feat: replacing custom coverage QC scripts with "alfred qc" (#481)

snappy_pipeline/workflows/ngs_mapping/Snakefile

@@ -203,27 +203,7 @@ rule ngs_mapping_target_coverage_report_run:
     log:
         **wf.get_log_file("target_coverage_report", "run"),
     wrapper:
-        wf.wrapper_path("target_cov_report/run")
-
-
-# Collect target region reports -----------------------------------------------
-
-
-rule ngs_mapping_target_coverage_report_collect:
-    input:
-        wf.get_input_files("target_coverage_report", "collect"),
-    output:
-        **wf.get_output_files("target_coverage_report", "collect"),
-    threads: wf.get_resource("target_coverage_report", "run", "threads")
-    resources:
-        time=wf.get_resource("target_coverage_report", "run", "time"),
-        memory=wf.get_resource("target_coverage_report", "run", "memory"),
-        partition=wf.get_resource("target_coverage_report", "run", "partition"),
-        tmpdir=wf.get_resource("target_coverage_report", "run", "tmpdir"),
-    log:
-        **wf.get_log_file("target_coverage_report", "collect"),
-    wrapper:
-        wf.wrapper_path("target_cov_report/collect")
+        wf.wrapper_path("alfred/qc")
 
 
 # Compute depth of coverage files (VCF and bigWig) ----------------------------

snappy_pipeline/workflows/ngs_mapping/__init__.py

@@ -341,8 +341,7 @@
       rna: []      # Required if RNA analysis; otherwise, leave empty. Example: 'star'.
       dna_long: [] # Required if long-read mapper used; otherwise, leave empty. Example: 'minimap2'.
     path_link_in: ""   # OPTIONAL Override data set configuration search paths for FASTQ files
-    # Thresholds for targeted sequencing coverage QC.  Enabled by specifying
-    # the path_arget_regions setting above
+    # Thresholds for targeted sequencing coverage QC.
     target_coverage_report:
       # Mapping from enrichment kit to target region BED file, for either computing per--target
       # region coverage or selecting targeted exons.
@@ -354,11 +353,6 @@
       #   pattern: "xGen Exome Research Panel V1\\.0*"
       #   path: "path/to/targets.bed"
       path_target_interval_list_mapping: []
-      # Maximal/minimal/warning coverage
-      max_coverage: 200
-      min_cov_warning: 20  # >= 20x for WARNING
-      min_cov_ok: 50  # >= 50x for OK
-      detailed_reporting: false  # per-exon details (cannot go into multiqc)
     # Depth of coverage collection, mainly useful for genomes.
     bam_collect_doc:
       enabled: false
@@ -1128,7 +1122,7 @@ def get_resource_usage(self, action):
         )
 
 
-class TargetCoverageReportStepPart(ReportGetResultFilesMixin, BaseStepPart):
+class TargetCovReportStepPart(ReportGetResultFilesMixin, BaseStepPart):
     """Build target coverage report"""
 
     #: Step name
@@ -1138,7 +1132,7 @@ class TargetCoverageReportStepPart(ReportGetResultFilesMixin, BaseStepPart):
     tool_categories = ("dna", "dna_long")
 
     #: Class available actions
-    actions = ("run", "collect")
+    actions = ("run",)
 
     def __init__(self, parent):
         super().__init__(parent)
@@ -1154,25 +1148,6 @@ def _get_input_files_run(self, wildcards):
         yield "bam", f"work/{mapper_lib}/out/{mapper_lib}.bam"
         yield "bai", f"work/{mapper_lib}/out/{mapper_lib}.bam.bai"
 
-    @listify
-    def _get_input_files_collect(self, wildcards):
-        _ = wildcards
-        for sheet in self.parent.shortcut_sheets:
-            for ngs_library in sheet.all_ngs_libraries:
-                extraction_type = ngs_library.test_sample.extra_infos.get("extractionType", "DNA")
-                if ngs_library.extra_infos["seqPlatform"] in ("ONP", "PacBio"):
-                    suffix = "_long"
-                else:
-                    suffix = ""
-                for mapper in self.config["tools"][extraction_type.lower() + suffix]:
-                    if (
-                        self.parent.default_kit_configured
-                        or ngs_library.name in self.parent.ngs_library_to_kit
-                    ):
-                        yield self._get_output_files_run_work()["txt"].format(
-                            mapper=mapper, library_name=ngs_library.name
-                        )
-
     @dictify
     def get_output_files(self, action):
         """Return output files"""
@@ -1193,13 +1168,8 @@ def get_output_files(self, action):
 
     @dictify
     def _get_output_files_run_work(self):
-        yield "txt", "work/{mapper}.{library_name}/report/cov_qc/{mapper}.{library_name}.txt"
-        yield "txt_md5", "work/{mapper}.{library_name}/report/cov_qc/{mapper}.{library_name}.txt.md5"
-
-    @dictify
-    def _get_output_files_collect_work(self):
-        yield "txt", "work/target_cov_report/out/target_cov_report.txt"
-        yield "txt_md5", "work/target_cov_report/out/target_cov_report.txt.md5"
+        yield "json", "work/{mapper}.{library_name}/report/alfred_qc/{mapper}.{library_name}.alfred.json.gz"
+        yield "json_md5", "work/{mapper}.{library_name}/report/alfred_qc/{mapper}.{library_name}.alfred.json.gz.md5"
 
     @dictify
     def get_log_file(self, action):
@@ -1235,10 +1205,6 @@ def _get_params_run(self, wildcards):
 
         return {
             "path_targets_bed": path_targets_bed,
-            "max_coverage": self.config["target_coverage_report"]["max_coverage"],
-            "min_cov_warning": self.config["target_coverage_report"]["min_cov_warning"],
-            "min_cov_ok": self.config["target_coverage_report"]["min_cov_ok"],
-            "detailed_reporting": self.config["target_coverage_report"]["detailed_reporting"],
         }
 
     def get_resource_usage(self, action):
@@ -1462,7 +1428,7 @@ def __init__(self, workflow, config, config_lookup_paths, config_paths, workdir)
                 Minimap2StepPart,
                 StarStepPart,
                 StrandednessStepPart,
-                TargetCoverageReportStepPart,
+                TargetCovReportStepPart,
                 BamCollectDocStepPart,
                 NgsChewStepPart,
             )

snappy_pipeline/workflows/varfish_export/__init__.py

@@ -411,7 +411,7 @@ def _get_input_files_bam_qc(self, wildcards):
         # Get names of primary libraries of the selected pedigree.  The pedigree is selected
         # by the primary DNA NGS library of the index.
         pedigree = self.index_ngs_library_to_pedigree[wildcards.index_ngs_library]
-        result = {"bamstats": [], "flagstats": [], "idxstats": [], "cov_qc": []}
+        result = {"bamstats": [], "flagstats": [], "idxstats": [], "alfred_qc": []}
         for donor in pedigree.donors:
             if not donor.dna_ngs_library:
                 continue
@@ -424,10 +424,10 @@ def _get_input_files_bam_qc(self, wildcards):
             if donor.dna_ngs_library.name not in self.parent.ngs_library_to_kit:
                 continue
             path = (
-                f"output/{wildcards.mapper}.{donor.dna_ngs_library.name}/report/cov_qc/"
-                f"{wildcards.mapper}.{donor.dna_ngs_library.name}.txt"
+                f"output/{wildcards.mapper}.{donor.dna_ngs_library.name}/report/alfred_qc/"
+                f"{wildcards.mapper}.{donor.dna_ngs_library.name}.alfred.json.gz"
             )
-            result["cov_qc"].append(ngs_mapping(path))
+            result["alfred_qc"].append(ngs_mapping(path))
         return result
 
     @dictify

snappy_pipeline/workflows/variant_export_external/__init__.py

@@ -94,7 +94,7 @@
     ResourceUsage,
     WritePedigreeSampleNameStepPart,
 )
-from snappy_pipeline.workflows.ngs_mapping import TargetCoverageReportStepPart
+from snappy_pipeline.workflows.ngs_mapping import TargetCovReportStepPart
 
 #: Default configuration for the somatic_variant_calling step
 DEFAULT_CONFIG = r"""
@@ -119,14 +119,10 @@
       # region coverage or selecting targeted exons. Only used if 'bam_available_flag' is True.
       # It will not generated detailed reporting.
       path_targets_bed: OPTIONAL # OPTIONAL
-      # Maximal/minimal/warning coverage
-      max_coverage: 200
-      min_cov_warning: 20  # >= 20x for WARNING
-      min_cov_ok: 50  # >= 50x for OK
 """
 
 
-class BamReportsExternalStepPart(TargetCoverageReportStepPart):
+class BamReportsExternalStepPart(TargetCovReportStepPart):
     """Build target coverage report and QC report for external BAM files"""
 
     #: Step name
@@ -166,7 +162,7 @@ def get_output_files(self, action):
     def _get_input_files_collect(self, wildcards):
         _ = wildcards
         mapper_lib = "{mapper}.{library_name}"
-        yield f"work/{mapper_lib}/report/cov_qc/{mapper_lib}.txt"
+        yield f"work/{mapper_lib}/report/alfred_qc/{mapper_lib}.alfred.json.gz"
 
     @dictify
     def _get_output_files_bam_qc_work(self):
@@ -214,10 +210,6 @@ def _get_params_run(self, wildcards):
             "bam": sorted(list(self._collect_bam_files(wildcards))),
             "bam_count": len(sorted(list(self._collect_bam_files(wildcards)))),
             "path_targets_bed": self.config["target_coverage_report"]["path_targets_bed"],
-            "max_coverage": self.config["target_coverage_report"]["max_coverage"],
-            "min_cov_warning": self.config["target_coverage_report"]["min_cov_warning"],
-            "min_cov_ok": self.config["target_coverage_report"]["min_cov_ok"],
-            "detailed_reporting": False,
         }
 
     def _get_params_bam_qc(self, wildcards):
@@ -335,7 +327,7 @@ def _get_input_files_bam_qc(self, wildcards):
                 result[key].append(tpl % key)
             if donor.dna_ngs_library.name not in self.parent.ngs_library_list:
                 continue
-            path = f"work/{mapper}.{library_name}/report/cov_qc/{mapper}.{library_name}.txt"
+            path = f"work/{mapper}.{library_name}/report/alfred_qc/{mapper}.{library_name}.alfred.json.gz"
             result["cov_qc"].append(path)
 
         return result