phc-ingestion 0.10.6__py3-none-any.whl → 1.0.0__py3-none-any.whl

ingestion/caris/util/ihc.py

@@ -121,9 +121,16 @@ def get_ihc_results(data, log) -> list[dict]:
                         )
                         trigger = True
                 if test_results.get("stainPercent"):
-                    if np.isnan(test_results["stainPercent"]) == False:
+                    try:
+                        stain_percent = float(test_results["stainPercent"])
+                        if np.isnan(stain_percent) == False:
+                            log.warning(
+                                f'IHC test {test_results["biomarkerName"]} has an unexpected pattern for "stainPercent": value of "{test_results["stainPercent"]}" was given when None was expected'
+                            )
+                            trigger = True
+                    except (ValueError, TypeError):
                         log.warning(
-                            f'IHC test {test_results["biomarkerName"]} has an unexpected pattern for "stainPercent": value of "{test_results["stainPercent"]}" was given when None was expected'
+                            f'IHC test {test_results["biomarkerName"]} has an invalid value for "stainPercent": "{test_results["stainPercent"]}"'
                         )
                         trigger = True
 
@@ -193,9 +200,16 @@ def get_ihc_results(data, log) -> list[dict]:
                     )
                     trigger = True
             if test_results.get("stainPercent"):
-                if np.isnan(test_results["stainPercent"]) == False:
+                try:
+                    stain_percent = float(test_results["stainPercent"])
+                    if not np.isnan(stain_percent):
+                        log.warning(
+                            f'IHC test {test_results["biomarkerName"]} has an unexpected pattern for "stainPercent": value of "{test_results["stainPercent"]}" was given when None was expected'
+                        )
+                        trigger = True
+                except (ValueError, TypeError):
                     log.warning(
-                        f'IHC test {test_results["biomarkerName"]} has an unexpected pattern for "stainPercent": value of "{test_results["stainPercent"]}" was given when None was expected'
+                        f'IHC test {test_results["biomarkerName"]} has an invalid value for "stainPercent": "{test_results["stainPercent"]}"'
                     )
                     trigger = True
             if test_results.get("threshold"):

ingestion/caris/util/metadata.py

@@ -106,10 +106,10 @@ def extract_metadata(data, prefix, files, source_file_id, log: Logger) -> dict:
     patient = data["patientInformation"]
     metadata["bodySiteSystem"] = "http://lifeomic.com/fhir/sequence-body-site"
     metadata["reportID"] = get_report_id(test_details)
-    metadata["mrn"] = patient["mrn"]
-    metadata["patientLastName"] = patient["lastName"]
+    metadata["mrn"] = patient["mrn"].strip()
+    metadata["patientLastName"] = patient["lastName"].strip()
 
-    metadata["patientDOB"] = patient["dob"]
+    metadata["patientDOB"] = patient["dob"].strip()
 
     # Get physician info - ordering name, NPI, and facility
     metadata["medFacilName"] = get_med_facil_name(physician_details)

ingestion/foundation/util/cnv.py

@@ -42,13 +42,15 @@ def extract_copy_numbers(
     log.info("Extracting copy numbers from xml")
     copy_number_list: dict = {"CopyNumbers": []}
 
-    if "copy-number-alterations" in results_payload_dict["variant-report"].keys():
+    if (
+        "variant-report" in results_payload_dict
+        and "copy-number-alterations" in results_payload_dict["variant-report"].keys()
+    ):
         if (
             results_payload_dict["variant-report"]["copy-number-alterations"] is not None
             and "copy-number-alteration"
             in results_payload_dict["variant-report"]["copy-number-alterations"].keys()
         ):
-
             variants_dict = results_payload_dict["variant-report"]["copy-number-alterations"][
                 "copy-number-alteration"
             ]

ingestion/foundation/util/fnv.py

@@ -67,7 +67,10 @@ def extract_fusion_variant(
     log.info("Extracting fusion variants from xml")
     fusion_variant_list: dict = {"FusionVariants": []}
 
-    if "rearrangements" in results_payload_dict["variant-report"].keys():
+    if (
+        "variant-report" in results_payload_dict
+        and "rearrangements" in results_payload_dict["variant-report"].keys()
+    ):
         if (
             results_payload_dict["variant-report"]["rearrangements"] is not None
             and "rearrangement" in results_payload_dict["variant-report"]["rearrangements"].keys()

ingestion/foundation/util/ga4gh.py

@@ -111,17 +111,23 @@ def get_hrd_status(genes) -> Optional[str]:
     hrd_dict = {
         "HRD Positive": "positive",
         "HRD Not Detected": "negative",
+        "HRDsig Positive": "positive",
+        "HRDsig Not Detected": "negative",
+        "HRDsig Negative": "negative",
     }
-    hrd_entry = [
-        entry
-        for entry in genes.get("Gene", {})
-        if entry.get("Name", "") == "Homologous Recombination status"
-    ]
-    if hrd_entry:
-        hrd_val = hrd_entry[0].get("Alterations", "").get("Alteration", "").get("Name", "")
-        return [value for (key, value) in hrd_dict.items() if key == hrd_val][0]
-    else:
+    hrd_entry = next(
+        (
+            entry
+            for entry in genes.get("Gene", {})
+            if entry.get("Name", "") == "Homologous Recombination status"
+            or entry.get("Name", "") == "HRD signature"
+        ),
+        None,
+    )
+    if not hrd_entry:
         return None
+    hrd_val = hrd_entry.get("Alterations", {}).get("Alteration", {}).get("Name", "")
+    return hrd_dict.get(hrd_val, None)
 
 
 def get_test_yml(
@@ -155,6 +161,14 @@ def get_test_yml(
         (prop for prop in properties if prop.get("@key") == "ComprehensiveTumorFractionScore"),
         {},
     ).get("value")
+    hrd_score = next(
+        (
+            prop
+            for prop in properties
+            if prop.get("@key") == "HomologousRecombinationDeficiencyScore"
+        ),
+        {},
+    ).get("value")
     plasma_tumor_fraction_score = None
     if plasma_tumor_fraction_score_value:
         plasma_tumor_fraction_score = get_plasma_tumor_fraction_score_from_value(
@@ -166,7 +180,7 @@ def get_test_yml(
     # Hard-code genome reference for FMI
     genome_reference = "GRCh37"
 
-    mrn = get_mrn(pmi)
+    mrn = get_mrn(pmi).strip()
 
     trf = get_trf(sample)
 
@@ -206,8 +220,8 @@ def get_test_yml(
         "reportDate": reportDate,
         "reportID": trf,
         "mrn": mrn,
-        "patientDOB": get_date(pmi.get("DOB")),
-        "patientLastName": pmi.get("LastName"),
+        "patientDOB": get_date(pmi.get("DOB")).strip(),
+        "patientLastName": pmi.get("LastName").strip(),
         "medFacilName": med_facil_info[0],
         "medFacilID": med_facil_info[1],
         "orderingMDName": ordering_md_info[0],
@@ -325,5 +339,7 @@ def get_test_yml(
     # add homologous recombination deficiency
     if hrd_status:
         yaml_file["hrdStatus"] = hrd_status
+    if hrd_score != None and is_number(hrd_score):
+        yaml_file["hrdScore"] = float(hrd_score)
 
     return yaml_file

ingestion/foundation/util/vcf_etl.py

@@ -55,6 +55,9 @@ def get_xml_short_vars(xml_file: str, log):
         xml_short_vars = xml_dict["rr:ResultsReport"]["rr:ResultsPayload"]["variant-report"][
             "short-variants"
         ]["short-variant"]
+    except KeyError as e:
+        log.info(f"Missing key in XML structure for short variants: {str(e)}")
+        return vendsig_dict
     except TypeError:
         log.info("No short variants found in xml")
         return vendsig_dict

ingestion/nebula/manifest_assembler.py

@@ -1,6 +1,10 @@
-from typing import Optional, TypedDict, Any
-from datetime import datetime
+import re
+import gzip
+from typing import Optional, TypedDict, Any, Callable
+from datetime import datetime, timezone
+from dateutil import parser
 from ingestion.shared_util.lambda_client import LambdaClient
+from ingestion.vcf_standardization.util.read_write import read_headers
 from ingestion.nebula.constants import (
     DATASET_SYSTEM,
     NEBULA_KIT_ID_SYSTEM,
@@ -9,7 +13,6 @@ from ingestion.nebula.constants import (
     NEBULA_BODY_SITE,
     NEBULA_INDICATION,
 )
-import re
 
 
 class HumanName(TypedDict):
@@ -37,7 +40,7 @@ class Patient(Resource):
     gender: str | None
     birthDate: str | None
     managingOrganization: Reference | None
-    generalPractitioner: Reference | None
+    generalPractitioner: list[Reference] | None
 
 
 class Organization(Resource):
@@ -49,11 +52,14 @@ class Practitioner(Resource):
 
 
 class ManifestAssembler:
-    def __init__(self, ingestion_id: str, account_id: str, project_id: str, kit_id: str):
+    def __init__(
+        self, ingestion_id: str, account_id: str, project_id: str, kit_id: str, vcf_file_path: str
+    ):
         self.ingestion_id = ingestion_id
         self.account_id = account_id
         self.project_id = project_id
         self.kit_id = kit_id
+        self.vcf_file_path = vcf_file_path
         self.client = LambdaClient(
             "patient-service",
             {
@@ -72,9 +78,16 @@ class ManifestAssembler:
 
         response = self.client.invoke(path, "get", None, params)
         entries = response.get("entry", [])
-        patient = entries[0]["resource"] if len(entries) > 0 else None
 
-        return patient
+        if len(entries) == 0:
+            return None
+
+        if len(entries) > 1:
+            raise RuntimeError(
+                f"Found {len(entries)} patients with kit id {self.kit_id}. Expected 1."
+            )
+
+        return entries[0]["resource"]
 
     def __fetch_resource_by_type_and_reference(
         self,
@@ -92,28 +105,16 @@ class ManifestAssembler:
         except RuntimeError:
             return None
 
-    def __extract_identifier_from_resource(self, resource: Resource | None) -> str:
-        if not resource:
-            return ""
-
+    def __extract_identifier_from_resource(self, resource: Resource) -> str:
         identifiers = resource.get("identifier", [])
         return identifiers[0].get("value", "") if identifiers else ""
 
     def __extract_id_from_reference(self, reference: Reference) -> str:
-        if not reference:
-            return ""
-
-        ref_string = reference.get("reference")
-        if not ref_string:
-            return ""
-
+        ref_string = reference.get("reference", "")
         parts = ref_string.split("/")
         return parts[1] if len(parts) > 1 else parts[0]
 
     def __extract_elation_mrn(self, patient: Patient) -> str:
-        if not patient:
-            return ""
-
         identifier = next(
             (
                 x
@@ -134,12 +135,9 @@ class ManifestAssembler:
 
     def __parse_human_name(self, human_name: list[HumanName] | None):
         if not human_name:
-            return None
+            return {}
 
-        human_name = next((x for x in human_name if x.get("use") == "official"), None)
-
-        if not human_name:
-            return None
+        human_name = next((x for x in human_name if x.get("use") == "official"), human_name[0])
 
         last_name = human_name.get("family", "")
         first_name = human_name.get("given", [])[0]
@@ -150,6 +148,37 @@ class ManifestAssembler:
             "fullName": f"{first_name} {last_name}",
         }
 
+    def _safe(self, lambda_func: Callable[[], Any]) -> Any:
+        try:
+            return lambda_func()
+        except Exception as e:
+            return None
+
+    def __extract_collection_date(self) -> dict[str, str]:
+        in_file = self.vcf_file_path
+        with gzip.open(in_file, "rt") if in_file.endswith(".gz") else open(in_file, "r") as f:
+            headers = read_headers(f)
+            for header in headers:
+                epoch_parts = re.search(r"Epoch=(\d+)", header)
+                epoch_time_raw = epoch_parts.group(1) if epoch_parts else None
+                epoch_time = self._safe(
+                    lambda: datetime.fromtimestamp(int(epoch_time_raw) / 1000.0, tz=timezone.utc)
+                )
+                date_parts = re.search(r"Date=\"(.*)\"", header)
+                date_string_raw = date_parts.group(1) if date_parts else None
+                date_string = self._safe(
+                    lambda: parser.parse(date_string_raw, tzinfos={"GST": "UTC+4"})
+                )
+
+                report_date = epoch_time or date_string
+                if report_date:
+                    return {
+                        "collDate": report_date.astimezone(tz=timezone.utc)
+                        .isoformat(timespec="milliseconds")
+                        .replace("+00:00", "Z")
+                    }
+        return {}
+
     def create_manifest(self) -> dict[str, Any]:
         patient = self.__fetch_patient_by_kit_id()
 
@@ -157,17 +186,17 @@ class ManifestAssembler:
             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("Patient birth date is a required to create a manifest")
+            raise RuntimeError("Patient birth date is 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")
+            "Practitioner", next(iter(patient.get("generalPractitioner", [])), None)
         )
 
-        patient_info = self.__parse_human_name(patient["name"])
+        patient_info = self.__parse_human_name(patient.get("name"))
         practitioner_info = self.__parse_human_name(
             general_practitioner.get("name") if general_practitioner else None
         )
@@ -175,6 +204,7 @@ class ManifestAssembler:
         return {
             "name": "Nebula",
             "indexedDate": datetime.now().strftime("%Y-%m-%d"),
+            **self.__extract_collection_date(),
             "reference": "GRCh38",
             "patientId": patient.get("id"),
             "mrn": self.__extract_elation_mrn(patient),
@@ -185,10 +215,10 @@ class ManifestAssembler:
             "indication": NEBULA_INDICATION,
             "indicationDisplay": NEBULA_INDICATION,
             "patientInfo": {
-                "lastName": patient_info.get("lastName"),
+                "lastName": patient_info.get("lastName", ""),
                 "dob": datetime.fromisoformat(patient_birth_date).strftime("%Y-%m-%d"),
-                "firstName": patient_info.get("firstName"),
-                "gender": patient["gender"],
+                "firstName": patient_info.get("firstName", ""),
+                "gender": patient.get("gender", ""),
             },
             **(
                 {

ingestion/nebula/process.py

@@ -1,6 +1,7 @@
 import os
 
 from ingestion.nebula.constants import NEBULA_TEST_TYPE
+from ingestion.shared_util.ga4gh import create_yaml
 from ingestion.vcf_standardization.standardize import standardize_vcf
 from lifeomic_logging import scoped_logger
 from ingestion.nebula.manifest_assembler import ManifestAssembler
@@ -14,8 +15,9 @@ def process(vcf_file, out_path, file_name, source_file_id, ingestion_id, account
         )
 
         case_id = file_name
-        manifest_assembler = ManifestAssembler(ingestion_id, account_id, project_id, case_id)
-        manifest = manifest_assembler.create_manifest()
+        manifest = ManifestAssembler(
+            ingestion_id, account_id, project_id, case_id, vcf_file
+        ).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")
@@ -34,15 +36,17 @@ def process(vcf_file, out_path, file_name, source_file_id, ingestion_id, account
         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["resources"] = [{"fileName": f".lifeomic/nebula/{case_id}/{base_vcf_file}"}]
         manifest["files"] = [
             {
-                "fileName": f".lifeomic/vcf-ingest/{case_id}/{vcf_final}",
+                "fileName": f".lifeomic/nebula/{case_id}/{vcf_final}",
                 "sequenceType": "germline",
                 "type": "shortVariant",
             }
         ]
 
+        create_yaml(manifest, f"{out_path}/{file_name}")
+
         # Hard-code genome reference for Nebula VCFs
         genome_reference = "GRCh38"
 

ingestion/shared_util/fetch_patient.py

@@ -0,0 +1,76 @@
+from typing import Any
+from lifeomic_logging import scoped_logger
+from ingestion.shared_util.lambda_client import LambdaClient
+
+# Constants
+DATASET_SYSTEM = "http://lifeomic.com/fhir/dataset"
+
+
+def fetch_patient(
+    *,
+    elation_id: str,
+    given_name: str,
+    birthdate: str,
+    project_id: str,
+    account_id: str,
+    ingestion_id: str,
+) -> dict[str, Any] | None:
+    """
+    Fetch a patient from the patient-service lambda using Elation ID AND given name AND
+    birthdate.
+
+    Returns:
+        The patient resource if found, None otherwise
+
+    Raises:
+        RuntimeError: When multiple patients are found (ambiguous match)
+    """
+    log_context = {
+        "accountId": account_id,
+        "projectId": project_id,
+        "elationId": elation_id,
+        "ingestionId": ingestion_id,
+    }
+
+    with scoped_logger(__name__, log_context) as log:
+        # Create LambdaClient instance with proper headers
+        client = LambdaClient(
+            "patient-service",
+            {
+                "Content-Type": "application/json",
+                "LifeOmic-Account": account_id,
+                "LifeOmic-Correlation-Id": ingestion_id,
+            },
+        )
+
+        # Search by Elation ID AND given name AND birthdate
+        log.info(
+            f"Searching for patient with Elation ID: {elation_id}, given name: {given_name}, birthdate: {birthdate}"
+        )
+        response = client.invoke(
+            f"/{account_id}/dstu3/Patient",
+            "get",
+            None,
+            {
+                "_tag": f"{DATASET_SYSTEM}|{project_id}",
+                "identifier": elation_id,
+                "name": given_name,
+                "birthdate": birthdate,
+            },
+        )
+        entries = response.get("entry", [])
+
+        if len(entries) == 0:
+            error_msg = f"No patient found with Elation ID: {elation_id}, given name: {given_name}, birthdate: {birthdate}"
+            log.error(error_msg)
+            raise RuntimeError(error_msg)
+
+        if len(entries) > 1:
+            error_msg = f"Found multiple patients when one was expected. Found {len(entries)}. Elation ID {elation_id}, given name {given_name}, birthdate {birthdate}."
+            log.error(error_msg)
+            raise RuntimeError(error_msg)
+
+        log.info(
+            f"Found patient with Elation ID: {elation_id}, given name: {given_name}, birthdate: {birthdate}"
+        )
+        return entries[0]["resource"]

ingestion/vcf_standardization/util/read_write.py

@@ -4,6 +4,8 @@ import re
 import os
 from typing import Iterator, Optional
 
+import pysam
+
 
 def check_vcf(infile: str, log: Logger) -> None:
     log.info("Checking VCF file")
@@ -72,11 +74,35 @@ def write_vcf(
 ) -> int:
     log.info(f"Writing standardized VCF to {outfile}")
 
-    with gzip.open(outfile, "wt") if compression else open(outfile, "w") as w:
-        w.write("\n".join(headers) + "\n")
-        for variant in variants_gen:
-            line_count += 1
-            if variant:
-                w.write(variant + "\n")
+    if compression:
+        # Write uncompressed first, then compress with bgzip (indexable format)
+        # pysam.tabix_compress requires an uncompressed input file
+        # Create a temporary uncompressed file
+        if outfile.endswith(".gz"):
+            temp_uncompressed = outfile[:-3]  # Remove .gz extension
+        else:
+            temp_uncompressed = outfile + ".tmp"
+
+        with open(temp_uncompressed, "w") as w:
+            w.write("\n".join(headers) + "\n")
+            for variant in variants_gen:
+                line_count += 1
+                if variant:
+                    w.write(variant + "\n")
+
+        # Compress with bgzip (indexable format) using pysam
+        log.info(f"Compressing VCF with bgzip to {outfile}")
+        pysam.tabix_compress(temp_uncompressed, outfile, force=True)
+
+        # Clean up temporary uncompressed file
+        if os.path.exists(temp_uncompressed):
+            os.remove(temp_uncompressed)
+    else:
+        with open(outfile, "w") as w:
+            w.write("\n".join(headers) + "\n")
+            for variant in variants_gen:
+                line_count += 1
+                if variant:
+                    w.write(variant + "\n")
 
     return line_count

{phc_ingestion-0.10.6.dist-info → phc_ingestion-1.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phc-ingestion
-Version: 0.10.6
+Version: 1.0.0
 Summary: Functions for LifeOmic PHC genomic ingestions
 License: MIT
 Author-email: LifeOmic Development <development@lifeomic.com>
@@ -13,6 +13,7 @@ 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: pysam>=0.21.0
 Requires-Dist: ruamel.yaml==0.17.21
 Requires-Dist: schema>=0.7.5
 Requires-Dist: urllib3>=1.26.16

{phc_ingestion-0.10.6.dist-info → phc_ingestion-1.0.0.dist-info}/RECORD

@@ -5,10 +5,10 @@ ingestion/caris/util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hS
 ingestion/caris/util/cnv.py,sha256=Nrc0aoG2k4tmrqHb69hAuXr0adDZIVVJRRjf9_sO91E,4441
 ingestion/caris/util/detect_genome_ref.py,sha256=MpiPa71QmlO3MWvjxPzNdbEHyOhorOcpQWWlwE5BO4c,1640
 ingestion/caris/util/hla.py,sha256=X_t6ngBRvmdG3m4I2_KnPFeWn3BaH-3IWHtOvDbS32A,770
-ingestion/caris/util/ihc.py,sha256=vegxudxHj7tLihrXGbEx_ptwkSsu3YCCB1nZVwoiYXg,12312
+ingestion/caris/util/ihc.py,sha256=1XfFJjvQq9E45cdPX4EPrg2VkXABxbMJP_BOgzA8z7g,13091
 ingestion/caris/util/interpretation.py,sha256=CghNurqeVA5VTBBorU8-ZTN-PVNPnR8wrmTwKCH3568,555
 ingestion/caris/util/json.py,sha256=aifO1hnZwNSS-ZtY20otyGbfIoc23w9HMWJ5D56lhFo,5020
-ingestion/caris/util/metadata.py,sha256=a6NToMtGtIRrlMd3CQwq4IRjGGmIiBA9JFwsATjNEoQ,10287
+ingestion/caris/util/metadata.py,sha256=OaEG50FrYqyj1n9u9F3Qt17SX2K0cmIIzI6d8Assj64,10311
 ingestion/caris/util/specimen_details.py,sha256=wDTIelrGelAuSljmE6dAoJRjb9kwrlhmB2f1_vcCiUc,2963
 ingestion/caris/util/structural.py,sha256=EUcMIea_WnafoVmFLIyEqlJ_HtYIj_g6qkekXa7QNQs,4628
 ingestion/caris/util/tests.py,sha256=mcG3A8TW81_sn2Bfoa-Gd6Q1sR3_R4FX2BNskD4DkJk,372
@@ -18,18 +18,18 @@ ingestion/caris/util/vcf.py,sha256=Lkr4HnjMmMvEBVkD-9EkxRI3HpFmgCkgj6CXN4lBfIg,5
 ingestion/foundation/__init__.py,sha256=CuUMsxSvWPAVzvnxx4hois632HpXwhwpjtMtiM98UoM,49
 ingestion/foundation/process.py,sha256=mzKVVefGZD1HkEi0Hbb9eD_flwGp1S6SZ7FNXZpWnvI,2464
 ingestion/foundation/util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ingestion/foundation/util/cnv.py,sha256=YSKCaOBhjZDNXth_GxC-50crDURpTNCMefoHo0uO7lQ,4215
-ingestion/foundation/util/fnv.py,sha256=-VstGsBKXM0duC-IpwUkektoTZ9yQUR0IQcDb1HibY0,5937
-ingestion/foundation/util/ga4gh.py,sha256=2oCTR9kvV5EeGZlrR35MfMkNL3nbeJYO88fo0NDDmRo,11304
+ingestion/foundation/util/cnv.py,sha256=eyTn1lqbo0tmEacnqWuGATt1h9lllTlVlboT8n5C6Ao,4283
+ingestion/foundation/util/fnv.py,sha256=B8tOREYsR45aIGdSj8SPpe7f3L8FlGaIhLe0DSNqCnc,6006
+ingestion/foundation/util/ga4gh.py,sha256=GVHjMQNd7RaRg9qX7fStBcW5toLjvJCuHvu6hqm4tAo,11803
 ingestion/foundation/util/interpretation.py,sha256=LVVUmMyD6Un1rIKXqiyQDUC6oIJUd8cU3I9YHD5fsXg,405
-ingestion/foundation/util/vcf_etl.py,sha256=ZBrX1XGRz-ymLUEiVcjjqmPZPb-AfD9On8UkZJDa1Dk,2133
+ingestion/foundation/util/vcf_etl.py,sha256=GXV5JXswwdyHEEdPsM3Qq8tDPFkvZajrZn5chWgF53k,2266
 ingestion/generic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 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/constants.py,sha256=thKqSwemdaAwAmKvF4FEVI9l1Ph5ergsnMlx6nWte7E,357
-ingestion/nebula/manifest_assembler.py,sha256=OPUnuvzL1Bti_1-4N3fDP22wHtaK__4Bwh5K21Mg-C4,6416
-ingestion/nebula/process.py,sha256=D2ct9tF60ZIP_jZdjvgjfTkhEAkNNEhxaSqa04CtNR8,2237
+ingestion/nebula/manifest_assembler.py,sha256=kcRSy6pixHkuVEK9QSoM-i6ZdLWMSYXw39eKGHvam34,7995
+ingestion/nebula/process.py,sha256=N9OuipynGV_XgEL3nO5I_-di1tk9szOy8LqsyNTw0E0,2323
 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 +46,7 @@ ingestion/resources/GRCh37_map.csv.gz,sha256=JOEkjtbYrJpIdyoZdCvfJhvvz2dNfkSve7l
 ingestion/resources/GRCh38_map.csv.gz,sha256=qriYO2_buCCb4T6WcuZ-pCwPxMsm0TL2OxAHvJ1cEfA,612373
 ingestion/shared_util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ingestion/shared_util/coords_to_genes.py,sha256=vz9EfgFm3BS6pEPnslbEka8cJKlQZtHJdH2WRCCUMdE,1669
+ingestion/shared_util/fetch_patient.py,sha256=-E-C2m6-fLfKy-r7rSsjZNu_ACGKvdjl1UuB-2gvaJc,2442
 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
@@ -58,7 +59,7 @@ ingestion/vcf_standardization/standardize.py,sha256=zYzZxncq8USA1bUs26L-ByLPTnUl
 ingestion/vcf_standardization/util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 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-0.10.6.dist-info/WHEEL,sha256=B19PGBCYhWaz2p_UjAoRVh767nYQfk14Sn4TpIZ-nfU,87
-phc_ingestion-0.10.6.dist-info/METADATA,sha256=IhIQUPLXKsepjBwgwe4ARhaZ2fKrmvsJhsgey1Yui7o,677
-phc_ingestion-0.10.6.dist-info/RECORD,,
+ingestion/vcf_standardization/util/read_write.py,sha256=xogLdqtm1xGzigY459LqP_1zM6c5X9AjAFGkfaDI-bg,3479
+phc_ingestion-1.0.0.dist-info/WHEEL,sha256=B19PGBCYhWaz2p_UjAoRVh767nYQfk14Sn4TpIZ-nfU,87
+phc_ingestion-1.0.0.dist-info/METADATA,sha256=cBi1pg6CnOcySSTE8zTJzsvS-Tq48YTB5R5waazNTuQ,705
+phc_ingestion-1.0.0.dist-info/RECORD,,