docs: Check & update of configuration defaults (first part)

snappy_pipeline/apps/tpls/project_config.yaml

@@ -4,18 +4,46 @@
 
 # Step Configuration ==============================================================================
 #
-# Configuration for paths with static data.  This has been preconfigured for the paths on the BIH
-# cluster.
+# Configuration for paths with static data (GRCh37/hs37d5 genome release, no CHR prefix in contig names).
+# This has been preconfigured for the paths on the BIH cluster.
 #
 static_data_config:
   cosmic:
-    path: /fast/projects/cubit/current/static_data/db/COSMIC/v72/GRCh37/CosmicAll.vcf.gz
+    path: /data/cephfs-1/work/projects/cubit/current/static_data/db/COSMIC/v72/GRCh37/CosmicAll.vcf.gz
   dbnsfp:
-    path: /fast/projects/cubit/current/static_data/db/dbNSFP/2.9/dbNSFP2.9.txt.gz
+    path: /data/cephfs-1/work/projects/cubit/current/static_data/db/dbNSFP/2.9/dbNSFP2.9.txt.gz
   dbsnp:
-    path: /fast/projects/cubit/current/static_data/db/dbSNP/b147/GRCh37/All_20160408.vcf.gz
+    path: /data/cephfs-1/work/projects/cubit/current/static_data/db/dbSNP/b147/GRCh37/All_20160408.vcf.gz
   reference:
-    path: /fast/projects/cubit/current/static_data/reference/GRCh37/hs37d5/hs37d5.fa
+    path: /data/cephfs-1/work/projects/cubit/current/static_data/reference/GRCh37/hs37d5/hs37d5.fa
+  features:
+    path: /data/cephfs-1/work/projects/cubit/current/static_data/annotation/GENCODE/19/GRCh37/gencode.v19.annotation.gtf
+
+# Step Configuration ==============================================================================
+#
+# Configuration for paths with static data (GRCh38.d1.vd1 genome release, includes decoys & viral sequences).  
+# This has been preconfigured for the paths on the BIH cluster (CUBI group members only).
+#
+# Notes: 
+# - GRCh38.d1.vd1 is the genome release used by the GDC consortium
+#   (https://docs.gdc.cancer.gov/Data/Bioinformatics_Pipelines/DNA_Seq_Variant_Calling_Pipeline/#alignment-workflow)
+# - GENCODE release 36 is the feature annotation used by the GDC consortium for its RNA pipeline
+#   (https://docs.gdc.cancer.gov/Data/Bioinformatics_Pipelines/Expression_mRNA_Pipeline/#rna-seq-alignment-workflow)
+# - The GENCODE release 36 corresponds to ENSEMBL release 102
+#   (https://www.gencodegenes.org/human/releases.html)
+# - Some files have not yet been moved to Tier 1.   
+#
+# static_data_config:
+#   cosmic:
+#     path: /data/cephfs-1/work/projects/cubit/current/static_data/db/COSMIC/v90/GRCh38/CosmicAll.vcf.gz
+#   dbnsfp:
+#     path: /data/cephfs-1/work/projects/cubit/current/static_data/db/dbNSFP/3.5/GRCh38/dbNSFP.txt.gz
+#   dbsnp:
+#     path: /data/cephfs-1/work/projects/cubit/current/static_data/db/dbSNP/b147/GRCh38/common_all_20160407.vcf.gz
+#   reference:
+#     path: /fast/work/groups/cubi/projects/biotools/static_data/reference/GRCh38.d1.vd1/GRCh38.d1.vd1.fa
+#   features:
+#     path: /fast/work/groups/cubi/projects/biotools/static_data_by_ref/GRCh38/annotation/GENCODE/36/gencode.v36.primary_assembly.annotation.gtf
 
 # Step Configuration ==============================================================================
 #

snappy_pipeline/workflows/ngs_mapping/model.py

@@ -43,6 +43,9 @@ class TargetCoverageReportEntry(SnappyModel):
       - name: IDT_xGen_V1_0
         pattern: "xGen Exome Research Panel V1\\.0*"
         path: "path/to/targets.bed"
+
+    Bed file for many Agilent exome panels can be found in
+    /fast/work/groups/cubi/projects/biotools/static_data/exome_panel/Agilent
     """
 
     name: Annotated[str, Field(examples=["IDT_xGen_V1_0"])]
@@ -72,7 +75,14 @@ class BwaMode(Enum):
 
 
 class BwaMapper(SnappyModel):
-    path_index: str
+    path_index: str = Field(
+        examples=[
+            "/data/cephfs-1/work/projects/cubit/current/static_data/precomputed/BWA/0.7.17/GRCh37/hs37d5/hs37d5.fa",
+            "/fast/work/groups/cubi/projects/biotools/static_data_by_ref/GRCh38.d1.vd1/precomputed/BWA/0.7.17/GRCh38.d1.vd1.fa",
+            "/data/cephfs-1/work/groups/cubi/projects/biotools/bwa-mem2/GRCh37/hs37d5/hs37d5.fa",
+            "/fast/work/groups/cubi/projects/biotools/static_data_by_ref/GRCh38.d1.vd1/precomputed/BWA_MEM2/2.2.1/GRCh38.d1.vd1.fa",
+        ]
+    )
     """Required if listed in ngs_mapping.tools.dna; otherwise, can be removed."""
     num_threads_align: int = 16
     num_threads_trimming: int = 8
@@ -145,8 +155,13 @@ class Somatic(SnappyModel):
 
 
 class Bqsr(SnappyModel):
-    common_variants: str
-    """Common germline variants (see /fast/work/groups/cubi/projects/biotools/static_data/app_support/GATK)"""
+    common_variants: str = Field(
+        examples=[
+            "/fast/work/groups/cubi/projects/biotools/static_data/app_support/GATK/b37/small_exac_common_3.vcf.gz",
+            "/fast/work/groups/cubi/projects/biotools/static_data/app_support/GATK/hg38/small_exac_common_3.hg38.vcf.gz",
+        ]
+    )
+    """Common germline variants (see https://console.cloud.google.com/storage/browser/gatk-best-practices)"""
 
 
 class AgentLibPrepType(Enum):
@@ -158,7 +173,11 @@ class AgentLibPrepType(Enum):
 
 
 class AgentPrepare(SnappyModel):
-    path: str
+    path: str = Field(
+        examples=[
+            "/fast/work/groups/cubi/projects/biotools/AGeNT_3.0.6/agent/lib/trimmer-3.0.5.jar"
+        ]
+    )
 
     lib_prep_type: AgentLibPrepType = None
     """One of "halo" (HaloPlex), "hs" (HaloPlexHS), "xt" (SureSelect XT, XT2, XT HS), "v2" (SureSelect XT HS2) & "qxt" (SureSelect QXT)"""
@@ -174,8 +193,17 @@ class AgentMarkDuplicatesConsensusMode(Enum):
 
 
 class AgentMarkDuplicates(SnappyModel):
-    path: str
+    path: str = Field(
+        examples=["/fast/work/groups/cubi/projects/biotools/AGeNT_3.0.6/agent/lib/creak-1.0.5.jar"]
+    )
     path_baits: str
+    """
+    Different exome panels cannot be accomodated here, because the selection method used for coverage is not used.
+    The absolute path of the exome panel must be input.
+
+    Bed file for many Agilent exome panels can be found in
+    /fast/work/groups/cubi/projects/biotools/static_data/exome_panel/Agilent
+    """
     consensus_mode: AgentMarkDuplicatesConsensusMode = None
     """One of "SINGLE", "HYBRID", "DUPLEX" """
 
@@ -194,7 +222,12 @@ class Agent(SnappyModel):
 
 
 class Star(SnappyModel):
-    path_index: str
+    path_index: str = Field(
+        examples=[
+            "/fast/work/groups/cubi/projects/biotools/static_data_by_ref/hs37d5/annotation/GENCODE/19/precomputed/STAR/2.7.10a/100",
+            "/fast/work/groups/cubi/projects/biotools/static_data_by_ref/GRCh38/annotations/GENCODE/36/precomputed/STAR/STAR_2.7.10a_100",
+        ]
+    )
     """Required if listed in ngs_mapping.tools.rna; otherwise, can be removed."""
     num_threads_align: int = 16
     num_threads_trimming: int = 8
@@ -245,7 +278,12 @@ class Strand(enum.IntEnum):
 
 
 class Strandedness(SnappyModel):
-    path_exon_bed: str
+    path_exon_bed: str = Field(
+        examples=[
+            "/fast/work/groups/cubi/projects/biotools/static_data_by_ref/hs37d5/annotation/GENCODE/19/gencode.v19.chr_scaff.annotation.cds.collapse_annotation.bed",
+            "/fast/work/groups/cubi/projects/biotools/static_data_by_ref/GRCh38/annotations/GENCODE/36/gencode.v36.primary_assembly.annotation.cds.collapse_annotation.bed",
+        ]
+    )
     """Location of usually highly expressed genes. Known protein coding genes is a good choice"""
 
     strand: Strand = Strand.UNKNOWN

snappy_pipeline/workflows/somatic_variant_calling/model.py

@@ -98,13 +98,38 @@ class Mutect2(Parallel):
     # Sadly a type of
     # `FilePath | None = None`
     # still applies `FilePath` validation on `None`, which errors
-    panel_of_normals: str | None = ""
+    panel_of_normals: Annotated[
+        str | None,
+        Field(
+            examples=[
+                "/fast/work/groups/cubi/projects/biotools/static_data/app_support/GATK/b37/Mutect2-exome-panel.vcf.gz",
+                "/fast/work/groups/cubi/projects/biotools/static_data/app_support/GATK/b37/Mutect2-WGS-panel-b37.vcf.gz",
+                "/fast/work/groups/cubi/projects/biotools/static_data/app_support/GATK/hg38/1000g_pon.hg38.vcf.gz",
+            ]
+        ),
+    ] = None
     """Set path to panel of normals vcf if required"""
 
-    germline_resource: str | None = ""
+    germline_resource: Annotated[
+        str | None,
+        Field(
+            examples=[
+                "/fast/work/groups/cubi/projects/biotools/static_data/app_support/GATK/b37/af-only-gnomad.raw.sites.vcf.gz",
+                "/fast/work/groups/cubi/projects/biotools/static_data/app_support/GATK/hg38/af-only-gnomad.hg38.vcf.gz",
+            ]
+        ),
+    ] = None
     """Germline variants resource (same as panel of normals)"""
 
-    common_variants: str | None = ""
+    common_variants: Annotated[
+        str | None,
+        Field(
+            examples=[
+                "/fast/work/groups/cubi/projects/biotools/static_data/app_support/GATK/b37/small_exac_common_3.vcf.gz",
+                "/fast/work/groups/cubi/projects/biotools/static_data/app_support/GATK/hg38/small_exac_common_3.hg38.vcf.gz",
+            ]
+        ),
+    ] = None
     """Common germline variants for contamination estimation"""
 
     extra_arguments: Annotated[
@@ -220,7 +245,12 @@ class SomaticVariantCalling(SnappyStepModel, validators.ToolsMixin):
 
     ignore_chroms: Annotated[
         list[str],
-        Field(examples=["NC_007605", "hs37d5", "chrEBV", "*_decoy", "HLA-*", "GL000220.*"]),
+        Field(
+            examples=[
+                ["NC_007605", "hs37d5", "chrEBV", "*_decoy", "HLA-*", "GL000220.*"],
+                ["*_decoy", "EBV", "HPV*", "HBV", "HCV-*", "HIV-*", "HTLV-1", "CMV", "KSHV", "MCV", "SV40", "chrUn_GL000220v1"]
+            ]
+        ),
     ] = ["NC_007605", "hs37d5", "chrEBV", "*_decoy", "HLA-*", "GL000220.*"]
     """Patterns of contig names to ignore"""