phc-ingestion 0.9.1__tar.gz → 0.9.3__tar.gz

{phc-ingestion-0.9.1 → phc-ingestion-0.9.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phc-ingestion
-Version: 0.9.1
+Version: 0.9.3
 Summary: Functions for LifeOmic PHC genomic ingestions
 License: MIT
 Author-email: LifeOmic Development <development@lifeomic.com>

{phc-ingestion-0.9.1 → phc-ingestion-0.9.3}/ingestion/foundation/process.py

@@ -11,25 +11,7 @@ from ingestion.foundation.util.vcf_etl import vcf_etl
 
 def read_xml(xml_file: str) -> dict:
     with open(xml_file) as fd:
-        return xmltodict.parse(fd.read())
-
-
-def get_specimen_name(results_payload_dict: dict) -> str:
-    specimen_name = None
-    if isinstance(results_payload_dict["variant-report"]["samples"]["sample"], list):
-        found = list(
-            filter(
-                lambda x: x["@nucleic-acid-type"] == "DNA",
-                results_payload_dict["variant-report"]["samples"]["sample"],
-            )
-        )
-        if len(found) > 0:
-            specimen_name = found[0]["@name"]
-    else:
-        specimen_name = results_payload_dict["variant-report"]["samples"]["sample"]["@name"]
-    if not specimen_name:
-        raise RuntimeError("Failed to find specimen name")
-    return specimen_name  # type: ignore
+        return xmltodict.parse(fd.read(), force_list=("reportProperty", "non-human", "Gene"))
 
 
 def process(
@@ -45,8 +27,6 @@ def process(
         customer_info_dict = xml_dict["rr:ResultsReport"]["rr:CustomerInformation"]
         results_payload_dict = xml_dict["rr:ResultsReport"]["rr:ResultsPayload"]
 
-        sample_name = get_specimen_name(results_payload_dict)
-
         base_xml_name = Path(xml_file).stem
 
         vcf_name = f"{local_output_dir}/{base_xml_name}/{base_xml_name}.modified.vcf"

{phc-ingestion-0.9.1 → phc-ingestion-0.9.3}/ingestion/foundation/util/ga4gh.py

@@ -47,25 +47,15 @@ def get_ordering_md(pmi, npi) -> list:
     return ordering_md_info
 
 
-def get_non_human_content(nhc_dicts) -> list:
+def get_non_human_content(nhc_dicts: list[dict]) -> list:
     nhc_final = []
 
-    if isinstance(nhc_dicts, list):
-        for sub_dict in nhc_dicts:
-            nhc_final.append(
-                {
-                    "nhcOrganism": sub_dict.get("@organism", "unknown"),
-                    "nhcReadsPerMil": float(sub_dict.get("@reads-per-million", 0.0)),
-                    "nhcStatus": sub_dict.get("@status", "unknown"),
-                }
-            )
-
-    else:
+    for sub_dict in nhc_dicts:
         nhc_final.append(
             {
-                "nhcOrganism": nhc_dicts.get("@organism", "unknown"),
-                "nhcReadsPerMil": float(nhc_dicts.get("@reads-per-million", 0.0)),
-                "nhcStatus": nhc_dicts.get("@status", "unknown"),
+                "nhcOrganism": sub_dict.get("@organism", "unknown"),
+                "nhcReadsPerMil": float(sub_dict.get("@reads-per-million", 0.0)),
+                "nhcStatus": sub_dict.get("@status", "unknown"),
             }
         )
 
@@ -90,6 +80,8 @@ def get_plasma_tumor_fraction(genes) -> Optional[str]:
     ptf_entry = next((entry for entry in entries if entry.get("Name", "") in ptf_entry_names), None)
     if ptf_entry:
         ptf_val = ptf_entry.get("Alterations", {}).get("Alteration", {}).get("Name", "")
+        if ptf_val in ["> 0%", ">0%"]:
+            return "Elevated"
         try:
             # See https://github.com/lifeomic/phc-ingestion/pull/129
             float_val = float(ptf_val.strip("%"))
@@ -150,11 +142,11 @@ def get_test_yml(
     biomarkers = variant_report.get("biomarkers", {})
     non_human_content = variant_report.get("non-human-content", {})
     report_properties = results_payload_dict.get("FinalReport", {}).get("reportProperties", {})
-    report_property = report_properties.get("reportProperty", [])
-    genes = results_payload_dict.get("FinalReport", {}).get("Genes", {})
+    properties = report_properties.get("reportProperty", [])
+    # `Genes` may exist as a key but have a value of None, so we need to ensure it defaults to an empty dict
+    genes = results_payload_dict.get("FinalReport", {}).get("Genes", {}) or {}
     plasma_tumor_fraction = get_plasma_tumor_fraction(genes)
     hrd_status = get_hrd_status(genes)
-    properties = report_property if isinstance(report_property, list) else [report_property]
     gw_loh = next(
         (prop for prop in properties if prop.get("@key") == "LossOfHeterozygosityScore"),
         None,
@@ -283,8 +275,7 @@ def get_test_yml(
     if gw_loh:
         values = {"loh-high": "high", "loh-low": "low"}
         alterations = []
-        gene = genes.get("Gene", [])
-        genes_list = gene if isinstance(gene, list) else [gene]
+        genes_list = genes.get("Gene", [])
         for gene in genes_list:
             alt = gene.get("Alterations", {}).get("Alteration", [])
             alterations.extend(alt) if isinstance(alt, list) else alterations.append(alt)
@@ -317,7 +308,7 @@ def get_test_yml(
 
     # adding non-human content fields
     if non_human_content != None:
-        yaml_file["nonHumanContent"] = get_non_human_content(non_human_content.get("non-human", ""))
+        yaml_file["nonHumanContent"] = get_non_human_content(non_human_content.get("non-human", []))
 
     if report_file:
         copyfile(report_file, f"{local_output_dir}/{base_xml_name}/{base_xml_name}.report.pdf")

phc-ingestion-0.9.3/ingestion/nebula/__init__.py

@@ -0,0 +1 @@
+from ingestion.nebula.process import process

phc-ingestion-0.9.3/ingestion/nebula/process.py

@@ -0,0 +1,46 @@
+import os
+from pathlib import Path
+from ingestion.vcf_standardization.standardize import standardize_vcf
+from lifeomic_logging import scoped_logger
+
+
+def process(vcf_file: str, source_file_id: str, out_path: str, case_id: str) -> dict:
+    with scoped_logger(__name__) as log:
+        # TODO: do we need to take in + process the manifest file here?
+
+        # Process VCF
+        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")
+        if not vcf_final.endswith(".gz"):
+            vcf_final = vcf_final + ".gz"
+
+        # Assuming Nebula VCFs are germline
+        sample_name = f"germline_{case_id}"
+        vcf_line_count = standardize_vcf(
+            vcf_file, vcf_out, out_path, sample_name, log, compression=True
+        )
+
+        # Create a basic manifest for the Nebula VCF
+        manifest = {
+            "testType": "Nebula",
+            "sourceFileId": source_file_id,
+            "reference": "GRCh38",  # Assuming GRCh38, adjust as needed
+            "resources": [{"fileName": f".lifeomic/nebula/{case_id}/{base_vcf_file}"}],
+            "files": [
+                {
+                    "fileName": f".lifeomic/nebula/{case_id}/{vcf_final}",
+                    "sequenceType": "germline",
+                    "type": "shortVariant",
+                }
+            ],
+        }
+
+        case_metadata = {
+            "test_type": "Nebula",
+            "vcf_line_count": vcf_line_count,
+            "case_id": case_id,
+            "germline_genome_reference": manifest["reference"],
+        }
+
+        return case_metadata, manifest

{phc-ingestion-0.9.1 → phc-ingestion-0.9.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "phc-ingestion"
-version = "0.9.1"
+version = "0.9.3"
 description = "Functions for LifeOmic PHC genomic ingestions"
 authors = [
     { name = "LifeOmic Development", email = "development@lifeomic.com" },