chore: move config accesses in wrappers to params

snappy_pipeline/workflows/adapter_trimming/__init__.py

@@ -237,6 +237,7 @@ def args_function(wildcards):
                     "reads_left": {key: reads_left[key] for key in sorted(reads_left.keys())},
                     "reads_right": {key: reads_right[key] for key in sorted(reads_right.keys())},
                 },
+                "config": dict(self.config.get(self.name)),
             }
 
         # Validate action

snappy_pipeline/workflows/adapter_trimming/model.py

@@ -96,7 +96,7 @@ class UmiLoc(Enum):
 
 
 class Fastp(SnappyModel):
-    num_threads: int = 0
+    num_threads: int = 4
     trim_front1: int = 0
     """
     trimming how many bases in front for read1, default is 0 (int [=0])
@@ -361,9 +361,9 @@ class Bbduk(SnappyModel):
         Field(
             examples=[
                 [
-                    "/fast/work/groups/cubi/projects/biotools/static_data/app_support/"
+                    "/data/cephfs-1/work/groups/cubi/projects/biotools/static_data/app_support/"
                     "bbtools/39.01/resources/adapters.fa",
-                    "/fast/work/groups/cubi/projects/biotools/static_data/app_support/"
+                    "/data/cephfs-1/work/groups/cubi/projects/biotools/static_data/app_support/"
                     "bbtools/39.01/resources/phix174_ill.ref.fa.gz",
                 ]
             ]

snappy_pipeline/workflows/cbioportal_export/__init__.py

@@ -602,6 +602,8 @@ def get_args(self, action):
                 # Multiple libraries should not be returned by _yield_libraries
                 assert extraction_type not in donors[donor_name][sample_name]
                 donors[donor_name][sample_name][extraction_type] = lib.name
+        assert "__config" not in donors.keys(), "__config is a reserved key, not a valid donor"
+        donors["__config"] = dict(self.config)
         return donors
 
     @dictify
@@ -654,6 +656,7 @@ def get_args(self, action):
             for sample_name in args["cnaseq"]["samples"]:
                 if sample_name in args["rna_seq_mrna"]["samples"]:
                     args["3way_complete"]["samples"] += [sample_name]
+        args["__cancer_study_id"] = self.config.study.cancer_study_identifier
         return args
 
     @dictify

snappy_pipeline/workflows/cbioportal_export/model.py

@@ -177,6 +177,8 @@ class CbioportalExport(SnappyStepModel):
                     datatype="NUMBER",
                     priority="2",
                     column="TMB",
+                    # FIXME: the cbioportal/clinical_data wrapper mentions key named "path"
+                    #  which seems to be mandatory but is not listed here
                 )
             }
         ],

snappy_pipeline/workflows/common/delly.py

@@ -53,11 +53,20 @@ def __init__(self, parent):
         for sheet in self.parent.shortcut_sheets:
             self.donor_ngs_library_to_pedigree.update(sheet.donor_ngs_library_to_pedigree)
 
+    def get_args(self, action):
+        # Validate action
+        self._validate_action(action)
+        return {
+            "genome": self.w_config.static_data_config.reference.path,
+            "config": dict(self.config.get(self.name)),
+        }
+
     @dictify
     def _get_input_files_call(self, wildcards):
         ngs_mapping = self.parent.sub_workflows["ngs_mapping"]
         token = f"{wildcards.mapper}.{wildcards.library_name}"
         yield "bam", ngs_mapping(f"output/{token}/out/{token}.bam")
+        yield "bai", ngs_mapping(f"output/{token}/out/{token}.bam.bai")
 
     @dictify
     def _get_output_files_call(self):

snappy_pipeline/workflows/common/gcnv/gcnv_run.py

@@ -7,6 +7,7 @@
 import warnings
 from glob import glob
 from itertools import chain
+from typing import Any
 
 from snakemake.io import Wildcards, expand, touch
 
@@ -426,6 +427,9 @@ def _get_input_files_joint_germline_cnv_segmentation(self, wildcards):
         name_pattern = f"write_pedigree.{wildcards.library_name}"
         yield "ped", f"work/{name_pattern}/out/{wildcards.library_name}.ped"
 
+    def _get_params_joint_germline_cnv_segmentation(self, wildcards: Wildcards) -> dict[str, Any]:
+        return {"reference": self.parent.w_config.static_data_config.reference.path}
+
 
 class MergeMultikitFamiliesMixin:
     """Methods for merging families with multiple kits.
@@ -524,6 +528,15 @@ def get_params(self, action: str):
         # Return requested function
         return getattr(self, f"_get_params_{action}")
 
+    def _get_params_preprocess_intervals(self, wildcards: Wildcards) -> dict[str, Any]:
+        return {"reference": self.parent.w_config.static_data_config.reference.path}
+
+    def _get_params_coverage(self, wildcards: Wildcards) -> dict[str, Any]:
+        return {"reference": self.parent.w_config.static_data_config.reference.path}
+
+    def _get_params_joint_germline_cnv_segmentation(self, wildcards: Wildcards) -> dict[str, Any]:
+        return {"reference": self.parent.w_config.static_data_config.reference.path}
+
     @listify
     def get_result_files(self):
         """Return list of **concrete** paths to result files for the given configuration and sample sheets.

snappy_pipeline/workflows/common/manta.py

@@ -3,6 +3,8 @@
 These are used in both ``sv_calling_targeted`` and ``sv_calling_wgs``.
 """
 
+from typing import Any
+
 from snappy_pipeline.base import UnsupportedActionException
 from snappy_pipeline.utils import dictify
 from snappy_pipeline.workflows.abstract import BaseStepPart
@@ -80,3 +82,7 @@ def _get_output_files_run(self):
         yield from augment_work_dir_with_output_links(
             work_files, self.get_log_file().values()
         ).items()
+
+    def get_args(self, action: str) -> dict[str, Any]:
+        self._validate_action(action)
+        return {"reference": self.parent.w_config.static_data_config.reference.path}

snappy_pipeline/workflows/common/melt.py

@@ -1,6 +1,7 @@
 import re
 import typing
 from itertools import chain
+from typing import Any
 
 from biomedsheets.shortcuts import is_not_background
 from snakemake.io import touch
@@ -228,3 +229,9 @@ def _get_output_files_merge_vcf(self):
     @dictify
     def _get_log_file_merge_vcf(self):
         yield from self._get_log_file_with_infix("{mapper}.melt.{library_name}").items()
+
+    def get_args(self, action: str) -> dict[str, Any]:
+        self._validate_action(action)
+        return self.config.melt.model_dump(by_alias=True) | {
+            "reference": self.parent.w_config.static_data_config.reference.path
+        }

snappy_pipeline/workflows/gene_expression_quantification/Snakefile

@@ -95,6 +95,8 @@ rule gene_expression_quantification_duplication_run:
         decision=wf.get_strandedness_file("run"),
     output:
         **wf.get_output_files("duplication", "run"),
+    params:
+        **{"args": wf.get_args("duplication", "run")},
     threads: wf.get_resource("duplication", "run", "threads")
     resources:
         time=wf.get_resource("duplication", "run", "time"),
@@ -113,6 +115,8 @@ rule gene_expression_quantification_dupradar_run:
         decision=wf.get_strandedness_file("run"),
     output:
         **wf.get_output_files("dupradar", "run"),
+    params:
+        **{"args": wf.get_args("dupradar", "run")},
     threads: wf.get_resource("dupradar", "run", "threads")
     resources:
         time=wf.get_resource("dupradar", "run", "time"),
@@ -131,6 +135,8 @@ rule gene_expression_quantification_rnaseqc_run:
         decision=wf.get_strandedness_file("run"),
     output:
         **wf.get_output_files("rnaseqc", "run"),
+    params:
+        **{"args": wf.get_args("rnaseqc", "run")},
     threads: wf.get_resource("rnaseqc", "run", "threads")
     resources:
         time=wf.get_resource("rnaseqc", "run", "time"),
@@ -143,12 +149,14 @@ rule gene_expression_quantification_rnaseqc_run:
         wf.wrapper_path("rnaqc/rnaseqc")
 
 
-rule gene_expression_quantification_star_run:
+rule gene_expression_quantification_stats_run:
     input:
         unpack(wf.get_input_files("stats", "run")),
         decision=wf.get_strandedness_file("run"),
     output:
         **wf.get_output_files("stats", "run"),
+    params:
+        **{"args": wf.get_args("stats", "run")},
     threads: wf.get_resource("stats", "run", "threads")
     resources:
         time=wf.get_resource("stats", "run", "time"),

snappy_pipeline/workflows/gene_expression_quantification/__init__.py

@@ -48,6 +48,7 @@
 """
 
 import os
+from typing import Any
 
 from biomedsheets.shortcuts import GenericSampleSheet, is_not_background
 from snakemake.io import expand
@@ -188,6 +189,8 @@ def args_function(wildcards):
             )
             if reads_right:
                 result["input"]["reads_right"] = reads_right
+            result |= self.config.salmon.model_dump(by_alias=True)
+            result["strand"] = self.config.strand
             return result
 
         assert action == "run", "Unsupported actions"
@@ -259,6 +262,10 @@ def get_output_files(self, action):
             )
         )
 
+    def get_args(self, action: str) -> dict[str, Any]:
+        self._validate_action(action)
+        return {"strand": self.config.strand}
+
     @dictify
     def get_log_file(self, action):
         """Return mapping of log files."""
@@ -287,6 +294,11 @@ class FeatureCountsStepPart(GeneExpressionQuantificationStepPart):
     #: Class available actions
     actions = ("run",)
 
+    def get_args(self, action: str) -> dict[str, Any]:
+        return super().get_args(action) | {
+            "path_annotation_gtf": self.config.featurecounts.path_annotation_gtf,
+        }
+
     def get_resource_usage(self, action: str, **kwargs) -> ResourceUsage:
         """Get Resource Usage
 
@@ -373,6 +385,12 @@ class QCStepPartDupradar(GeneExpressionQuantificationStepPart):
     #: Class available actions
     actions = ("run",)
 
+    def get_args(self, action: str) -> dict[str, Any]:
+        return super().get_args(action) | {
+            "dupradar_path_annotation_gtf": self.config.dupradar.dupradar_path_annotation_gtf,
+            "num_threads": self.config.dupradar.num_threads,
+        }
+
     def get_resource_usage(self, action: str, **kwargs) -> ResourceUsage:
         """Get Resource Usage
 
@@ -397,6 +415,12 @@ class QCStepPartRnaseqc(GeneExpressionQuantificationStepPart):
     #: Class available actions
     actions = ("run",)
 
+    def get_args(self, action: str) -> dict[str, Any]:
+        return super().get_args(action) | {
+            "reference": self.parent.w_config.static_data_config.reference.path,
+            "rnaseqc_path_annotation_gtf": self.config.rnaseqc.rnaseqc_path_annotation_gtf,
+        }
+
     def get_resource_usage(self, action: str, **kwargs) -> ResourceUsage:
         """Get Resource Usage
 

snappy_pipeline/workflows/helper_gcnv_model_targeted/Snakefile

@@ -58,7 +58,7 @@ rule build_gcnv_model_preprocess_intervals:
     log:
         wf.get_log_file("gcnv", "preprocess_intervals"),
     params:
-        step_key="helper_gcnv_model_targeted",
+        **{"args": wf.get_args("gcnv", "preprocess_intervals")},
     wrapper:
         wf.wrapper_path("gcnv/preprocess_intervals")
 
@@ -68,6 +68,8 @@ rule build_gcnv_model_annotate_gc:
         unpack(wf.get_input_files("gcnv", "annotate_gc")),
     output:
         **wf.get_output_files("gcnv", "annotate_gc"),
+    params:
+        **{"args": wf.get_args("gcnv", "annotate_gc")},
     threads: wf.get_resource("gcnv", "annotate_gc", "threads")
     resources:
         time=wf.get_resource("gcnv", "annotate_gc", "time"),
@@ -85,6 +87,8 @@ rule build_gcnv_model_coverage:
         unpack(wf.get_input_files("gcnv", "coverage")),
     output:
         **wf.get_output_files("gcnv", "coverage"),
+    params:
+        **{"args": wf.get_args("gcnv", "coverage")},
     threads: wf.get_resource("gcnv", "coverage", "threads")
     resources:
         time=wf.get_resource("gcnv", "coverage", "time"),
@@ -128,7 +132,7 @@ rule build_gcnv_model_contig_ploidy:
     log:
         wf.get_log_file("gcnv", "contig_ploidy"),
     params:
-        step_key="helper_gcnv_model_targeted",
+        **{"args": wf.get_args("gcnv", "contig_ploidy")},
     wrapper:
         wf.wrapper_path("gcnv/contig_ploidy")
 

snappy_pipeline/workflows/helper_gcnv_model_targeted/__init__.py

@@ -85,6 +85,7 @@
 
 import os
 import re
+from typing import Any
 
 from biomedsheets.shortcuts import GermlineCaseSheet, is_not_background
 from snakemake.io import glob_wildcards
@@ -159,6 +160,15 @@ def _get_input_files_post_germline_calls(self, wildcards, checkpoints):
         )
         yield ext, "work/{name_pattern}/out/{name_pattern}/.done".format(name_pattern=name_pattern)
 
+    def get_args(self, action: str) -> dict[str, Any]:
+        gcnv_config = self.w_config.step_config["helper_gcnv_model_targeted"].gcnv
+        return {
+            "reference": self.parent.w_config.static_data_config.reference.path,
+            "path_par_intervals": gcnv_config.path_par_intervals,
+            "path_target_interval_list_mapping": gcnv_config.path_target_interval_list_mapping,
+            "path_uniquely_mapable_bed": gcnv_config.path_uniquely_mapable_bed,
+        }
+
 
 class HelperBuildTargetSeqGcnvModelWorkflow(BaseStep):
     """Perform gCNV model building for WES samples by library kit"""

snappy_pipeline/workflows/helper_gcnv_model_wgs/Snakefile

@@ -47,6 +47,8 @@ rule build_gcnv_model_preprocess_intervals:
         unpack(wf.get_input_files("gcnv", "preprocess_intervals")),
     output:
         **wf.get_output_files("gcnv", "preprocess_intervals"),
+    params:
+        **{"args": wf.get_args("gcnv", "preprocess_intervals")}
     threads: wf.get_resource("gcnv", "preprocess_intervals", "threads")
     resources:
         time=wf.get_resource("gcnv", "preprocess_intervals", "time"),
@@ -66,6 +68,8 @@ rule build_gcnv_model_annotate_gc:
         unpack(wf.get_input_files("gcnv", "annotate_gc")),
     output:
         **wf.get_output_files("gcnv", "annotate_gc"),
+    params:
+        **{"args": wf.get_args("gcnv", "annotate_gc")}
     threads: wf.get_resource("gcnv", "annotate_gc", "threads")
     resources:
         time=wf.get_resource("gcnv", "annotate_gc", "time"),
@@ -83,6 +87,8 @@ rule build_gcnv_model_coverage:
         unpack(wf.get_input_files("gcnv", "coverage")),
     output:
         **wf.get_output_files("gcnv", "coverage"),
+    params:
+        **{"args": wf.get_args("gcnv", "coverage")}
     threads: wf.get_resource("gcnv", "coverage", "threads")
     resources:
         time=wf.get_resource("gcnv", "coverage", "time"),
@@ -117,6 +123,8 @@ rule build_gcnv_model_contig_ploidy:
         unpack(wf.get_input_files("gcnv", "contig_ploidy")),
     output:
         **wf.get_output_files("gcnv", "contig_ploidy"),
+    params:
+        **{"args": wf.get_args("gcnv", "preprocess_intervals")}
     threads: wf.get_resource("gcnv", "contig_ploidy", "threads")
     resources:
         time=wf.get_resource("gcnv", "contig_ploidy", "time"),
@@ -126,7 +134,7 @@ rule build_gcnv_model_contig_ploidy:
     log:
         wf.get_log_file("gcnv", "contig_ploidy"),
     params:
-        step_key="helper_gcnv_model_wgs",
+        **{"args": wf.get_args("gcnv", "coverage")}
     wrapper:
         wf.wrapper_path("gcnv/contig_ploidy")
 

snappy_pipeline/workflows/helper_gcnv_model_wgs/__init__.py

@@ -84,6 +84,7 @@
 """
 
 import os
+from typing import Any
 
 import attr
 from biomedsheets.shortcuts import GermlineCaseSheet, is_not_background
@@ -184,6 +185,14 @@ def _get_input_files_post_germline_calls(self, wildcards, checkpoints):
         )
         yield ext, "work/{name_pattern}/out/{name_pattern}/.done".format(name_pattern=name_pattern)
 
+    def get_args(self, action: str) -> dict[str, Any]:
+        gcnv_config = self.w_config.step_config["helper_gcnv_model_wgs"].gcnv
+        return {
+            "reference": self.parent.w_config.static_data_config.reference.path,
+            "path_par_intervals": gcnv_config.path_par_intervals,
+            "path_uniquely_mapable_bed": gcnv_config.path_uniquely_mapable_bed,
+        }
+
     def get_resource_usage(self, action: str, **kwargs) -> ResourceUsage:
         """Get Resource Usage
 

snappy_pipeline/workflows/hla_typing/__init__.py

@@ -165,6 +165,8 @@ def args_function(wildcards):
             )
             if reads_right:
                 result["input"]["reads_right"] = reads_right
+            result["num_mapping_threads"] = self.config.optitype.num_mapping_threads
+            result["max_reads"] = self.confing.optitype.max_reads
             return result
 
         assert action == "run", "Unsupported actions"

snappy_pipeline/workflows/homologous_recombination_deficiency/Snakefile

@@ -83,6 +83,8 @@ rule homologous_recombination_deficiency_scarHRD_run:
         unpack(wf.get_input_files("scarHRD", "run")),
     output:
         **wf.get_output_files("scarHRD", "run"),
+    params:
+        **{"args": wf.get_args("scarHRD", "run")},
     threads: wf.get_resource("scarHRD", "run", "threads")
     resources:
         time=wf.get_resource("scarHRD", "run", "time"),