phc-ingestion 0.8.25__py3-none-any.whl → 0.8.27__py3-none-any.whl

ingestion/nextgen/util/nextgen_specific_genes.py

@@ -0,0 +1,28 @@
+from typing import TypedDict
+
+
+class GeneWithLocation(TypedDict):
+    gene: str
+    chr: str
+    start: int
+    end: int
+
+
+nextgen_specific_genes: 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},
+]
+
+
+def maybe_get_matching_gene_for_location(chr: str, position: int) -> str | None:
+    for gene in nextgen_specific_genes:
+        if gene["chr"] == chr and gene["start"] <= position <= gene["end"]:
+            return gene["gene"]
+    return None

ingestion/nextgen/util/pre_filter_somatic_vcf.py

@@ -9,6 +9,17 @@ def build_variant_key_from_vcf_line(line: str) -> str:
     return f"{chrom}:{pos}:{ref}:{alt}"
 
 
+def extract_filter_from_vcf_line(line: str) -> str:
+    split_line = line.strip().split("\t")
+    return split_line[6]
+
+
+def replace_filter_in_vcf_line(line: str, new_filter: str) -> str:
+    split_line = line.strip().split("\t")
+    split_line[6] = new_filter
+    return "\t".join(split_line) + "\n"
+
+
 def pre_filter_somatic_vcf(
     somatic_vcf_file: str,
     somatic_vcf_snv_file: str,
@@ -19,22 +30,25 @@ def pre_filter_somatic_vcf(
     """
     Removes all variants from the `somatic_vcf_file` that are not
     also in the `somatic_vcf_snv_file` or `somatic_vcf_indel_file`.
+
+    Also updates the FILTER field in the `somatic_vcf_file` to match
+    the FILTER field of the corresponding variant in the
+    `somatic_vcf_snv_file` or `somatic_vcf_indel_file`.
     """
     log.info("Pre-filtering somatic VCF file")
 
-    valid_variant_keys = set()
-    with open_maybe_gzipped(somatic_vcf_snv_file, "rt") as f:
-        for line in f:
-            if line.startswith("#"):
-                continue
-            valid_variant_keys.add(build_variant_key_from_vcf_line(line))
-    with open_maybe_gzipped(somatic_vcf_indel_file, "rt") as f:
-        for line in f:
-            if line.startswith("#"):
-                continue
-            valid_variant_keys.add(build_variant_key_from_vcf_line(line))
+    valid_variants_with_filters: dict[str, str] = {}
+
+    for file in [somatic_vcf_snv_file, somatic_vcf_indel_file]:
+        with open_maybe_gzipped(file, "rt") as f:
+            for line in f:
+                if line.startswith("#"):
+                    continue
+                valid_variants_with_filters[build_variant_key_from_vcf_line(line)] = (
+                    extract_filter_from_vcf_line(line)
+                )
 
-    log.info(f"Found {len(valid_variant_keys)} valid variants")
+    log.info(f"Found {len(valid_variants_with_filters)} valid variants")
 
     output_vcf_path = f"{working_dir}/filtered_somatic.vcf.gz"
     with (
@@ -45,8 +59,9 @@ def pre_filter_somatic_vcf(
             if line.startswith("#"):
                 w.write(line)
             else:
-                if build_variant_key_from_vcf_line(line) in valid_variant_keys:
-                    w.write(line)
+                key = build_variant_key_from_vcf_line(line)
+                if key in valid_variants_with_filters:
+                    w.write(replace_filter_in_vcf_line(line, valid_variants_with_filters[key]))
 
     log.info(f"Successfully pre-filtered somatic VCF file to {output_vcf_path}")
     return output_vcf_path

ingestion/nextgen/util/process_structural.py

@@ -5,6 +5,7 @@ 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
 from ingestion.shared_util.open_maybe_gzipped import open_maybe_gzipped
 
 
@@ -42,6 +43,23 @@ 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:
@@ -74,9 +92,7 @@ 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 +105,8 @@ 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"

{phc_ingestion-0.8.25.dist-info → phc_ingestion-0.8.27.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phc-ingestion
-Version: 0.8.25
+Version: 0.8.27
 Summary: Functions for LifeOmic PHC genomic ingestions
 License: MIT
 Author-email: LifeOmic Development <development@lifeomic.com>

{phc_ingestion-0.8.25.dist-info → phc_ingestion-0.8.27.dist-info}/RECORD

@@ -33,10 +33,11 @@ ingestion/nextgen/process.py,sha256=GKiQ2dCxrR7tBD8TSP6Wk-TyoX3xBGip5zfpeT2buiQ,
 ingestion/nextgen/util/alteration_table.py,sha256=KwpJCQv_rVsL30jkzgZn0bKdd205fjVodYBNTcK3D1s,4220
 ingestion/nextgen/util/interpretation.py,sha256=ozuzb0vozff34zfP6AdOiUmI8Q77hI02jve_nCPZHfE,297
 ingestion/nextgen/util/manifest_helpers.py,sha256=PpSay-pe62jk735nom1tVD9nDE8-CxmzzCrgpBhgtjY,1571
-ingestion/nextgen/util/pre_filter_somatic_vcf.py,sha256=beAtOpznVtUOWKCUNNv1UukNBSa0LKmhXsJ_3K5xk2E,1759
+ingestion/nextgen/util/nextgen_specific_genes.py,sha256=KcZ9HzUUobsLFM7z7oaXdnpVnY5-niYR-VSMKY985Po,1084
+ingestion/nextgen/util/pre_filter_somatic_vcf.py,sha256=K_gH4EnUXrKB22u_f8FqQVGrOS5LxXNsNO3VBn381eY,2301
 ingestion/nextgen/util/process_cnv.py,sha256=m-AhsXFlYw4LTzgJJaj5vXYbK5n3H7cImzBxD2To6M0,2598
 ingestion/nextgen/util/process_manifest.py,sha256=TAbCHwN_2m08jySn1J4qEd9Nrxjw9CrsspwFWack0V4,8448
-ingestion/nextgen/util/process_structural.py,sha256=BXhwbRtFLTZsDi4ioSna1qmMtxVcsB0R-xNIvymm5Vw,5947
+ingestion/nextgen/util/process_structural.py,sha256=9xdJnSYtIT86lbhEIsPop39NGMwLHuqQGqlcQttlt64,6520
 ingestion/nextgen/util/process_vcf.py,sha256=TvyV5wyXXSpFy2lc6h3ljqVQ5VeDPGxihHl2_K6LalQ,8432
 ingestion/nextgen/util/types.py,sha256=SSzt5gv-kss1PR45eQUelypWrGI-dAfQMO3GSD-T-Wg,22
 ingestion/resources/GRCh37_map.csv.gz,sha256=JOEkjtbYrJpIdyoZdCvfJhvvz2dNfkSve7lXSXkCCD8,408290
@@ -53,6 +54,6 @@ ingestion/vcf_standardization/util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQe
 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=IQotJ27To1MoQcRstc5AbHZtUuJz5cqkkZiHsDNaBvI,2471
-phc_ingestion-0.8.25.dist-info/WHEEL,sha256=B19PGBCYhWaz2p_UjAoRVh767nYQfk14Sn4TpIZ-nfU,87
-phc_ingestion-0.8.25.dist-info/METADATA,sha256=AU2E4U0eLh5aXCGiCmVsVloyruqmkF_oNdkv7rmAfBQ,552
-phc_ingestion-0.8.25.dist-info/RECORD,,
+phc_ingestion-0.8.27.dist-info/WHEEL,sha256=B19PGBCYhWaz2p_UjAoRVh767nYQfk14Sn4TpIZ-nfU,87
+phc_ingestion-0.8.27.dist-info/METADATA,sha256=vNzI7puyTHjuXFU7CBTQ4tUOiXxHF3aYUWAPgnFnA0Y,552
+phc_ingestion-0.8.27.dist-info/RECORD,,