phc-ingestion 0.10.2__py3-none-any.whl → 0.10.4__py3-none-any.whl

ingestion/nebula/constants.py

@@ -0,0 +1 @@
+NEBULA_TEST_TYPE = "WGS-30x"

ingestion/nebula/manifest_assembler.py

@@ -0,0 +1,172 @@
+from typing import Optional, TypedDict, Any
+from datetime import datetime
+from ingestion.shared_util.lambda_client import LambdaClient
+
+
+class HumanName(TypedDict):
+    use: str
+    given: list[str]
+    family: str
+
+
+class Identifier(TypedDict):
+    system: str
+    value: str
+
+
+class Reference(TypedDict):
+    reference: str | None
+
+
+class Resource(TypedDict):
+    id: str | None
+    identifier: list[Identifier] | None
+
+
+class Patient(Resource):
+    name: list[HumanName] | None
+    gender: str | None
+    birthDate: str | None
+    managingOrganization: Reference | None
+    generalPractitioner: Reference | None
+
+
+class Organization(Resource):
+    name: str | None
+
+
+class Practitioner(Resource):
+    name: list[HumanName] | None
+
+
+class ManifestAssembler:
+    def __init__(self, ingestion_id: str, account_id: str, project_id: str, kit_id: str):
+        self.ingestion_id = ingestion_id
+        self.account_id = account_id
+        self.project_id = project_id
+        self.kit_id = kit_id
+        self.client = LambdaClient(
+            "patient-service",
+            {
+                "Content-Type": "application/json",
+                "LifeOmic-Account": self.account_id,
+                "LifeOmic-Correlation-Id": self.ingestion_id,
+            },
+        )
+
+    def __fetch_patient_by_kit_id(self) -> Optional[Patient]:
+        path = f"/{self.account_id}/dstu3/Patient"
+        params = {
+            "_tag": f"http://lifeomic.com/fhir/dataset|{self.project_id}",
+            "identifier": f"http://lifeomic.com/fhir/nebula-kit-id|{self.kit_id}",
+        }
+
+        response = self.client.invoke(path, "get", None, params)
+        entries = response.get("entry", [])
+        patient = entries[0]["resource"] if len(entries) > 0 else None
+
+        return patient
+
+    def __fetch_resource_by_type_and_reference(
+        self,
+        resource_type: str,
+        reference: Reference | None,
+    ) -> Any:
+        if not reference:
+            return None
+
+        resource_id = self.__extract_id_from_reference(reference)
+        path = f"/{self.account_id}/dstu3/{resource_type}/{resource_id}"
+
+        try:
+            return self.client.invoke(path, "get")
+        except RuntimeError as e:
+            return None
+
+    def __extract_identifier_from_resource(self, resource: Resource | None) -> str:
+        if not resource:
+            return ""
+
+        identifiers = resource.get("identifier", [])
+        return identifiers[0].get("value", "") if identifiers else ""
+
+    def __extract_id_from_reference(self, reference: Reference) -> str:
+        if not reference or not reference.get("reference"):
+            return ""
+
+        ref_string = reference.get("reference")
+        if not ref_string:
+            return ""
+
+        parts = ref_string.split("/")
+        return parts[1] if len(parts) > 1 else parts[0]
+
+    def __parse_human_name(self, human_name: list[HumanName] | None):
+        if not human_name or len(human_name) == 0:
+            return None
+
+        last_name = human_name[0].get("family", "")
+        first_name = human_name[0].get("given", [])[0]
+
+        return {
+            "lastName": last_name,
+            "firstName": first_name,
+            "fullName": f"{first_name} {last_name}",
+        }
+
+    def create_manifest(self) -> dict[str, Any]:
+        patient = self.__fetch_patient_by_kit_id()
+
+        if not patient:
+            raise RuntimeError(f"Patient with kit id {self.kit_id} not found")
+        patient_birth_date = patient.get("birthDate")
+        if not patient_birth_date:
+            raise RuntimeError(f"Patient birth date is a required to create a manifest")
+
+        organization: Organization | None = self.__fetch_resource_by_type_and_reference(
+            "Organization", patient.get("managingOrganization")
+        )
+
+        general_practitioner: Practitioner | None = self.__fetch_resource_by_type_and_reference(
+            "Practitioner", patient.get("generalPractitioner")
+        )
+
+        patient_info = self.__parse_human_name(patient["name"])
+        practitioner_info = self.__parse_human_name(
+            general_practitioner.get("name") if general_practitioner else None
+        )
+
+        return {
+            "name": "Nebula",
+            "indexedDate": datetime.now().strftime("%Y-%m-%d"),
+            "reference": "GRCh38",  # TODO: Get from project?
+            "mrn": patient.get("id"),
+            "bodySite": "Buccal Swab",
+            "bodySiteDisplay": "Buccal Swab",
+            "bodySiteSystem": "http://lifeomic.com/fhir/sequence-body-site",
+            "indicationSystem": "http://lifeomic.com/fhir/sequence-indication",
+            "indication": "Genetic Health Screening",
+            "indicationDisplay": "Genetic Health Screening",
+            "patientInfo": {
+                "lastName": patient_info.get("lastName"),
+                "dob": datetime.fromisoformat(patient_birth_date).strftime("%Y-%m-%d"),
+                "firstName": patient_info.get("firstName"),
+                "gender": patient["gender"],
+            },
+            **(
+                {
+                    "medFacilName": organization.get("name"),
+                    "medFacilID": self.__extract_identifier_from_resource(organization),
+                }
+                if organization
+                else {}
+            ),
+            **(
+                {
+                    "orderingMDName": practitioner_info.get("fullName"),
+                    "orderingMDNPI": self.__extract_identifier_from_resource(general_practitioner),
+                }
+                if general_practitioner
+                else {}
+            ),
+        }

ingestion/nebula/process.py

@@ -1,18 +1,21 @@
 import os
 
+from ingestion.nebula.constants import NEBULA_TEST_TYPE
 from ingestion.vcf_standardization.standardize import standardize_vcf
 from lifeomic_logging import scoped_logger
+from ingestion.nebula.manifest_assembler import ManifestAssembler
 
 
-def process(vcf_file, out_path, file_name, source_file_id):
+def process(vcf_file, out_path, file_name, source_file_id, ingestion_id, account_id, project_id):
 
     with scoped_logger(__name__) as log:
         log.info(
             f"Beginning Nebula ingestion for vcf_file: {vcf_file}, file_name: {file_name}, out_path: {out_path}, source_file_id: {source_file_id}"
         )
 
-        manifest = {}
         case_id = file_name
+        manifest_assembler = ManifestAssembler(ingestion_id, account_id, project_id, case_id)
+        manifest = manifest_assembler.create_manifest()
         base_vcf_file = os.path.basename(vcf_file)
         vcf_out = base_vcf_file.replace(".vcf", ".modified.vcf")
         vcf_final = base_vcf_file.replace(".vcf", ".modified.nrm.filtered.vcf")
@@ -28,6 +31,8 @@ def process(vcf_file, out_path, file_name, source_file_id):
         )
 
         # Add to manifest
+        manifest["testType"] = NEBULA_TEST_TYPE
+        manifest["reportID"] = case_id
         manifest["sourceFileId"] = source_file_id
         manifest["resources"] = [{"fileName": f".lifeomic/vcf-ingest/{case_id}/{base_vcf_file}"}]
         manifest["files"] = [
@@ -44,7 +49,7 @@ def process(vcf_file, out_path, file_name, source_file_id):
         case_metadata = {
             "test_type": manifest["testType"],
             "vcf_line_count": vcf_line_count,
-            "case_id": manifest["reportID"],
+            "germline_case_id": manifest["reportID"],
             "germline_genome_reference": genome_reference,
         }
 

ingestion/shared_util/lambda_client.py

@@ -0,0 +1,81 @@
+import boto3
+from mypy_boto3_lambda.type_defs import InvocationResponseTypeDef
+import json
+from typing import Optional, Any, cast
+from urllib3.util.url import parse_url
+
+
+class LambdaHandler:
+    ACCEPTABLE_STATUS_CODES = [200, 201, 204]
+
+    def __init__(self) -> None:
+        return
+
+    def invoke(
+        self,
+        url: str,
+        header: dict,
+        method: str,
+        body: Optional[dict] = None,
+        query_params: Optional[dict] = None,
+    ) -> Any:
+        parsed_url = parse_url(url)
+        payload = {
+            "headers": header,
+            "path": parsed_url.path,
+            "httpMethod": method.upper(),
+            "body": body,
+            "queryStringParameters": query_params,
+        }
+
+        client = boto3.client("lambda")
+        try:
+            raw_response = client.invoke(
+                FunctionName=cast(str, parsed_url.netloc),
+                InvocationType="RequestResponse",
+                Payload=json.dumps(payload),
+            )
+            return self.parse_response(raw_response)
+
+        except RuntimeError as e:
+            raise RuntimeError(f"Error invoking lambda for payload {str(payload)}") from e
+
+    def parse_response(self, response: InvocationResponseTypeDef) -> Any:
+        raw_payload = response["Payload"].read() if "Payload" in response else None
+        invocation_status_code = response.get("StatusCode", None)
+        if invocation_status_code not in self.ACCEPTABLE_STATUS_CODES:
+            raise RuntimeError(
+                f"Error invoking lambda. Invocation status code: {invocation_status_code}. Response: {str(raw_payload)}"
+            )
+
+        payload = json.loads(raw_payload)
+        lambda_status_code = payload.get("statusCode", None)
+        if lambda_status_code not in self.ACCEPTABLE_STATUS_CODES:
+            raise RuntimeError(
+                f"Error invoking lambda. Lambda status code: {lambda_status_code}. Response: {str(payload)}"
+            )
+
+        return json.loads(payload.get("body", "{}"))
+
+
+class LambdaClient:
+    def __init__(self, host: str, default_header: dict):
+        self.host = host
+        self.default_header = default_header
+        self.handler = LambdaHandler()
+
+    def invoke(
+        self,
+        path: str,
+        method: str,
+        body: Optional[dict] = None,
+        query_params: Optional[dict] = None,
+    ):
+        if path.startswith("/"):
+            path = path[1:]
+        endpoint = f"{self.host}/{path}"
+        try:
+            return self.handler.invoke(endpoint, self.default_header, method, body, query_params)
+
+        except RuntimeError as e:
+            raise RuntimeError(f"Error invoking API. Request error: {str(e)}") from e

{phc_ingestion-0.10.2.dist-info → phc_ingestion-0.10.4.dist-info}/METADATA

@@ -1,18 +1,21 @@
 Metadata-Version: 2.1
 Name: phc-ingestion
-Version: 0.10.2
+Version: 0.10.4
 Summary: Functions for LifeOmic PHC genomic ingestions
 License: MIT
 Author-email: LifeOmic Development <development@lifeomic.com>
 Requires-Python: >=3.11
+Requires-Dist: boto3>=1.28.34
 Requires-Dist: jsonschema<5.0.0,>=4.16.0
 Requires-Dist: lifeomic-logging<0.4.0,>=0.3.2
+Requires-Dist: mypy-boto3-lambda>=1.28.19
 Requires-Dist: natsort==7.1.1
 Requires-Dist: numpy>=2.1.2
 Requires-Dist: packaging>=23.1
 Requires-Dist: pandas>=2.2.3
 Requires-Dist: ruamel.yaml==0.17.21
 Requires-Dist: schema>=0.7.5
+Requires-Dist: urllib3>=1.26.16
 Requires-Dist: xmltodict>=0.14.2
 Description-Content-Type: text/markdown
 

{phc_ingestion-0.10.2.dist-info → phc_ingestion-0.10.4.dist-info}/RECORD

@@ -27,7 +27,9 @@ ingestion/generic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 ingestion/generic/process.py,sha256=ZaVnZ_gx9faDUsuresI1A0oCegTa-dPQT7DBFMeZGyY,1777
 ingestion/generic/utils.py,sha256=1MEIru7uq38IjUdL8lcHqDH0oTki9uWrz1f2e-pmRoU,2814
 ingestion/nebula/__init__.py,sha256=VauK-rup_N8ZXVohx3HYqHX_PE_WoPyMUhdv2R7al4o,45
-ingestion/nebula/process.py,sha256=kIFhndcXFUICKMg4PfFhEsBxb_0oPkGPnpVNHhHFJ7k,1853
+ingestion/nebula/constants.py,sha256=015BkvYnu5JTzFCS3zjqsaFb0emzH4I8ZewpBjMJQfo,29
+ingestion/nebula/manifest_assembler.py,sha256=2nXMfFESs00NeetpizIJlFa8SR0KKqYgK_Xnusdjb58,5616
+ingestion/nebula/process.py,sha256=D2ct9tF60ZIP_jZdjvgjfTkhEAkNNEhxaSqa04CtNR8,2237
 ingestion/nextgen/__init__.py,sha256=7LQ-h_Bvc5P1QcHMdzsqi1Qm4fTJn04-ozar2ty9wSc,59
 ingestion/nextgen/process.py,sha256=5Z0RfclwTAYZruGDiLPutjPCYFh1DJpoWY9dnttghT4,3993
 ingestion/nextgen/util/alteration_table.py,sha256=JTWBL1Fqj_pGsH5vwuVEnCUJle2wOBk6VYImHYCF9vg,6129
@@ -46,6 +48,7 @@ ingestion/shared_util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3h
 ingestion/shared_util/coords_to_genes.py,sha256=vz9EfgFm3BS6pEPnslbEka8cJKlQZtHJdH2WRCCUMdE,1669
 ingestion/shared_util/ga4gh.py,sha256=-jNQj79zspxG67MxHzOfwAhLbb9je55M1h4-i5ri-tU,507
 ingestion/shared_util/gene_to_coords.py,sha256=M-q5ateLSQ4fCF0uMk5TX2uBLRrcZzXqXEf05TPaLsU,876
+ingestion/shared_util/lambda_client.py,sha256=0EdV5nOqe_w-OoDyi72w1P0lk30g1vlTW2sD3ci_Qqw,2695
 ingestion/shared_util/open_maybe_gzipped.py,sha256=FrOPJ4OgfpQGyT3f1Su1rFeuuYYu6QJ-nVIBIosbfhw,232
 ingestion/shared_util/tar.py,sha256=BGR_2vBbxyMgF-GzJ3SrihsPdOzII4SFVz9tvKV5vo0,482
 ingestion/shared_util/types.py,sha256=u9AD2OrTQWMBtK_7VXHsD8Rv6HFs-7ZUItNl4KXdL7k,68
@@ -56,6 +59,6 @@ ingestion/vcf_standardization/util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQe
 ingestion/vcf_standardization/util/af_helpers.py,sha256=dpTzoeIQVeBRt0ETF3a9rp5ojZqznHg4x_hCZ8OPcOg,1061
 ingestion/vcf_standardization/util/dp_helpers.py,sha256=Nq8oLOLObu4_pv16qwwgpALRlUoJVCULrd9cFOD-eoI,823
 ingestion/vcf_standardization/util/read_write.py,sha256=x3Pf6Dq8tmolblbCS5CrNmrcHS3FGfqBSFpFgvFGC4g,2526
-phc_ingestion-0.10.2.dist-info/WHEEL,sha256=B19PGBCYhWaz2p_UjAoRVh767nYQfk14Sn4TpIZ-nfU,87
-phc_ingestion-0.10.2.dist-info/METADATA,sha256=HuebNLig9ccPPhZrF9It2bxP7p4ZWf0LGiz_rt__1Zk,573
-phc_ingestion-0.10.2.dist-info/RECORD,,
+phc_ingestion-0.10.4.dist-info/WHEEL,sha256=B19PGBCYhWaz2p_UjAoRVh767nYQfk14Sn4TpIZ-nfU,87
+phc_ingestion-0.10.4.dist-info/METADATA,sha256=2bo_7YXbyMWyhO2pJDyGSbMWb_IYdPWgihQDWuB9b6s,677
+phc_ingestion-0.10.4.dist-info/RECORD,,