Merge branch 'pydantic' of github.com:bihealth/snappy-pipeline into p…

…ydantic
bihealth · Jun 3, 2024 · 257c542 · 257c542
2 parents c68e056 + 7e1f359
commit 257c542
Show file tree

Hide file tree

Showing 5 changed files with 42 additions and 72 deletions.
diff --git a/snappy_pipeline/workflows/somatic_variant_signatures/__init__.py b/snappy_pipeline/workflows/somatic_variant_signatures/__init__.py
@@ -268,23 +268,24 @@ def get_result_files(self):
         assert len(mappers) > 0, "No valid mapper"
         callers = set(config.tools_somatic_variant_calling) & set(SOMATIC_VARIANT_CALLERS_MATCHED)
         assert len(callers) > 0, "No valid somatic variant caller"
+
+        anno_callers = []
+        filters = []
+        regions = []
         if config.is_filtered:
             anno_callers = set(config.tools_somatic_variant_annotation) & set(ANNOTATION_TOOLS)
             assert len(anno_callers) > 0, "No valid somatic variant annotation tool"
-            filters = list(
-                self.w_config.step_config["somatic_variant_filtration"].filter_sets.keys()
-            )
-            filters.append("no_filter")
-            filters = set(filters) & set(config.filters)
-            regions = list(
-                self.w_config.step_config["somatic_variant_filtration"].exon_lists.keys()
-            )
-            regions.append("genome_wide")
-            regions = set(regions) & set(config.filtered_regions)
-        else:
-            anno_callers = []
-            filters = []
-            regions = []
+            if len(config.filters) > 0:
+                filters = list(
+                    self.w_config.step_config["somatic_variant_filtration"].filter_sets.keys()
+                )
+                filters.append("no_filter")
+                filters = set(filters) & set(config.filters)
+                regions = list(
+                    self.w_config.step_config["somatic_variant_filtration"].exon_lists.keys()
+                )
+                regions.append("genome_wide")
+                regions = set(regions) & set(config.filtered_regions)
 
         yield from self._yield_result_files_matched(
             os.path.join("output", name_pattern, "out", name_pattern + ".tsv"),

diff --git a/snappy_wrappers/wrappers/vcf2maf/vcf_to_table/common_functions.py b/snappy_wrappers/wrappers/vcf2maf/vcf_to_table/common_functions.py
@@ -101,7 +101,7 @@ def variant_type(x, args=None):
     return [variant_type]
 
 
-strip_sequence_version_pattern = re.compile("\.[0-9]+$")  # noqa: W605
+strip_sequence_version_pattern = re.compile(r"\.[0-9]+$")
 
 
 def strip_sequence_version(x, args):

diff --git a/snappy_wrappers/wrappers/vcf2maf/vcf_to_table/parser.py b/snappy_wrappers/wrappers/vcf2maf/vcf_to_table/parser.py
@@ -8,7 +8,7 @@
 
 
 class VcfParser:
-    pattern = re.compile("^([^\[\]\s]+)(\[([0-9]+|REF)\])?$")  # noqa: W605
+    pattern = re.compile(r"^([^\[\]\s]+)(\[([0-9]+|REF)\])?$")
 
     def __init__(
         self,

diff --git a/snappy_wrappers/wrappers/vcf2maf/vcf_to_table/protein_mutation_parser.py b/snappy_wrappers/wrappers/vcf2maf/vcf_to_table/protein_mutation_parser.py
@@ -167,28 +167,14 @@ class ProteinMutationFormatException(Exception):
 
 @functools.lru_cache
 def _build_protein_pattern():
-    prefix = "^(([A-z0-9_\.\(\)-]+):)?p\.\(?"  # noqa: W605
-    postfix = "\)?$"  # noqa: W605
+    prefix = r"^(([A-z0-9_\.\(\)-]+):)?p\.\(?"
+    postfix = r"\)?$"
 
     aa = "(" + "|".join(aa_codes_short) + "|" + "|".join(aa_codes_long) + ")"
-    aaTer = (
-        "("
-        + "|".join(aa_codes_short)
-        + "|"
-        + "|".join(aa_codes_long)
-        + "|\*|Ter"  # noqa: W605
-        + ")"
-    )
-    aaAll = (
-        "("
-        + "|".join(aa_codes_short)
-        + "|"
-        + "|".join(aa_codes_long)
-        + "|\*|Ter|=|\?"  # noqa: W605
-        + ")"
-    )
+    aaTer = "(" + "|".join(aa_codes_short) + "|" + "|".join(aa_codes_long) + r"|\*|Ter" + ")"
+    aaAll = "(" + "|".join(aa_codes_short) + "|" + "|".join(aa_codes_long) + r"|\*|Ter|=|\?" + ")"
     nb = "([0-9]+)"
-    nb_unknown = "([0-9]+|\?)"  # noqa: W605
+    nb_unknown = r"([0-9]+|\?)"
 
     interval = aa + nb + "_" + aa + nb
     one_or_interval = aa + nb + "(_" + aa + nb + ")?"
@@ -202,17 +188,17 @@ def _build_protein_pattern():
 
     delins = one_or_interval + "delins" + "(" + aa + "*)" + aaTer
 
-    frameshift = aaTer + nb + aa + "fs" + "(Ter|\*)" + nb_unknown  # noqa: W605
+    frameshift = aaTer + nb + aa + "fs" + r"(Ter|\*)" + nb_unknown
 
-    extensionN = "(Met|M)1" + "ext(-[0-9]+|\?)"  # noqa: W605
-    extensionC = "(Ter|\*)" + nb + aa + "ext" + "(Ter|\*)" + nb_unknown  # noqa: W605
+    extensionN = "(Met|M)1" + r"ext(-[0-9]+|\?)"
+    extensionC = r"(Ter|\*)" + nb + aa + "ext" + r"(Ter|\*)" + nb_unknown
 
     pattern = (
         prefix
         + "("
         + "|".join(
             [
-                "(0\??|=|\?)",  # noqa: W605
+                r"(0\??|=|\?)",
                 substitution,  # 4: ref, 5: position, 6: alt
                 duplication,  # 7: start, 8: start pos, 10: end, 11: end pos
                 deletion,  # 12: start, 13: start pos, 15: end, 16: end pos
@@ -232,18 +218,11 @@ def _build_protein_pattern():
 
 @functools.lru_cache
 def _build_silent_dinucleotide():
-    prefix = "^(([A-z0-9_\.\(\)-]+):)?p\.\(?"  # noqa: W605
-    postfix = "\)?$"  # noqa: W605
+    prefix = r"^(([A-z0-9_\.\(\)-]+):)?p\.\(?"
+    postfix = r"\)?$"
 
     aa = "(" + "|".join(aa_codes_short) + "|" + "|".join(aa_codes_long) + ")"
-    aaTer = (
-        "("
-        + "|".join(aa_codes_short)
-        + "|"
-        + "|".join(aa_codes_long)
-        + "|\*|Ter"  # noqa: W605
-        + ")"
-    )
+    aaTer = "(" + "|".join(aa_codes_short) + "|" + "|".join(aa_codes_long) + r"|\*|Ter" + ")"
     nb = "([0-9]+)"
 
     return re.compile(prefix + aa + aaTer + "*" + nb + "=" + postfix)

diff --git a/tests/snappy_pipeline/workflows/test_workflows_somatic_variant_signatures.py b/tests/snappy_pipeline/workflows/test_workflows_somatic_variant_signatures.py
@@ -89,8 +89,8 @@ def somatic_variant_signatures_workflow(
 def test_tabulate_vcf_step_part_get_input_files(somatic_variant_signatures_workflow):
     """Tests TabulateVariantsStepPart.get_input_files()"""
     base_name = (
-        "SOMATIC_VARIANT_FILTRATION/output/{mapper}.{var_caller}.{anno_caller}.dkfz_bias_filter.eb_filter.{tumor_library}.{filter}.{region}/out/"
-        "{mapper}.{var_caller}.{anno_caller}.dkfz_bias_filter.eb_filter.{tumor_library}.{filter}.{region}"
+        "SOMATIC_VARIANT_FILTRATION/output/{mapper}.{var_caller}.{anno_caller}.filtered.{tumor_library}/out/"
+        "{mapper}.{var_caller}.{anno_caller}.filtered.{tumor_library}"
     )
     expected = {
         "vcf": base_name + ".vcf.gz",
@@ -104,8 +104,8 @@ def test_tabulate_vcf_step_part_get_output_files(somatic_variant_signatures_work
     """Tests TabulateVariantsStepPart.get_output_files()"""
     expected = {
         "tsv": (
-            "work/{mapper}.{var_caller}.{anno_caller}.dkfz_bias_filter.eb_filter.tabulate_vcf.{tumor_library}.{filter}.{region}/out/"
-            "{mapper}.{var_caller}.{anno_caller}.dkfz_bias_filter.eb_filter.tabulate_vcf.{tumor_library}.{filter}.{region}.tsv"
+            "work/{mapper}.{var_caller}.{anno_caller}.filtered.tabulate_vcf.{tumor_library}/out/"
+            "{mapper}.{var_caller}.{anno_caller}.filtered.tabulate_vcf.{tumor_library}.tsv"
         )
     }
     actual = somatic_variant_signatures_workflow.get_output_files("tabulate_vcf", "run")
@@ -114,7 +114,7 @@ def test_tabulate_vcf_step_part_get_output_files(somatic_variant_signatures_work
 
 def test_tabulate_vcf_step_part_get_log_file(somatic_variant_signatures_workflow):
     """Tests TabulateVariantsStepPart.get_log_file()"""
-    expected = "work/{mapper}.{var_caller}.{anno_caller}.dkfz_bias_filter.eb_filter.tabulate_vcf.{tumor_library}.{filter}.{region}/log/snakemake.tabulate_vcf.log"
+    expected = "work/{mapper}.{var_caller}.{anno_caller}.filtered.tabulate_vcf.{tumor_library}/log/snakemake.tabulate_vcf.log"
     actual = somatic_variant_signatures_workflow.get_log_file("tabulate_vcf", "run")
     assert actual == expected
 
@@ -145,8 +145,8 @@ def test_deconstruct_sigs_step_part_get_input_files(somatic_variant_signatures_w
     """Tests DeconstructSigsStepPart.get_input_files()"""
     expected = {
         "tsv": (
-            "work/{mapper}.{var_caller}.{anno_caller}.dkfz_bias_filter.eb_filter.tabulate_vcf.{tumor_library}.{filter}.{region}/out/"
-            "{mapper}.{var_caller}.{anno_caller}.dkfz_bias_filter.eb_filter.tabulate_vcf.{tumor_library}.{filter}.{region}.tsv"
+            "work/{mapper}.{var_caller}.{anno_caller}.filtered.tabulate_vcf.{tumor_library}/out/"
+            "{mapper}.{var_caller}.{anno_caller}.filtered.tabulate_vcf.{tumor_library}.tsv"
         )
     }
     actual = somatic_variant_signatures_workflow.get_input_files("deconstruct_sigs", "run")
@@ -156,8 +156,8 @@ def test_deconstruct_sigs_step_part_get_input_files(somatic_variant_signatures_w
 def test_deconstruct_sigs_step_part_get_output_files(somatic_variant_signatures_workflow):
     """Tests DeconstructSigsStepPart.get_output_files()"""
     base_name_out = (
-        "work/{mapper}.{var_caller}.{anno_caller}.dkfz_bias_filter.eb_filter.deconstruct_sigs.{tumor_library}.{filter}.{region}/out/"
-        "{mapper}.{var_caller}.{anno_caller}.dkfz_bias_filter.eb_filter.deconstruct_sigs.{tumor_library}.{filter}.{region}"
+        "work/{mapper}.{var_caller}.{anno_caller}.filtered.deconstruct_sigs.{tumor_library}/out/"
+        "{mapper}.{var_caller}.{anno_caller}.filtered.deconstruct_sigs.{tumor_library}"
     )
     expected = {
         "tsv": base_name_out + ".tsv",
@@ -170,7 +170,7 @@ def test_deconstruct_sigs_step_part_get_output_files(somatic_variant_signatures_
 def test_deconstruct_sigs_step_part_get_log_file(somatic_variant_signatures_workflow):
     """Tests DeconstructSigsStepPart.get_log_file()"""
     expected = (
-        "work/{mapper}.{var_caller}.{anno_caller}.dkfz_bias_filter.eb_filter.deconstruct_sigs.{tumor_library}.{filter}.{region}/log/"
+        "work/{mapper}.{var_caller}.{anno_caller}.filtered.deconstruct_sigs.{tumor_library}/log/"
         "snakemake.deconstruct_sigs.log"
     )
     actual = somatic_variant_signatures_workflow.get_log_file("deconstruct_sigs", "run")
@@ -201,7 +201,7 @@ def test_somatic_variant_signatures_workflow(somatic_variant_signatures_workflow
     assert actual == expected
 
     # Check result file construction
-    name_pattern = "{mapper}.{caller}.{annotator}.dkfz_bias_filter.eb_filter.deconstruct_sigs.P00{i}-T{t}-DNA1-WGS1.{filt}.{region}"
+    name_pattern = "{mapper}.{caller}.{annotator}.filtered.deconstruct_sigs.P00{i}-T{t}-DNA1-WGS1"
     tpl = "output/" + name_pattern + "/out/" + name_pattern + ".tsv"
     expected = [
         tpl.format(
@@ -210,21 +210,11 @@ def test_somatic_variant_signatures_workflow(somatic_variant_signatures_workflow
             annotator=annotator,
             i=i,
             t=t,
-            filt=filt,
-            region=region,
         )
         for i, t in ((1, 1), (2, 1), (2, 2))
         for mapper in ("bwa",)
-        for caller in ("mutect", "scalpel")
-        for annotator in ("vep", "jannovar")
-        for filt in (
-            "no_filter",
-            "dkfz_only",
-            "dkfz_and_ebfilter",
-            "dkfz_and_ebfilter_and_oxog",
-            "dkfz_and_oxog",
-        )
-        for region in ("genome_wide",)
+        for caller in ("mutect",)
+        for annotator in ("vep",)
     ]
     expected = set(expected)
     actual = set(somatic_variant_signatures_workflow.get_result_files())