phc-ingestion 0.8.33__tar.gz → 0.8.34__tar.gz

{phc-ingestion-0.8.33 → phc-ingestion-0.8.34}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phc-ingestion
-Version: 0.8.33
+Version: 0.8.34
 Summary: Functions for LifeOmic PHC genomic ingestions
 License: MIT
 Author-email: LifeOmic Development <development@lifeomic.com>

phc-ingestion-0.8.34/ingestion/nextgen/util/interpretation.py

@@ -0,0 +1,28 @@
+from logging import Logger
+
+
+def map_interpretation(status: str, log: Logger):
+    """
+    Map interpretation for structural and copy number variants
+    """
+    if status == "Pathogenic":
+        return "Pathogenic"
+    elif "VUS" in status:
+        return "Uncertain significance"
+    else:
+        log.error(f"Failed to resolve interpretation: {status}")
+        return ""
+
+
+def map_vendsig(vendsig: str) -> str:
+    """
+    Map vendor significance for short variants
+    """
+    if vendsig in ["Pathogenic"]:
+        return "VENDSIG=Pathogenic"
+    elif vendsig in ["Likely Pathogenic", "LikelyPathogenic"]:
+        return "VENDSIG=Likely pathogenic"
+    elif vendsig in ["VUS"]:
+        return "VENDSIG=Uncertain significance"
+    else:
+        raise RuntimeError(f"Unable to map vendor significance: {vendsig}")

{phc-ingestion-0.8.33 → phc-ingestion-0.8.34}/ingestion/nextgen/util/nextgen_specific_genes.py

@@ -14,7 +14,7 @@ nextgen_specific_genes_with_location: list[GeneWithLocation] = [
     {"gene": "CCND3", "chr": "chr6", "start": 41920534, "end": 42562008},
     {"gene": "MYC", "chr": "chr8", "start": 125309416, "end": 129673293},
     {"gene": "CCND1", "chr": "chr11", "start": 69090733, "end": 69656860},
-    {"gene": "IGH", "chr": "chr14", "start": 105516968, "end": 109902208},
+    {"gene": "IGH", "chr": "chr14", "start": 105325507, "end": 109902208},
     {"gene": "MAF", "chr": "chr16", "start": 78428398, "end": 79615096},
     {"gene": "MAFB", "chr": "chr20", "start": 39039005, "end": 40688948},
     {"gene": "IGL", "chr": "chr22", "start": 22012552, "end": 22965858},

{phc-ingestion-0.8.33 → phc-ingestion-0.8.34}/ingestion/nextgen/util/process_manifest.py

@@ -65,7 +65,7 @@ def get_cell_purity(interpretation_lines: list):
         return float(00.00)
 
 
-def extract_patient_data(patient_info_lines: list):
+def extract_patient_data(patient_info_lines: list[str]):
     patient_data: dict = {}
     patient_data["patientInfo"] = {}
 

{phc-ingestion-0.8.33 → phc-ingestion-0.8.34}/ingestion/nextgen/util/process_vcf.py

@@ -5,6 +5,7 @@ from logging import Logger
 from typing import Literal
 
 from ingestion.nextgen.util.alteration_table import AlterationTableRow, ShortVariantGene
+from ingestion.nextgen.util.interpretation import map_vendsig
 
 SequenceType = Literal["somatic", "germline"]
 
@@ -204,17 +205,6 @@ def process_vcf(
     return {"vcf_path_name": vcf_path, "vcf_line_count": line_count}
 
 
-def map_vendsig(vendsig: str) -> str:
-    if vendsig in ["Pathogenic"]:
-        return "VENDSIG=Pathogenic"
-    elif vendsig in ["Likely Pathogenic", "LikelyPathogenic"]:
-        return "VENDSIG=Likely pathogenic"
-    elif vendsig in ["VUS"]:
-        return "VENDSIG=Uncertain significance"
-    else:
-        raise RuntimeError(f"Unable to map vendor significance: {vendsig}")
-
-
 def add_vendsig_to_info(
     info: str,
     short_variant_table_rows: list[AlterationTableRow[ShortVariantGene]],

{phc-ingestion-0.8.33 → phc-ingestion-0.8.34}/ingestion/vcf_standardization/Variant.py

@@ -18,7 +18,7 @@ class Variant:
         self.info = {x.split("=")[0]: x.split("=")[1] for x in fields[7].split(";") if "=" in x}
         self.frmt = fields[8].split(":")
         self.smpl = fields[9].split(":")
-        self.ad_af_dp = {"AD": False, "AF": False, "DP": False}
+        self.ad_af_dp: dict[str, bool | str] = {"AD": False, "AF": False, "DP": False}
 
     def standardize_allele_frequency(self, log):
         # Detect if allele frequency is present either in the INFO or FORMAT/SAMPLE fields
@@ -131,19 +131,19 @@ class Variant:
         )
         return updated_variant
 
+    @classmethod
+    def check_formatting(cls, var: str):
+        # Loose formatting check, return as Variant class object
+        split_var = var.split("\t")
+        if len(split_var) < 8 or not split_var[1].isdigit():
+            raise RuntimeError(f"Variant contains incorrect number, or invalid fields:  {var}")
 
-def check_formatting(var: str) -> Variant:
-    # Loose formatting check, return as Variant class object
-    split_var = var.split("\t")
-    if len(split_var) < 8 or not split_var[1].isdigit():
-        raise RuntimeError(f"Variant contains incorrect number, or invalid fields:  {var}")
+        if len(split_var) == 8:
+            split_var.append(".")  # Add placeholder for FORMAT
+            split_var.append(".")  # Add placeholder for SAMPLE
 
-    if len(split_var) == 8:
-        split_var.append(".")  # Add placeholder for FORMAT
-        split_var.append(".")  # Add placeholder for SAMPLE
+        elif len(split_var) == 9:
+            split_var.append(".")  # Add placeholder for SAMPLE
 
-    elif len(split_var) == 9:
-        split_var.append(".")  # Add placeholder for SAMPLE
-
-    working_variant = Variant(split_var)
-    return working_variant
+        working_variant = cls(split_var)
+        return working_variant

{phc-ingestion-0.8.33 → phc-ingestion-0.8.34}/ingestion/vcf_standardization/standardize.py

@@ -9,15 +9,15 @@ from ingestion.vcf_standardization.util.read_write import (
     read_headers,
     read_variants,
 )
-from ingestion.vcf_standardization.Variant import check_formatting
+from ingestion.vcf_standardization.Variant import Variant
 
 
-def format_variant(variant: str, log: Logger, vendsig_dict: dict = None) -> Optional[str]:
+def format_variant(variant: str, log: Logger, vendsig_dict: dict | None = None) -> Optional[str]:
     # Ignore structural variants
     if "SVTYPE" in variant:
         return None
     # Working variant
-    wv = check_formatting(variant)
+    wv = Variant.check_formatting(variant)
 
     # Only process variants that aren't multiallelic
     if len(wv.alt.split(",")) == 1:
@@ -48,7 +48,7 @@ def standardize_vcf(
     out_path: str,
     case_id: str,
     log: Logger,
-    vendsig_dict: dict = None,
+    vendsig_dict: dict | None = None,
     compression: bool = False,
 ) -> Optional[int]:
     check_vcf(infile, log)

{phc-ingestion-0.8.33 → phc-ingestion-0.8.34}/ingestion/vcf_standardization/util/read_write.py

@@ -1,10 +1,11 @@
 import gzip
+from logging import Logger
 import re
 import os
 from typing import Iterator, Optional
 
 
-def check_vcf(infile, log):
+def check_vcf(infile: str, log: Logger) -> None:
     log.info("Checking VCF file")
     # Check if file exists. Raise if it doesn't.
     if os.path.exists(infile) == False:
@@ -68,7 +69,7 @@ def write_vcf(
     compression: bool,
     line_count: int,
     log,
-):
+) -> int:
     log.info(f"Writing standardized VCF to {outfile}")
 
     with gzip.open(outfile, "wt") if compression else open(outfile, "w") as w:

{phc-ingestion-0.8.33 → phc-ingestion-0.8.34}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "phc-ingestion"
-version = "0.8.33"
+version = "0.8.34"
 description = "Functions for LifeOmic PHC genomic ingestions"
 authors = [
     { name = "LifeOmic Development", email = "development@lifeomic.com" },

phc-ingestion-0.8.33/ingestion/nextgen/util/interpretation.py

@@ -1,11 +0,0 @@
-from logging import Logger
-
-
-def map_interpretation(status: str, log: Logger):
-    if status == "Pathogenic":
-        return "Pathogenic"
-    elif "VUS" in status:
-        return "Uncertain significance"
-    else:
-        log.error(f"Failed to resolve interpretation: {status}")
-        return ""