phc-ingestion 0.8.42__tar.gz → 0.9.1__tar.gz

{phc-ingestion-0.8.42 → phc-ingestion-0.9.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phc-ingestion
-Version: 0.8.42
+Version: 0.9.1
 Summary: Functions for LifeOmic PHC genomic ingestions
 License: MIT
 Author-email: LifeOmic Development <development@lifeomic.com>

{phc-ingestion-0.8.42 → phc-ingestion-0.9.1}/ingestion/caris/util/metadata.py

@@ -94,9 +94,13 @@ def extract_metadata(data, prefix, files, source_file_id, log: Logger) -> dict:
     # Get date of collected and received for the specimen
     metadata["receivedDate"] = specimen_details["receivedDate"]
     metadata["collDate"] = specimen_details["collDate"]
+    if specimen_details["specimenId"]:
+        metadata["specimenIds"] = [specimen_details["specimenId"]]
+    if specimen_details["specimenTypes"]:
+        metadata["specimenTypes"] = specimen_details["specimenTypes"]
     metadata["reportDate"] = get_report_date(test_details, log)
 
-    #  Get the date without the time
+    # Get the date without the time
     metadata["indexedDate"] = metadata["reportDate"]
 
     patient = data["patientInformation"]

phc-ingestion-0.9.1/ingestion/caris/util/specimen_details.py

@@ -0,0 +1,86 @@
+from logging import Logger
+from typing import TypedDict, cast, Optional
+
+
+class SpecimenDetails(TypedDict, total=False):
+    """A partial representation of the specimen details in the Caris JSON file"""
+
+    specimenReceivedDate: str
+    specimenCollectionDate: str
+    specimenSite: str
+    specimenType: str
+    specimenID: str | int
+
+
+class ParsedSpecimenDetails(TypedDict):
+    bodySite: str
+    receivedDate: str
+    collDate: str
+    specimenId: Optional[str]
+    specimenTypes: Optional[list[str]]
+
+
+def parse_specimen_details(specimen_details: list[SpecimenDetails]) -> ParsedSpecimenDetails:
+    specimen_types: list[str] = []
+    for specimen in specimen_details:
+        specimen_type = specimen.get("specimenType")
+        if specimen_type and specimen_type not in specimen_types:
+            specimen_types.append(specimen_type)
+    maybe_specimen_id = specimen_details[0].get("specimenID")
+
+    return {
+        "bodySite": specimen_details[0].get("specimenSite", ""),
+        "receivedDate": specimen_details[0].get("specimenReceivedDate", ""),
+        "collDate": specimen_details[0].get("specimenCollectionDate", ""),
+        "specimenId": str(maybe_specimen_id) if maybe_specimen_id else None,
+        "specimenTypes": specimen_types if specimen_types else None,
+    }
+
+
+def standardize_specimen_details(
+    specimen_details: SpecimenDetails | list[SpecimenDetails],
+    log: Logger,
+) -> list[SpecimenDetails]:
+    """
+    Specimen details can be a single dictionary or a list of dictionaries
+    This function standardizes the input to always be a list of dictionaries
+
+    If it is a list, we expect all the specimens to have the same site and warn otherwise.
+    """
+    if isinstance(specimen_details, dict):
+        return [specimen_details]
+
+    # Sometimes, we have multiple specimen details
+    # In this case, we expect them to all be the same and warn otherwise
+    sites = {specimen.get("specimenSite") for specimen in specimen_details}
+
+    if len(sites) > 1:
+        log.warning("Multiple specimen sites found")
+
+    return specimen_details
+
+
+def extract_and_parse_specimen_details(data: dict, log: Logger) -> ParsedSpecimenDetails:
+    specimen_information = data["specimenInformation"]
+    specimen_details: SpecimenDetails | list[SpecimenDetails] | None = None
+
+    # The key for the specimen details varies based on the test type
+    potential_keys = [
+        # Tissue case
+        "tumorSpecimenInformation",
+        # Liquid case
+        "liquidBiopsySpecimenInformation",
+    ]
+    for key in potential_keys:
+        if key in specimen_information:
+            specimen_details = cast(
+                SpecimenDetails | list[SpecimenDetails], specimen_information[key]
+            )
+            break
+
+    if not specimen_details:
+        raise ValueError("No specimen details found in data")
+
+    specimen_details = standardize_specimen_details(specimen_details, log)
+
+    return parse_specimen_details(specimen_details)

{phc-ingestion-0.8.42 → phc-ingestion-0.9.1}/ingestion/foundation/util/ga4gh.py

@@ -190,6 +190,19 @@ def get_test_yml(
     reportDate = str(get_date(signatures.get("Signature").get("ServerTime")))[0:10]
     indexedDate = reportDate
 
+    sample_id = (sample.get("SampleId") or "").strip()
+    block_id = (sample.get("BlockId") or "").strip()
+    if block_id == "N/A":
+        block_id = ""
+
+    specimen_ids = []
+    if sample_id:
+        specimen_ids.append(sample_id)
+    if block_id:
+        specimen_ids.append(block_id)
+
+    specimenType = sample.get("SpecFormat", "").strip()
+
     yaml_file = {
         "name": "Foundation Medicine",
         "reference": "GRCh37",
@@ -216,6 +229,11 @@ def get_test_yml(
         "files": [],
     }
 
+    if specimen_ids:
+        yaml_file["specimenIds"] = specimen_ids
+    if specimenType:
+        yaml_file["specimenTypes"] = [specimenType]
+
     if write_to_manifest["cnv"]:
         yaml_file["files"].append(
             {

{phc-ingestion-0.8.42 → phc-ingestion-0.9.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "phc-ingestion"
-version = "0.8.42"
+version = "0.9.1"
 description = "Functions for LifeOmic PHC genomic ingestions"
 authors = [
     { name = "LifeOmic Development", email = "development@lifeomic.com" },

phc-ingestion-0.8.42/ingestion/caris/util/specimen_details.py

@@ -1,67 +0,0 @@
-from logging import Logger
-from typing import TypedDict, cast
-
-
-class SpecimenDetails(TypedDict, total=False):
-    """A partial representation of the specimen details in the Caris JSON file"""
-
-    specimenReceivedDate: str
-    specimenCollectionDate: str
-    specimenSite: str
-
-
-class ParsedSpecimenDetails(TypedDict):
-    bodySite: str
-    receivedDate: str
-    collDate: str
-
-
-def parse_specimen_details(specimen_details: SpecimenDetails) -> ParsedSpecimenDetails:
-    return {
-        "bodySite": specimen_details.get("specimenSite", ""),
-        "receivedDate": specimen_details.get("specimenReceivedDate", ""),
-        "collDate": specimen_details.get("specimenCollectionDate", ""),
-    }
-
-
-def ensure_single_specimen_details(
-    specimen_details: SpecimenDetails | list[SpecimenDetails],
-    log: Logger,
-) -> SpecimenDetails:
-    if isinstance(specimen_details, dict):
-        return specimen_details
-
-    # Sometimes, we have multiple specimen details
-    # In this case, we expect them to all be the same and warn otherwise
-    sites = {specimen["specimenSite"] for specimen in specimen_details}
-
-    if len(sites) > 1:
-        log.warn(f"Multiple specimen sites found")
-
-    return specimen_details[0]
-
-
-def extract_and_parse_specimen_details(data: dict, log: Logger) -> ParsedSpecimenDetails:
-    specimen_information = data["specimenInformation"]
-    specimen_details: SpecimenDetails | list[SpecimenDetails] | None = None
-
-    # The key for the specimen details varies based on the test type
-    potential_keys = [
-        # Tissue case
-        "tumorSpecimenInformation",
-        # Liquid case
-        "liquidBiopsySpecimenInformation",
-    ]
-    for key in potential_keys:
-        if key in specimen_information:
-            specimen_details = cast(
-                SpecimenDetails | list[SpecimenDetails], specimen_information[key]
-            )
-            break
-
-    if not specimen_details:
-        raise ValueError("No specimen details found in data")
-
-    specimen_details = ensure_single_specimen_details(specimen_details, log)
-
-    return parse_specimen_details(specimen_details)