server
     #   notebook
     #   notebook-shim
-jupyter-server-terminals==0.5.2
+jupyter-server-terminals==0.5.3
     # via jupyter-server
-jupyterlab==4.1.2
+jupyterlab==4.1.8
     # via
     #   -r requirements/main.in
     #   notebook
 jupyterlab-pygments==0.3.0
     # via nbconvert
-jupyterlab-server==2.25.3
+jupyterlab-server==2.27.1
     # via
     #   jupyterlab
     #   notebook
 jupyterlab-widgets==3.0.10
     # via ipywidgets
-jupytext==1.16.1
+jupytext==1.16.2
     # via mkdocs-jupyter
 lazy-model==0.2.0
     # via beanie
@@ -356,15 +369,17 @@ linkml==1.7.5
     #   nmdc-schema
 linkml-dataops==0.1.0
     # via linkml
-linkml-runtime==1.7.2
+linkml-runtime==1.7.5
     # via
     #   -r requirements/main.in
     #   linkml
     #   linkml-dataops
     #   nmdc-schema
-mako==1.3.2
+lxml==5.2.2
+    # via -r requirements/main.in
+mako==1.3.5
     # via alembic
-markdown==3.5.2
+markdown==3.6
     # via
     #   mkdocs
     #   mkdocs-material
@@ -380,28 +395,32 @@ markupsafe==2.1.5
     #   mako
     #   mkdocs
     #   nbconvert
-matplotlib-inline==0.1.6
+matplotlib-inline==0.1.7
     # via
     #   ipykernel
     #   ipython
-mdit-py-plugins==0.4.0
+mdit-py-plugins==0.4.1
     # via jupytext
 mdurl==0.1.2
     # via markdown-it-py
 mergedeep==1.3.4
-    # via mkdocs
+    # via
+    #   mkdocs
+    #   mkdocs-get-deps
 mistune==3.0.2
     # via nbconvert
-mkdocs==1.5.3
+mkdocs==1.6.0
     # via
     #   mkdocs-jupyter
     #   mkdocs-material
     #   mkdocs-mermaid2-plugin
     #   mkdocs-redirects
     #   nmdc-schema
-mkdocs-jupyter==0.24.6
+mkdocs-get-deps==0.2.0
+    # via mkdocs
+mkdocs-jupyter==0.24.7
     # via -r requirements/main.in
-mkdocs-material==9.5.12
+mkdocs-material==9.5.23
     # via
     #   -r requirements/main.in
     #   mkdocs-jupyter
@@ -414,7 +433,9 @@ mkdocs-mermaid2-plugin==0.6.0
     #   nmdc-schema
 mkdocs-redirects==1.2.1
     # via nmdc-schema
-motor==3.3.2
+more-click==0.1.2
+    # via bioregistry
+motor==3.4.0
     # via
     #   -r requirements/main.in
     #   beanie
@@ -422,12 +443,12 @@ multidict==6.0.5
     # via yarl
 nbclient==0.9.0
     # via nbconvert
-nbconvert==7.16.1
+nbconvert==7.16.4
     # via
     #   jupyter
     #   jupyter-server
     #   mkdocs-jupyter
-nbformat==5.9.2
+nbformat==5.10.4
     # via
     #   jupyter-server
     #   jupytext
@@ -437,7 +458,7 @@ nest-asyncio==1.6.0
     # via ipykernel
 nmdc-schema==10.5.5
     # via -r requirements/main.in
-notebook==7.1.1
+notebook==7.1.3
     # via jupyter
 notebook-shim==0.2.4
     # via
@@ -449,9 +470,11 @@ openpyxl==3.1.2
     # via
     #   -r requirements/main.in
     #   linkml
+orjson==3.10.3
+    # via fastapi
 overrides==7.7.0
     # via jupyter-server
-packaging==23.2
+packaging==24.0
     # via
     #   dagster
     #   ipykernel
@@ -473,7 +496,7 @@ pandocfilters==1.5.1
     # via nbconvert
 parse==1.20.1
     # via linkml
-parso==0.8.3
+parso==0.8.4
     # via jedi
 passlib==1.7.4
     # via -r requirements/main.in
@@ -483,12 +506,12 @@ pendulum==3.0.0
     # via dagster
 pexpect==4.9.0
     # via ipython
-platformdirs==4.2.0
+platformdirs==4.2.2
     # via
     #   jupyter-core
-    #   mkdocs
+    #   mkdocs-get-deps
     #   requests-cache
-pluggy==1.4.0
+pluggy==1.5.0
     # via pytest
 ply==3.11
     # via jsonpath-ng
@@ -496,7 +519,7 @@ prefixcommons==0.1.12
     # via
     #   linkml
     #   linkml-runtime
-prefixmaps==0.2.2
+prefixmaps==0.2.4
     # via
     #   linkml
     #   linkml-runtime
@@ -520,13 +543,13 @@ ptyprocess==0.7.0
     #   terminado
 pure-eval==0.2.2
     # via stack-data
-pyasn1==0.5.1
+pyasn1==0.6.0
     # via
     #   python-jose
     #   rsa
-pycparser==2.21
+pycparser==2.22
     # via cffi
-pydantic==2.6.3
+pydantic==2.7.1
     # via
     #   -r requirements/main.in
     #   beanie
@@ -536,7 +559,7 @@ pydantic==2.6.3
     #   lazy-model
     #   linkml
     #   linkml-runtime
-pydantic-core==2.16.3
+pydantic-core==2.18.2
     # via pydantic
 pygments==2.17.2
     # via
@@ -552,7 +575,7 @@ pyjsg==0.11.10
     #   linkml
     #   pyshexc
     #   shexjsg
-pymdown-extensions==10.7
+pymdown-extensions==10.8.1
     # via
     #   mkdocs-material
     #   mkdocs-mermaid2-plugin
@@ -561,7 +584,7 @@ pymongo==4.7.3
     #   -r requirements/main.in
     #   motor
     #   nmdc-schema
-pyparsing==3.1.1
+pyparsing==3.1.2
     # via rdflib
 pyshex==0.8.1
     # via linkml
@@ -569,10 +592,16 @@ pyshexc==0.9.1
     # via
     #   linkml
     #   pyshex
-pytest==8.0.2
-    # via pytest-logging
+pystow==0.5.4
+    # via bioregistry
+pytest==8.2.0
+    # via
+    #   pytest-logging
+    #   pytest-mock
 pytest-logging==2015.11.4
     # via prefixcommons
+pytest-mock==3.14.0
+    # via -r requirements/main.in
 python-dateutil==2.9.0.post0
     # via
     #   arrow
@@ -595,7 +624,9 @@ python-jose==3.3.0
 python-json-logger==2.0.7
     # via jupyter-events
 python-multipart==0.0.9
-    # via -r requirements/main.in
+    # via
+    #   -r requirements/main.in
+    #   fastapi
 pytrie==0.4.0
     # via curies
 pytz==2024.1
@@ -613,6 +644,7 @@ pyyaml==6.0.1
     #   linkml
     #   linkml-runtime
     #   mkdocs
+    #   mkdocs-get-deps
     #   mkdocs-mermaid2-plugin
     #   prefixcommons
     #   prefixmaps
@@ -621,14 +653,14 @@ pyyaml==6.0.1
     #   uvicorn
 pyyaml-env-tag==0.1
     # via mkdocs
-pyzmq==25.1.2
+pyzmq==26.0.3
     # via
     #   ipykernel
     #   jupyter-client
     #   jupyter-console
     #   jupyter-server
     #   qtconsole
-qtconsole==5.5.1
+qtconsole==5.5.2
     # via jupyter
 qtpy==2.4.1
     # via qtconsole
@@ -648,12 +680,12 @@ rdflib-shim==1.0.3
     #   pyshex
     #   pyshexc
     #   sparqlslurper
-referencing==0.33.0
+referencing==0.35.1
     # via
     #   jsonschema
     #   jsonschema-specifications
     #   jupyter-events
-regex==2023.12.25
+regex==2024.5.15
     # via mkdocs-material
 requests==2.31.0
     # via
@@ -686,8 +718,10 @@ rfc3986-validator==0.1.1
 rfc3987==1.3.8
     # via jsonschema
 rich==13.7.1
-    # via dagster
-rpds-py==0.18.0
+    # via
+    #   dagster
+    #   typer
+rpds-py==0.18.1
     # via
     #   jsonschema
     #   referencing
@@ -697,13 +731,15 @@ ruamel-yaml==0.18.6
     # via linkml-dataops
 ruamel-yaml-clib==0.2.8
     # via ruamel-yaml
-s3transfer==0.10.0
+ruff==0.4.4
+    # via shed
+s3transfer==0.10.1
     # via boto3
 semver==3.0.2
     # via -r requirements/main.in
-send2trash==1.8.2
+send2trash==1.8.3
     # via jupyter-server
-setuptools-scm==8.0.4
+setuptools-scm==8.1.0
     # via -r requirements/main.in
 shexjsg==0.8.2
     # via
@@ -742,7 +778,7 @@ sqlalchemy==2.0.27
     #   linkml
 stack-data==0.6.3
     # via ipython
-starlette==0.36.3
+starlette==0.37.2
     # via
     #   dagster-graphql
     #   dagster-webserver
@@ -753,24 +789,23 @@ tabulate==0.9.0
     # via dagster
 tenacity==8.2.3
     # via -r requirements/main.in
-terminado==0.18.0
+terminado==0.18.1
     # via
     #   jupyter-server
     #   jupyter-server-terminals
 time-machine==2.13.0
     # via pendulum
-tinycss2==1.2.1
+tinycss2==1.3.0
     # via nbconvert
 toml==0.10.2
-    # via
-    #   beanie
-    #   jupytext
+    # via beanie
 tomli==2.0.1
     # via
     #   dagster
     #   jupyterlab
     #   pytest
     #   setuptools-scm
+    #   sphinx
 toolz==0.12.1
     # via -r requirements/main.in
 toposort==1.10
@@ -783,7 +818,7 @@ tornado==6.4
     #   jupyterlab
     #   notebook
     #   terminado
-tqdm==4.66.2
+tqdm==4.66.4
     # via
     #   -r requirements/main.in
     #   dagster
@@ -806,7 +841,7 @@ traitlets==5.14.1
     #   qtconsole
 types-python-dateutil==2.8.19.20240106
     # via arrow
-typing-extensions==4.10.0
+typing-extensions==4.11.0
     # via
     #   alembic
     #   anyio
@@ -817,29 +852,32 @@ typing-extensions==4.10.0
     #   fastapi
     #   pydantic
     #   pydantic-core
-    #   setuptools-scm
     #   sqlalchemy
     #   uvicorn
 tzdata==2024.1
     # via
     #   pandas
     #   pendulum
-universal-pathlib==0.2.1
+ujson==5.10.0
+    # via fastapi
+universal-pathlib==0.2.2
     # via dagster
 uri-template==1.3.0
     # via jsonschema
 url-normalize==1.4.3
     # via requests-cache
-urllib3==2.0.7
+urllib3==2.2.1
     # via
     #   botocore
     #   pyshex
     #   requests
     #   requests-cache
-uvicorn==0.27.1
+uvicorn==0.29.0
     # via
     #   -r requirements/main.in
     #   dagster-webserver
+    #   fastapi
+    #   fastapi-cli
 uvloop==0.19.0
     # via uvicorn
 watchdog==4.0.0
@@ -857,7 +895,7 @@ webencodings==0.5.1
     # via
     #   bleach
     #   tinycss2
-websocket-client==1.7.0
+websocket-client==1.8.0
     # via jupyter-server
 websockets==12.0
     # via uvicorn
@@ -873,7 +911,7 @@ yarl==1.9.4
     # via gql
 
 # The following packages are considered to be unsafe in a requirements file:
-setuptools==69.1.1
+setuptools==69.5.1
     # via
     #   dagster
     #   mkdocs-mermaid2-plugin
diff --git a/tests/test_data/test_ncbi_xml.py b/tests/test_data/test_ncbi_xml.py
new file mode 100644
index 00000000..7996b4d1
--- /dev/null
+++ b/tests/test_data/test_ncbi_xml.py
@@ -0,0 +1,540 @@
+from unittest.mock import MagicMock
+import pytest
+import xml.etree.ElementTree as ET
+
+from nmdc_runtime.site.export.ncbi_xml import NCBISubmissionXML
+from nmdc_runtime.site.export.ncbi_xml_utils import (
+    load_mappings,
+    handle_quantity_value,
+    handle_text_value,
+    handle_timestamp_value,
+    handle_controlled_term_value,
+    handle_controlled_identified_term_value,
+    handle_geolocation_value,
+    handle_float_value,
+    handle_string_value,
+)
+
+MOCK_NMDC_STUDY = {
+    "id": "nmdc:sty-11-34xj1150",
+    "name": "National Ecological Observatory Network: soil metagenomes (DP1.10107.001)",
+    "description": "This study contains the quality-controlled laboratory metadata and minimally processed sequence data from NEON's soil microbial shotgun metagenomics sequencing. Typically, measurements are done on plot-level composite samples and represent up to three randomly selected sampling locations within a plot.",
+    "gold_study_identifiers": ["gold:Gs0144570", "gold:Gs0161344"],
+    "principal_investigator": {
+        "has_raw_value": "Kate Thibault",
+        "email": "kthibault@battelleecology.org",
+        "name": "Kate Thibault",
+        "orcid": "orcid:0000-0003-3477-6424",
+        "profile_image_url": "https://portal.nersc.gov/project/m3408/profile_images/thibault_katy.jpg",
+    },
+    "title": "National Ecological Observatory Network: soil metagenomes (DP1.10107.001)",
+    "type": "nmdc:Study",
+    "websites": [
+        "https://data.neonscience.org/data-products/DP1.10107.001",
+        "https://data.neonscience.org/api/v0/documents/NEON.DOC.014048vO",
+        "https://data.neonscience.org/api/v0/documents/NEON_metagenomes_userGuide_vE.pdf",
+    ],
+    "study_image": [
+        {
+            "url": "https://portal.nersc.gov/project/m3408/profile_images/nmdc_sty-11-34xj1150.jpg"
+        }
+    ],
+    "funding_sources": [
+        "NSF#1724433 National Ecological Observatory Network: Operations Activities"
+    ],
+    "has_credit_associations": [
+        {
+            "applies_to_person": {
+                "name": "Hugh Cross",
+                "email": "crossh@battelleecology.org",
+                "orcid": "orcid:0000-0002-6745-9479",
+            },
+            "applied_roles": ["Methodology", "Data curation"],
+        },
+        {
+            "applies_to_person": {
+                "name": "Samantha Weintraub-Leff",
+                "email": "sweintraub@battelleecology.org",
+                "orcid": "orcid:0000-0003-4789-5086",
+            },
+            "applied_roles": ["Methodology", "Data curation"],
+        },
+        {
+            "applies_to_person": {
+                "name": "Kate Thibault",
+                "email": "kthibault@battelleecology.org",
+                "orcid": "orcid:0000-0003-3477-6424",
+            },
+            "applied_roles": ["Principal Investigator"],
+        },
+    ],
+    "part_of": ["nmdc:sty-11-nxrz9m96"],
+    "study_category": "consortium",
+    "insdc_bioproject_identifiers": ["bioproject:PRJNA1029061"],
+    "homepage_website": ["https://www.neonscience.org/"],
+}
+
+MOCK_NCBI_SUBMISSION_METADATA = {
+    "nmdc_ncbi_attribute_mapping_file_url": "http://example.com/mappings.tsv",
+    "ncbi_submission_metadata": {
+        "organization": "Test Org",
+    },
+    "ncbi_biosample_metadata": {
+        "organism_name": "E. coli",
+    },
+}
+
+
+@pytest.fixture
+def ncbi_submission_client():
+    return NCBISubmissionXML(
+        nmdc_study=MOCK_NMDC_STUDY,
+        ncbi_submission_metadata=MOCK_NCBI_SUBMISSION_METADATA,
+    )
+
+
+@pytest.fixture
+def nmdc_biosample():
+    return [
+        {
+            "analysis_type": ["metagenomics"],
+            "biosample_categories": ["NEON"],
+            "collection_date": {"has_raw_value": "2015-07-21T18:00Z"},
+            "depth": {
+                "has_maximum_numeric_value": 1,
+                "has_minimum_numeric_value": 0,
+                "has_unit": "meters",
+            },
+            "elev": 1179.5,
+            "env_broad_scale": {
+                "term": {"id": "ENVO:01000253", "name": "freshwater river biome"}
+            },
+            "env_local_scale": {"term": {"id": "ENVO:03600094", "name": "stream pool"}},
+            "env_medium": {"term": {"id": "ENVO:00002007", "name": "sediment"}},
+            "geo_loc_name": {"has_raw_value": "USA: Colorado, Arikaree River"},
+            "id": "nmdc:bsm-12-p9q5v236",
+            "lat_lon": {"latitude": 39.758206, "longitude": -102.447148},
+            "name": "ARIK.20150721.AMC.EPIPSAMMON.3",
+            "part_of": ["nmdc:sty-11-34xj1150"],
+            "type": "nmdc:Biosample",
+        }
+    ]
+
+
+@pytest.fixture
+def omics_processing_list():
+    return [
+        {
+            "has_input": ["nmdc:procsm-12-ehktny16"],
+            "has_output": ["nmdc:dobj-12-1zv4q961", "nmdc:dobj-12-b3ft7a80"],
+            "id": "nmdc:omprc-12-zqm9p096",
+            "instrument_name": "Illumina NextSeq550",
+            "name": "Terrestrial soil microbial communities - ARIK.20150721.AMC.EPIPSAMMON.3-DNA1",
+            "ncbi_project_name": "PRJNA406976",
+            "omics_type": {"has_raw_value": "metagenome"},
+            "part_of": ["nmdc:sty-11-34xj1150"],
+            "processing_institution": "Battelle",
+            "type": "nmdc:OmicsProcessing",
+        }
+    ]
+
+
+@pytest.fixture
+def data_objects_list():
+    return [
+        {
+            "data_object_type": "Metagenome Raw Read 1",
+            "description": "sequencing results for BMI_HVKNKBGX5_Tube347_R1",
+            "id": "nmdc:dobj-12-b3ft7a80",
+            "md5_checksum": "cae0a9342d786e731ae71f6f37b76120",
+            "name": "BMI_HVKNKBGX5_Tube347_R1.fastq.gz",
+            "type": "nmdc:DataObject",
+            "url": "https://storage.neonscience.org/neon-microbial-raw-seq-files/2023/BMI_HVKNKBGX5_mms_R1/BMI_HVKNKBGX5_Tube347_R1.fastq.gz",
+        },
+        {
+            "data_object_type": "Metagenome Raw Read 2",
+            "description": "sequencing results for BMI_HVKNKBGX5_Tube347_R2",
+            "id": "nmdc:dobj-12-1zv4q961",
+            "md5_checksum": "7340fe25644183a4f56d36ce52389d83",
+            "name": "BMI_HVKNKBGX5_Tube347_R2.fastq.gz",
+            "type": "nmdc:DataObject",
+            "url": "https://storage.neonscience.org/neon-microbial-raw-seq-files/2023/BMI_HVKNKBGX5_mms_R2/BMI_HVKNKBGX5_Tube347_R2.fastq.gz",
+        },
+    ]
+
+
+class TestNCBISubmissionXML:
+    def test_set_element(self, ncbi_submission_client):
+        element = ncbi_submission_client.set_element("Test", "Hello", {"attr": "value"})
+        assert element.tag == "Test"
+        assert element.text == "Hello"
+        assert element.attrib == {"attr": "value"}
+
+    def test_set_description(self, ncbi_submission_client):
+        ncbi_submission_client.set_description(
+            ncbi_submission_client.nmdc_pi_email,
+            "testuser",
+            "Kate",
+            "Thibault",
+            "Test Org",
+        )
+        description = ET.tostring(
+            ncbi_submission_client.root.find("Description"), "unicode"
+        )
+
+        root = ET.fromstring(description)
+        comment = root.find("Comment").text
+        submitter = root.find("Submitter").attrib["user_name"]
+        org_name = root.find("Organization/Name").text
+        contact_email = root.find("Organization/Contact").attrib["email"]
+        contact_first = root.find("Organization/Contact/Name/First").text
+        contact_last = root.find("Organization/Contact/Name/Last").text
+
+        assert comment == f"NMDC Submission for {MOCK_NMDC_STUDY['id']}"
+        assert submitter == "testuser"
+        assert org_name == "Test Org"
+        assert contact_email == "kthibault@battelleecology.org"
+        assert contact_first == "Kate"
+        assert contact_last == "Thibault"
+
+    def test_set_bioproject(self, ncbi_submission_client):
+        ncbi_submission_client.set_bioproject(
+            title=MOCK_NMDC_STUDY["title"],
+            project_id=MOCK_NMDC_STUDY["insdc_bioproject_identifiers"][0],
+            description=MOCK_NMDC_STUDY["description"],
+            data_type="metagenome",
+            org="Test Org",
+        )
+        bioproject_xml = ET.tostring(
+            ncbi_submission_client.root.find(".//Project"), "unicode"
+        )
+        assert (
+            "National Ecological Observatory Network: soil metagenomes (DP1.10107.001)"
+            in bioproject_xml
+        )
+        assert "bioproject:PRJNA1029061" in bioproject_xml
+        assert (
+            "This study contains the quality-controlled laboratory metadata and minimally processed sequence data from NEON's soil microbial shotgun metagenomics sequencing."
+            in bioproject_xml
+        )
+        assert "metagenome" in bioproject_xml
+        assert "Test Org" in bioproject_xml
+
+    def test_set_biosample(self, ncbi_submission_client, nmdc_biosample, mocker):
+        mocker.patch(
+            "nmdc_runtime.site.export.ncbi_xml.load_mappings",
+            return_value=(
+                {
+                    "analysis_type": "",
+                    "biosample_categories": "",
+                    "collection_date": "collection_date",
+                    "conduc": "conduc",
+                    "elev": "elev",
+                    "env_broad_scale": "env_broad_scale",
+                    "env_local_scale": "env_local_scale",
+                    "env_medium": "env_medium",
+                    "env_package": "env_package",
+                    "geo_loc_name": "geo_loc_name",
+                    "id": "",
+                    "lat_lon": "lat_lon",
+                    "name": "sample_name",
+                    "part_of": "",
+                    "samp_collec_device": "samp_collect_device",
+                    "temp": "temp",
+                    "type": "",
+                },
+                {
+                    "analysis_type": "AnalysisTypeEnum",
+                    "biosample_categories": "BiosampleCategoryEnum",
+                    "collection_date": "TimestampValue",
+                    "conduc": "QuantityValue",
+                    "elev": "float",
+                    "env_broad_scale": "ControlledIdentifiedTermValue",
+                    "env_local_scale": "ControlledIdentifiedTermValue",
+                    "env_medium": "ControlledIdentifiedTermValue",
+                    "env_package": "TextValue",
+                    "geo_loc_name": "TextValue",
+                    "id": "uriorcurie",
+                    "lat_lon": "GeolocationValue",
+                    "name": "string",
+                    "part_of": "Study",
+                    "samp_collec_device": "string",
+                    "temp": "QuantityValue",
+                    "type": "string",
+                },
+            ),
+        )
+        ncbi_submission_client.set_biosample(
+            organism_name=MOCK_NCBI_SUBMISSION_METADATA["ncbi_biosample_metadata"][
+                "organism_name"
+            ],
+            org=MOCK_NCBI_SUBMISSION_METADATA["ncbi_submission_metadata"][
+                "organization"
+            ],
+            bioproject_id=MOCK_NMDC_STUDY["insdc_bioproject_identifiers"][0],
+            nmdc_biosamples=nmdc_biosample,
+            nmdc_omics_processing=[],
+        )
+        biosample_xml = ET.tostring(
+            ncbi_submission_client.root.find(".//BioSample"), "unicode"
+        )
+        assert "E. coli" in biosample_xml
+        assert "Test Org" in biosample_xml
+        assert "PRJNA1029061" in biosample_xml
+
+    def test_set_fastq(self, ncbi_submission_client, data_objects_list, nmdc_biosample):
+        biosample_data_objects = [
+            {biosample["id"]: data_objects_list} for biosample in nmdc_biosample
+        ]
+
+        ncbi_submission_client.set_fastq(
+            biosample_data_objects=biosample_data_objects,
+            bioproject_id=MOCK_NMDC_STUDY["insdc_bioproject_identifiers"][0],
+            org="Test Org",
+        )
+
+        action_elements = ncbi_submission_client.root.findall(".//Action")
+        assert len(action_elements) == len(biosample_data_objects)
+
+        for action_element in action_elements:
+            action_xml = ET.tostring(action_element, "unicode")
+            assert (
+                "BMI_HVKNKBGX5_Tube347_R1.fastq.gz" in action_xml
+                or "BMI_HVKNKBGX5_Tube347_R2.fastq.gz" in action_xml
+            )
+            assert "PRJNA1029061" in action_xml
+            assert "nmdc:bsm-12-p9q5v236" in action_xml
+            assert "Test Org" in action_xml
+
+    def test_get_submission_xml(
+        self, mocker, ncbi_submission_client, nmdc_biosample, data_objects_list
+    ):
+        mocker.patch(
+            "nmdc_runtime.site.export.ncbi_xml.load_mappings",
+            return_value=(
+                {
+                    "analysis_type": "",
+                    "biosample_categories": "",
+                    "collection_date": "collection_date",
+                    "conduc": "conduc",
+                    "elev": "elev",
+                    "env_broad_scale": "env_broad_scale",
+                    "env_local_scale": "env_local_scale",
+                    "env_medium": "env_medium",
+                    "env_package": "env_package",
+                    "geo_loc_name": "geo_loc_name",
+                    "id": "",
+                    "lat_lon": "lat_lon",
+                    "name": "sample_name",
+                    "part_of": "",
+                    "samp_collec_device": "samp_collect_device",
+                    "temp": "temp",
+                    "type": "",
+                },
+                {
+                    "analysis_type": "AnalysisTypeEnum",
+                    "biosample_categories": "BiosampleCategoryEnum",
+                    "collection_date": "TimestampValue",
+                    "conduc": "QuantityValue",
+                    "elev": "float",
+                    "env_broad_scale": "ControlledIdentifiedTermValue",
+                    "env_local_scale": "ControlledIdentifiedTermValue",
+                    "env_medium": "ControlledIdentifiedTermValue",
+                    "env_package": "TextValue",
+                    "geo_loc_name": "TextValue",
+                    "id": "uriorcurie",
+                    "lat_lon": "GeolocationValue",
+                    "name": "string",
+                    "part_of": "Study",
+                    "samp_collec_device": "string",
+                    "temp": "QuantityValue",
+                    "type": "string",
+                },
+            ),
+        )
+
+        biosample_data_objects = [
+            {biosample["id"]: data_objects_list} for biosample in nmdc_biosample
+        ]
+
+        ncbi_submission_client.set_fastq(
+            biosample_data_objects=biosample_data_objects,
+            bioproject_id=MOCK_NMDC_STUDY["insdc_bioproject_identifiers"][0],
+            org="Test Org",
+        )
+
+        submission_xml = ncbi_submission_client.get_submission_xml(
+            nmdc_biosample, [], biosample_data_objects
+        )
+
+        assert "nmdc:bsm-12-p9q5v236" in submission_xml
+        assert "E. coli" in submission_xml
+        assert "sediment" in submission_xml
+        assert "USA: Colorado, Arikaree River" in submission_xml
+        assert "2015-07-21T18:00Z" in submission_xml
+        assert "National Microbiome Data Collaborative (NMDC)" in submission_xml
+        assert (
+            "National Ecological Observatory Network: soil metagenomes (DP1.10107.001)"
+            in submission_xml
+        )
+
+
+class TestNCBIXMLUtils:
+    def test_handle_quantity_value(self):
+        assert (
+            handle_quantity_value({"has_numeric_value": 10, "has_unit": "mg"})
+            == "10 mg"
+        )
+        assert (
+            handle_quantity_value(
+                {
+                    "has_maximum_numeric_value": 15,
+                    "has_minimum_numeric_value": 5,
+                    "has_unit": "kg",
+                }
+            )
+            == "10 kg"
+        )
+        assert handle_quantity_value({"has_raw_value": "20 units"}) == "20 units"
+        assert handle_quantity_value({}) == "Unknown format"
+
+    def test_handle_text_value(self):
+        assert handle_text_value({"has_raw_value": "Sample Text"}) == "Sample Text"
+        assert handle_text_value({}) == "Unknown format"
+
+    def test_handle_timestamp_value(self):
+        assert handle_timestamp_value({"has_raw_value": "2021-01-01"}) == "2021-01-01"
+        assert handle_timestamp_value({}) == "Unknown format"
+
+    def test_handle_controlled_term_value(self):
+        term_data = {"term": {"name": "Homo sapiens", "id": "NCBITaxon:9606"}}
+        assert (
+            handle_controlled_term_value(term_data) == "Homo sapiens [NCBITaxon:9606]"
+        )
+        assert (
+            handle_controlled_term_value({"term": {"id": "NCBITaxon:9606"}})
+            == "NCBITaxon:9606"
+        )
+        assert (
+            handle_controlled_term_value({"term": {"name": "Homo sapiens"}})
+            == "Homo sapiens"
+        )
+        assert (
+            handle_controlled_term_value(
+                {"has_raw_value": "Homo sapiens [NCBITaxon:9606]"}
+            )
+            == "Homo sapiens [NCBITaxon:9606]"
+        )
+        assert handle_controlled_term_value({}) == "Unknown format"
+
+    def test_handle_controlled_identified_term_value(self):
+        term_data = {"term": {"name": "Homo sapiens", "id": "NCBITaxon:9606"}}
+        assert (
+            handle_controlled_identified_term_value(term_data)
+            == "Homo sapiens [NCBITaxon:9606]"
+        )
+        assert (
+            handle_controlled_identified_term_value({"term": {"id": "NCBITaxon:9606"}})
+            == "NCBITaxon:9606"
+        )
+        assert (
+            handle_controlled_identified_term_value({"term": {"name": "Homo sapiens"}})
+            == "Unknown format"
+        )
+        assert (
+            handle_controlled_identified_term_value(
+                {"has_raw_value": "Homo sapiens [NCBITaxon:9606]"}
+            )
+            == "Homo sapiens [NCBITaxon:9606]"
+        )
+        assert handle_controlled_identified_term_value({}) == "Unknown format"
+
+    def test_handle_geolocation_value(self):
+        assert (
+            handle_geolocation_value({"latitude": 34.05, "longitude": -118.25})
+            == "34.05 -118.25"
+        )
+        assert (
+            handle_geolocation_value({"has_raw_value": "34.05, -118.25"})
+            == "34.05, -118.25"
+        )
+        assert handle_geolocation_value({}) == "Unknown format"
+
+    def test_handle_float_value(self):
+        assert handle_float_value(10.1234) == "10.12"
+
+    def test_handle_string_value(self):
+        assert handle_string_value("Foo") == "Foo"
+
+    def test_load_mappings(self, mocker):
+        mock_tsv_content = (
+            "nmdc_schema_class\tnmdc_schema_slot\tnmdc_schema_slot_range\tncbi_biosample_attribute_name\tstatic_value\tignore\n"
+            "Biosample\tanalysis_type\tAnalysisTypeEnum\t\t\t\n"
+            "Biosample\tbiosample_categories\tBiosampleCategoryEnum\t\t\t\n"
+            "Biosample\tcollection_date\tTimestampValue\tcollection_date\t\t\n"
+            "Biosample\tconduc\tQuantityValue\tconduc\t\t\n"
+            "Biosample\telev\tfloat\telev\t\t\n"
+            "Biosample\tenv_broad_scale\tControlledIdentifiedTermValue\tenv_broad_scale\t\t\n"
+            "Biosample\tenv_local_scale\tControlledIdentifiedTermValue\tenv_local_scale\t\t\n"
+            "Biosample\tenv_medium\tControlledIdentifiedTermValue\tenv_medium\t\t\n"
+            "Biosample\tenv_package\tTextValue\tenv_package\t\t\n"
+            "Biosample\tgeo_loc_name\tTextValue\tgeo_loc_name\t\t\n"
+            "Biosample\tid\turiorcurie\t\t\t\n"
+            "Biosample\tlat_lon\tGeolocationValue\tlat_lon\t\t\n"
+            "Biosample\tname\tstring\tsample_name\t\t\n"
+            "Biosample\tpart_of\tStudy\t\t\t\n"
+            "Biosample\tsamp_collec_device\tstring\tsamp_collect_device\t\t\n"
+            "Biosample\ttemp\tQuantityValue\ttemp\t\t\n"
+            "Biosample\ttype\tstring\t\t\t\n"
+        )
+
+        mock_response = MagicMock()
+        mock_response.text = mock_tsv_content
+        mocker.patch("requests.get", return_value=mock_response)
+
+        attribute_mappings, slot_range_mappings = load_mappings(
+            "http://example.com/mappings.tsv"
+        )
+
+        expected_attribute_mappings = {
+            "analysis_type": "analysis_type",
+            "biosample_categories": "biosample_categories",
+            "collection_date": "collection_date",
+            "conduc": "conduc",
+            "elev": "elev",
+            "env_broad_scale": "env_broad_scale",
+            "env_local_scale": "env_local_scale",
+            "env_medium": "env_medium",
+            "env_package": "env_package",
+            "geo_loc_name": "geo_loc_name",
+            "id": "id",
+            "lat_lon": "lat_lon",
+            "name": "sample_name",
+            "part_of": "part_of",
+            "samp_collec_device": "samp_collect_device",
+            "temp": "temp",
+            "type": "type",
+        }
+
+        expected_slot_range_mappings = {
+            "analysis_type": "AnalysisTypeEnum",
+            "biosample_categories": "BiosampleCategoryEnum",
+            "collection_date": "TimestampValue",
+            "conduc": "QuantityValue",
+            "elev": "float",
+            "env_broad_scale": "ControlledIdentifiedTermValue",
+            "env_local_scale": "ControlledIdentifiedTermValue",
+            "env_medium": "ControlledIdentifiedTermValue",
+            "env_package": "TextValue",
+            "geo_loc_name": "TextValue",
+            "id": "uriorcurie",
+            "lat_lon": "GeolocationValue",
+            "name": "string",
+            "part_of": "Study",
+            "samp_collec_device": "string",
+            "temp": "QuantityValue",
+            "type": "string",
+        }
+
+        assert attribute_mappings == expected_attribute_mappings
+        assert slot_range_mappings == expected_slot_range_mappings