Use sample id instead of case id for rnafusion (#3069) (patch)

### Changed - Use sample id instead of case id for rnafusion
Clinical-Genomics · Aug 6, 2024 · b54a0e2 · b54a0e2
1 parent ed66523
commit b54a0e2
Show file tree

Hide file tree

Showing 5 changed files with 40 additions and 45 deletions.
diff --git a/cg/constants/delivery.py b/cg/constants/delivery.py
@@ -151,6 +151,13 @@
 ]
 
 RNAFUSION_ANALYSIS_CASE_TAGS: list[set[str]] = [
+    {AnalysisTag.MULTIQC_HTML, AnalysisTag.RNA},
+    {HK_DELIVERY_REPORT_TAG},
+]
+
+RNAFUSION_ANALYSIS_SAMPLE_TAGS: list[set[str]] = [
+    {AlignmentFileTag.CRAM},
+    {AlignmentFileTag.CRAM_INDEX},
     {AnalysisTag.FUSION, AnalysisTag.ARRIBA},
     {AnalysisTag.FUSION, AnalysisTag.STARFUSION},
     {AnalysisTag.FUSION, AnalysisTag.FUSIONCATCHER},
@@ -159,17 +166,10 @@
     {AnalysisTag.FUSIONREPORT, AnalysisTag.RESEARCH},
     {AnalysisTag.FUSIONINSPECTOR_HTML, AnalysisTag.RESEARCH},
     {AnalysisTag.ARRIBA_VISUALIZATION, AnalysisTag.RESEARCH},
-    {AnalysisTag.MULTIQC_HTML, AnalysisTag.RNA},
-    {HK_DELIVERY_REPORT_TAG},
     {AnalysisTag.VCF_FUSION},
     {AnalysisTag.GENE_COUNTS},
 ]
 
-RNAFUSION_ANALYSIS_SAMPLE_TAGS: list[set[str]] = [
-    {AlignmentFileTag.CRAM},
-    {AlignmentFileTag.CRAM_INDEX},
-]
-
 NF_ANALYSIS_CASE_TAGS: list[set[str]] = [{HermesFileTag.CLINICAL_DELIVERY}]
 
 NF_ANALYSIS_SAMPLE_TAGS: list[set[str]] = [{HermesFileTag.CLINICAL_DELIVERY}]

diff --git a/cg/meta/workflow/rnafusion.py b/cg/meta/workflow/rnafusion.py
@@ -13,7 +13,7 @@
 from cg.models.deliverables.metric_deliverables import MetricsBase
 from cg.models.rnafusion.rnafusion import RnafusionParameters, RnafusionSampleSheetEntry
 from cg.resources import RNAFUSION_BUNDLE_FILENAMES_PATH
-from cg.store.models import CaseSample, Sample
+from cg.store.models import CaseSample
 
 LOG = logging.getLogger(__name__)
 
@@ -76,7 +76,7 @@ def get_sample_sheet_content_per_sample(self, case_sample: CaseSample) -> list[l
             sample=case_sample.sample
         )
         sample_sheet_entry = RnafusionSampleSheetEntry(
-            name=case_sample.case.internal_id,
+            name=case_sample.sample.internal_id,
             fastq_forward_read_paths=fastq_forward_read_paths,
             fastq_reverse_read_paths=fastq_reverse_read_paths,
             strandedness=Strandedness.REVERSE,
@@ -100,12 +100,6 @@ def get_references_path(self, genomes_base: Path | None = None) -> Path:
             return genomes_base.absolute()
         return Path(self.references).absolute()
 
-    def get_multiqc_search_patterns(self, case_id: str) -> dict:
-        """Return search patterns for MultiQC for Rnafusion."""
-        samples: list[Sample] = self.status_db.get_samples_by_case_id(case_id=case_id)
-        search_patterns: dict[str, str] = {case_id: sample.internal_id for sample in samples}
-        return search_patterns
-
     @staticmethod
     def ensure_mandatory_metrics_present(metrics: list[MetricsBase]) -> None:
         """Check that all mandatory metrics are present.

diff --git a/cg/resources/rnafusion_bundle_filenames.yaml b/cg/resources/rnafusion_bundle_filenames.yaml
@@ -1,60 +1,60 @@
 - format: tsv
-  id: CASEID
-  path: PATHTOCASE/fusioncatcher/CASEID.fusioncatcher.fusion-genes.txt
+  id: SAMPLEID
+  path: PATHTOCASE/fusioncatcher/SAMPLEID.fusioncatcher.fusion-genes.txt
   path_index: ~
   step: fusioncatcher
   tag: fusioncatcher
 - format: txt
-  id: CASEID
-  path: PATHTOCASE/fusioncatcher/CASEID.fusioncatcher.summary.txt
+  id: SAMPLEID
+  path: PATHTOCASE/fusioncatcher/SAMPLEID.fusioncatcher.summary.txt
   path_index: ~
   step: fusioncatcher
   tag: fusioncatcher-summary
 - format: tsv
-  id: CASEID
-  path: PATHTOCASE/starfusion/CASEID.starfusion.fusion_predictions.tsv
+  id: SAMPLEID
+  path: PATHTOCASE/starfusion/SAMPLEID.starfusion.fusion_predictions.tsv
   path_index: ~
   step: star-fusion
   tag: star-fusion
 - format: tsv
-  id: CASEID
-  path: PATHTOCASE/arriba/CASEID.arriba.fusions.tsv
+  id: SAMPLEID
+  path: PATHTOCASE/arriba/SAMPLEID.arriba.fusions.tsv
   path_index: ~
   step: arriba
   tag: arriba
 - format: cram
   id: SAMPLEID
-  path: PATHTOCASE/cram_starfusion/CASEID.star_for_starfusion.Aligned.sortedByCoord.out.cram
+  path: PATHTOCASE/cram_starfusion/SAMPLEID.star_for_starfusion.Aligned.sortedByCoord.out.cram
   path_index: ~
   step: star-fusion
   tag: star-fusion-cram
 - format: cram
   id: SAMPLEID
-  path: PATHTOCASE/cram_starfusion/CASEID.star_for_starfusion.Aligned.sortedByCoord.out.cram.crai
+  path: PATHTOCASE/cram_starfusion/SAMPLEID.star_for_starfusion.Aligned.sortedByCoord.out.cram.crai
   path_index: ~
   step: star-fusion
   tag: star-fusion-cram-index
 - format: html
-  id: CASEID
-  path: PATHTOCASE/fusionreport/CASEID/CASEID_fusionreport_index.html
+  id: SAMPLEID
+  path: PATHTOCASE/fusionreport/SAMPLEID/SAMPLEID_fusionreport_index.html
   path_index: ~
   step: report
   tag: fusionreport
 - format: tsv
-  id: CASEID
-  path: PATHTOCASE/fusioninspector/CASEID.FusionInspector.fusions.tsv
+  id: SAMPLEID
+  path: PATHTOCASE/fusioninspector/SAMPLEID.FusionInspector.fusions.tsv
   path_index: ~
   step: report
   tag: fusioninspector
 - format: html
-  id: CASEID
-  path: PATHTOCASE/fusioninspector/CASEID.fusion_inspector_web.html
+  id: SAMPLEID
+  path: PATHTOCASE/fusioninspector/SAMPLEID.fusion_inspector_web.html
   path_index: ~
   step: report
   tag: fusioninspector-html
 - format: pdf
-  id: CASEID
-  path: PATHTOCASE/arriba_visualisation/CASEID_combined_fusions_arriba_visualisation.pdf
+  id: SAMPLEID
+  path: PATHTOCASE/arriba_visualisation/SAMPLEID_combined_fusions_arriba_visualisation.pdf
   path_index: ~
   step: arriba
   tag: arriba-visualisation
@@ -77,14 +77,14 @@
   step: software-versions
   tag: software-versions
 - format: vcf
-  id: CASEID
-  path: PATHTOCASE/vcf/CASEID_fusion_data.vcf.gz
+  id: SAMPLEID
+  path: PATHTOCASE/vcf/SAMPLEID_fusion_data.vcf.gz
   path_index: ~
   step: vcf-collect
   tag: vcf-fusion
 - format: tab
-  id: CASEID
-  path: PATHTOCASE/star_for_starfusion/CASEID.ReadsPerGene.out.tab
+  id: SAMPLEID
+  path: PATHTOCASE/star_for_starfusion/SAMPLEID.ReadsPerGene.out.tab
   path_index: ~
   step: star-align
   tag: star-align-gene-counts

diff --git a/tests/conftest.py b/tests/conftest.py
@@ -2773,6 +2773,7 @@ def rnafusion_workflow() -> str:
 @pytest.fixture(scope="function")
 def rnafusion_sample_sheet_content(
     rnafusion_case_id: str,
+    sample_id: str,
     fastq_forward_read_path: Path,
     fastq_reverse_read_path: Path,
     strandedness: str,
@@ -2781,7 +2782,7 @@ def rnafusion_sample_sheet_content(
     headers: str = ",".join(RnafusionSampleSheetEntry.headers())
     row: str = ",".join(
         [
-            rnafusion_case_id,
+            sample_id,
             fastq_forward_read_path.as_posix(),
             fastq_reverse_read_path.as_posix(),
             strandedness,
@@ -3034,7 +3035,7 @@ def rnafusion_deliverable_data(rnafusion_dir: Path, rnafusion_case_id: str, samp
                 "path_index": "",
                 "step": "report",
                 "tag": ["multiqc-html", "rna"],
-                "id": rnafusion_case_id,
+                "id": sample_id,
                 "format": "html",
                 "mandatory": True,
             },

diff --git a/tests/fixtures/analysis/rnafusion/multiqc_data.json b/tests/fixtures/analysis/rnafusion/multiqc_data.json
@@ -2,7 +2,7 @@
     "report_data_sources": {},
     "report_general_stats_data": [
         {
-            "rnafusion_case_enough_reads": {
+            "ADM1": {
                 "PF_BASES": 14818118467.0,
                 "PF_ALIGNED_BASES": 14216931956.0,
                 "RIBOSOMAL_BASES": 93556030.0,
@@ -37,7 +37,7 @@
             }
         },
         {
-            "rnafusion_case_enough_reads": {
+            "ADM1": {
                 "LIBRARY": "Unknown Library",
                 "UNPAIRED_READS_EXAMINED": 589.0,
                 "READ_PAIRS_EXAMINED": 72391566.0,
@@ -51,7 +51,7 @@
             }
         },
         {
-            "rnafusion_case_enough_reads": {
+            "ADM1": {
                 "total_reads": 74557102.0,
                 "avg_input_read_length": 198.0,
                 "uniquely_mapped": 67865050.0,
@@ -81,7 +81,7 @@
             }
         },
         {
-            "rnafusion_case_enough_reads": {
+            "ADM1": {
                 "filtering_result_passed_filter_reads": 149114204.0,
                 "filtering_result_low_quality_reads": 855796.0,
                 "filtering_result_too_many_N_reads": 4992.0,
@@ -105,15 +105,15 @@
             }
         },
         {
-            "rnafusion_case_enough_reads_1": {
+            "ADM1_1": {
             "percent_gc": 51.0,
             "avg_sequence_length": 98.42709962090532,
             "median_sequence_length": 100,
             "total_sequences": 74557102.0,
             "percent_duplicates": 64.54554620264767,
             "percent_fails": 18.181818181818183
         },
-            "rnafusion_case_enough_reads_2": {
+            "ADM1_2": {
             "percent_gc": 51.0,
             "avg_sequence_length": 151.0,
             "median_sequence_length": 151,