phc-ingestion 1.0.1__py3-none-any.whl → 1.0.3__py3-none-any.whl

ingestion/broad/process.py

@@ -0,0 +1,50 @@
+import os
+
+from ingestion.vcf_standardization.standardize import standardize_vcf
+from ingestion.broad.utils import check_manifest
+from lifeomic_logging import scoped_logger
+
+
+def process(
+    manifest_file: str, vcf_file: str, source_file_id: str, out_path: str, case_id: str
+) -> dict[str, str]:
+    with scoped_logger(__name__) as log:
+
+        # Read in supplied manifest
+        manifest = check_manifest(manifest_file, case_id, log)
+
+        # 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"
+        # All broad VCF ingestions are germline, so ensure the
+        # sample name is prefixed with "germline_". This matches
+        # the downstream logic in genomic-manifest
+        sample_name = f"germline_{case_id}"
+        vcf_line_count = standardize_vcf(
+            vcf_file, vcf_out, out_path, sample_name, log, compression=True
+        )
+
+        # Add to manifest
+        manifest["sourceFileId"] = source_file_id
+        manifest["resources"] = [
+            {"fileName": f".lifeomic/broad_filtered/{case_id}/{base_vcf_file}"}
+        ]
+        manifest["files"] = [
+            {
+                "fileName": f".lifeomic/broad_filtered/{case_id}/{vcf_final}",
+                "sequenceType": "germline",
+                "type": "shortVariant",
+            }
+        ]
+
+        case_metadata = {
+            "test_type": manifest["testType"],
+            "vcf_line_count": vcf_line_count,
+            "case_id": manifest["reportID"],
+            "germline_genome_reference": manifest["reference"],
+        }
+
+        return case_metadata, manifest

ingestion/broad/utils.py

@@ -0,0 +1,82 @@
+import os
+from logging import Logger
+from schema import Schema, SchemaError, Optional
+from ruamel.yaml import YAML
+
+
+def check_manifest(manifest_file_path: str, case_id, log: Logger):
+    manifest_schema = Schema(
+        {
+            # Required fields
+            "name": str,  # Vendor name
+            "testType": str,  # Vendor test name
+            "indexedDate": str,  # Date of ingestion YYYY-MM-DD
+            "reference": str,  # Reference genome
+            "mrn": str,  # Patient MRN
+            "patientInfo": {
+                "lastName": str,
+                "dob": str,  # YYYY-MM-DD
+                "firstName": str,
+                "gender": str,
+            },
+            # Optional fields
+            Optional("receivedDate"): str,
+            Optional("collDate"): str,
+            Optional("reportDate"): str,
+            Optional("reportFile"): str,
+            Optional("medFacilName"): str,
+            Optional("medFacilID"): str,
+            Optional("orderingMDName"): str,
+            Optional("orderingMDNPI"): str,
+            Optional("indicationSystem"): "http://lifeomic.com/fhir/sequence-indication",
+            Optional("indication"): str,
+            Optional("indicationDisplay"): str,
+            Optional("bodySite"): str,
+            Optional("bodySiteDisplay"): str,
+            Optional("bodySiteSystem"): "http://lifeomic.com/fhir/sequence-body-site",
+            Optional("tmb"): str,
+            Optional("tmbScore"): float,
+            Optional("msi"): str,
+            Optional("lossOfHeterozygosityScore"): int,
+            Optional("lossOfHeterozygosityStatus"): str,
+            Optional("ihcTests"): any,
+            Optional("nonHumanContent"): any,
+            Optional("plasmaTumorFraction"): str,
+            Optional("cellPurity"): float,
+            Optional("hrdStatus"): str,
+            Optional("sampleId"): str,
+        }
+    )
+
+    # Read in manifest yaml
+    if os.path.exists(manifest_file_path):
+        with open(manifest_file_path, "r") as file:
+            manifest = YAML(typ="safe")
+            manifest = manifest.load(file)
+    else:
+        raise FileNotFoundError(f"Manifest file not found: {manifest_file_path}")
+
+    # Validate
+    try:
+        manifest_schema.validate(manifest)
+    except SchemaError as e:
+        log.error(e)
+        raise e
+
+    # Add duplicate fields from supplied ones to fit formatting
+    manifest["patientInfo"]["identifiers"] = [
+        {
+            "codingCode": "MR",
+            "codingSystem": "http://hl7.org/fhir/v2/0203",
+            "value": manifest["mrn"],
+        }
+    ]
+
+    manifest["patientLastName"] = manifest["patientInfo"]["lastName"]
+
+    manifest["patientDOB"] = manifest["patientInfo"]["dob"]
+
+    manifest["reportID"] = case_id  # Vendor report ID / Case ID
+
+    log.info(f"Manifest file validated")
+    return manifest

ingestion/vcf_standardization/util/read_write.py

@@ -4,8 +4,6 @@ import re
 import os
 from typing import Iterator, Optional
 
-import pysam
-
 
 def check_vcf(infile: str, log: Logger) -> None:
     log.info("Checking VCF file")
@@ -74,35 +72,11 @@ def write_vcf(
 ) -> int:
     log.info(f"Writing standardized VCF to {outfile}")
 
-    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")
+    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")
 
     return line_count

{phc_ingestion-1.0.1.dist-info → phc_ingestion-1.0.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phc-ingestion
-Version: 1.0.1
+Version: 1.0.3
 Summary: Functions for LifeOmic PHC genomic ingestions
 License: MIT
 Author-email: LifeOmic Development <development@lifeomic.com>
@@ -13,7 +13,6 @@ 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-1.0.1.dist-info → phc_ingestion-1.0.3.dist-info}/RECORD

@@ -1,4 +1,7 @@
 ingestion/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ingestion/broad/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ingestion/broad/process.py,sha256=IrtnANQlbPpI7aza-N_v8qMyxBOX17jq904wDNq7Nng,1803
+ingestion/broad/utils.py,sha256=YHzbmB0tP-aQjvY9vRSn8iOhailleYwvctDbB0IEKb8,2853
 ingestion/caris/__init__.py,sha256=sFHl6qZWaacTbCFyikkIkuC-z459m5XQ7kwwoCw7HK8,61
 ingestion/caris/process.py,sha256=7GaSTg9LjqSn7iTNbY3FJIPFvVjkd6wgXiVC00pn-7A,1411
 ingestion/caris/util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -59,7 +62,7 @@ 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=xogLdqtm1xGzigY459LqP_1zM6c5X9AjAFGkfaDI-bg,3479
-phc_ingestion-1.0.1.dist-info/WHEEL,sha256=B19PGBCYhWaz2p_UjAoRVh767nYQfk14Sn4TpIZ-nfU,87
-phc_ingestion-1.0.1.dist-info/METADATA,sha256=jvycAlRde4lUsP8O87F9a5bSF3fFINgtkMrr5FKsqWE,705
-phc_ingestion-1.0.1.dist-info/RECORD,,
+ingestion/vcf_standardization/util/read_write.py,sha256=x3Pf6Dq8tmolblbCS5CrNmrcHS3FGfqBSFpFgvFGC4g,2526
+phc_ingestion-1.0.3.dist-info/WHEEL,sha256=B19PGBCYhWaz2p_UjAoRVh767nYQfk14Sn4TpIZ-nfU,87
+phc_ingestion-1.0.3.dist-info/METADATA,sha256=3B6vgXo5LbPEbaAxeCDBfhynbjPtpUd9KKSTpaO-S5Q,676
+phc_ingestion-1.0.3.dist-info/RECORD,,