phc-ingestion 0.8.26__tar.gz → 0.8.28__tar.gz

{phc-ingestion-0.8.26 → phc-ingestion-0.8.28}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phc-ingestion
-Version: 0.8.26
+Version: 0.8.28
 Summary: Functions for LifeOmic PHC genomic ingestions
 License: MIT
 Author-email: LifeOmic Development <development@lifeomic.com>

{phc-ingestion-0.8.26 → phc-ingestion-0.8.28}/ingestion/nextgen/process.py

@@ -46,7 +46,7 @@ def process(
             prefix=case_id,
             log=log,
         )
-        structural_path_name = process_structural(
+        structural_path_name, translocations = process_structural(
             xml_in_file=vendor_files["xmlFile"],
             sv_in_file=vendor_files["somaticSvVcfFile"],
             root_path=local_output_dir,
@@ -59,6 +59,7 @@ def process(
             prefix=case_id,
             include_copy_number=bool(cnv_path_name),
             include_structural=bool(structural_path_name),
+            somatic_translocations=translocations,
             log=log,
         )
         pre_filtered_somatic_vcf_path = pre_filter_somatic_vcf(

phc-ingestion-0.8.28/ingestion/nextgen/util/nextgen_specific_genes.py

@@ -0,0 +1,29 @@
+from typing import TypedDict
+
+
+class GeneWithLocation(TypedDict):
+    gene: str
+    chr: str
+    start: int
+    end: int
+
+
+nextgen_specific_genes_with_location: list[GeneWithLocation] = [
+    {"gene": "IGK", "chr": "chr2", "start": 88852034, "end": 90258119},
+    {"gene": "NSD2", "chr": "chr4", "start": 1792518, "end": 1940193},
+    {"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": 105578834, "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},
+]
+nextgen_specific_genes: set[str] = {gene["gene"] for gene in nextgen_specific_genes_with_location}
+
+
+def maybe_get_matching_gene_for_location(chr: str, position: int) -> str | None:
+    for gene in nextgen_specific_genes_with_location:
+        if gene["chr"] == chr and gene["start"] <= position <= gene["end"]:
+            return gene["gene"]
+    return None

{phc-ingestion-0.8.26 → phc-ingestion-0.8.28}/ingestion/nextgen/util/process_manifest.py

@@ -176,6 +176,7 @@ def process_manifest(
     prefix: str,
     include_copy_number: bool,
     include_structural: bool,
+    somatic_translocations: list[str],
     log: Logger,
 ):
     test_text = extract_xml_text(xml_in_file)
@@ -186,6 +187,8 @@ def process_manifest(
     hyperdiploidy_chromosomes = manifest_helpers.extract_hyperdiploidy_chromosomes(xml_in_file, log)
     if hyperdiploidy_chromosomes:
         manifest["hyperdiploidyTrisomies"] = hyperdiploidy_chromosomes
+    if somatic_translocations:
+        manifest["somaticTranslocations"] = somatic_translocations
 
     manifest["reportFile"] = f".lifeomic/nextgen/{prefix}/{prefix}.pdf"
     manifest["sourceFileId"] = source_file_id

{phc-ingestion-0.8.26 → phc-ingestion-0.8.28}/ingestion/nextgen/util/process_structural.py

@@ -5,6 +5,10 @@ from typing import TypedDict
 from ingestion.shared_util.coords_to_genes import coords_to_genes
 from ingestion.nextgen.util.alteration_table import extract_variant_table
 from ingestion.nextgen.util.interpretation import map_interpretation
+from ingestion.nextgen.util.nextgen_specific_genes import (
+    maybe_get_matching_gene_for_location,
+    nextgen_specific_genes,
+)
 from ingestion.shared_util.open_maybe_gzipped import open_maybe_gzipped
 
 
@@ -42,9 +46,26 @@ def is_del_dup_or_ins(variant: list[str]) -> bool:
     return any([x in variant[2] for x in ["MantaDEL", "MantaDUP", "MantaINS"]])
 
 
+def get_gene_from_coords(
+    chromosome: str, start_position: str, end_position: str, log: Logger
+) -> str:
+    """
+    A number of genes of interest with specific start and end positions have been provided.
+    If a variant falls within the start and end positions of one of those genes of interest, that gene will be used.
+    Otherwise, we fall back to the standard gene lookup.
+    """
+    center_position = int((int(start_position) + int(end_position)) / 2)
+
+    gene = maybe_get_matching_gene_for_location(chromosome, center_position)
+    if gene:
+        return gene
+
+    return coords_to_genes("GRCh38", chromosome, center_position, log)
+
+
 def process_structural(
     sv_in_file: str, xml_in_file, root_path: str, prefix: str, log: Logger
-) -> str | None:
+) -> tuple[str | None, list[str]]:
     structural_variant_table = extract_variant_table(
         xml_in_file=xml_in_file, variant_type="structural", log=log
     )
@@ -74,9 +95,7 @@ def process_structural(
                 effect = "insertion"
 
             # Get genes from coordinates using center point of start and end positions
-            gene1 = coords_to_genes(
-                "GRCh38", chromosome1, int((int(start_position1) + int(end_position1)) / 2), log
-            )
+            gene1 = get_gene_from_coords(chromosome1, start_position1, end_position1, log)
             gene2 = "N/A"
 
         else:
@@ -89,12 +108,8 @@ def process_structural(
             effect = "translocation"
 
             # Get genes from coordinates using center point of start and end positions
-            gene1 = coords_to_genes(
-                "GRCh38", chromosome1, int((int(start_position1) + int(end_position1)) / 2), log
-            )
-            gene2 = coords_to_genes(
-                "GRCh38", chromosome2, int((int(start_position2) + int(end_position2)) / 2), log
-            )
+            gene1 = get_gene_from_coords(chromosome1, start_position1, end_position1, log)
+            gene2 = get_gene_from_coords(chromosome2, start_position2, end_position2, log)
 
         # Scrape interpretation
         interpretation = "unknown"
@@ -149,7 +164,7 @@ def process_structural(
 
     if not deduped_structural_variants:
         log.info(f"Ignoring empty structural variant file {sv_in_file}")
-        return None
+        return (None, [])
 
     log.info(f"Saving file to {structural_variant_path_name}")
     with open(structural_variant_path_name, "w+") as f:
@@ -159,4 +174,24 @@ def process_structural(
         for sv in deduped_structural_variants:
             f.write(structural_variant_to_csv_row(sv))
 
-    return structural_variant_path_name
+    log.info("Finding structural variant translocations for genes of interest")
+    translocations = [sv for sv in deduped_structural_variants if sv["effect"] == "translocation"]
+    formatted_translocations: set[str] = set()
+    for translocation in translocations:
+        gene1, gene2 = translocation["gene1"], translocation["gene2"]
+        # MYC is a special case
+        if gene1 == "MYC" or gene2 == "MYC":
+            formatted_translocations.add("t(MYC)")
+            continue
+        if gene1 in nextgen_specific_genes and gene2 in nextgen_specific_genes:
+            chr1, chr2 = int(translocation["position1"][0][3:]), int(
+                translocation["position2"][0][3:]
+            )
+            # Ensure chromosomes are in ascending order
+            if chr1 > chr2:
+                chr1, chr2 = chr2, chr1
+            formatted_translocations.add(f"t({chr1};{chr2})")
+
+    log.info(f"Found {len(formatted_translocations)} translocations for genes of interest")
+
+    return structural_variant_path_name, list(formatted_translocations)

{phc-ingestion-0.8.26 → phc-ingestion-0.8.28}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "phc-ingestion"
-version = "0.8.26"
+version = "0.8.28"
 description = "Functions for LifeOmic PHC genomic ingestions"
 authors = [
     { name = "LifeOmic Development", email = "development@lifeomic.com" },