Support for qc_values pseudo-columns in smaht-submitr (and multiple s…

CHANGELOG.rst

@@ -6,6 +6,14 @@ dcicutils
 Change Log
 ----------
 
+8.18.0
+======
+* dmichaels / 2025-02-11 / branch: dmichaels-20250211-submitr-custom-excel / PR-326
+  - Support for qc_values pseudo-columns in smaht-submitr (and multiple sheet with same type).
+    This is encapsulated in custom_excel.py, here because it is needed not only
+    within smaht-submitr but also within smaht-portal (ingestion_processor.py).
+
+
 8.17.0
 ======
 * dmichaels / 2025-01-14 / branch: dmichaels-structured-data-row-mapper-hook-20250114 / PR-324

dcicutils/structured_data.py

@@ -105,11 +105,13 @@ def load(file: str, portal: Optional[Union[VirtualApp, TestApp, Portal]] = None,
              ref_lookup_strategy: Optional[Callable] = None,
              ref_lookup_nocache: bool = False,
              norefs: bool = False, merge: bool = False,
+             excel_class: Optional[Excel] = None,
              progress: Optional[Callable] = None,
              debug_sleep: Optional[str] = None) -> StructuredDataSet:
         return StructuredDataSet(file=file, portal=portal, schemas=schemas, autoadd=autoadd, order=order, prune=prune,
                                  remove_empty_objects_from_lists=remove_empty_objects_from_lists,
                                  ref_lookup_strategy=ref_lookup_strategy, ref_lookup_nocache=ref_lookup_nocache,
+                                 excel_class=excel_class,
                                  norefs=norefs, merge=merge, progress=progress, debug_sleep=debug_sleep)
 
     def validate(self, force: bool = False) -> None:

dcicutils/submitr/config/custom_column_mappings.json

@@ -0,0 +1,79 @@
+{
+    "version": "1.0.0",
+    "sheet_mappings": {
+        "ExternalQualityMetric": "external_quality_metric",
+        "AnotherTypeForCustomColumnMappingsHere": "another_custom_column_mappings_here"
+    },
+    "column_mappings": {
+        "external_quality_metric": {
+            "total_raw_reads_sequenced": {
+                "qc_values#.derived_from": "{name}",
+                "qc_values#.value": "{value:integer}",
+                "qc_values#.key": "Total Raw Reads Sequenced",
+                "qc_values#.tooltip": "# of reads (150bp)"
+            },
+            "total_raw_bases_sequenced": {
+                "qc_values#.derived_from": "{name}",
+                "qc_values#.value": "{value:integer}",
+                "qc_values#.key": "Total Raw Bases Sequenced",
+                "qc_values#.tooltip": null
+            },
+            "prefiltering_number_of_consensus_molecules": {
+                "qc_values#.derived_from": "{name}",
+                "qc_values#.value": "{value:integer}",
+                "qc_values#.key": "Pre-filtering # of Consensus Molecules",
+                "qc_values#.tooltip": "Number of DNA molecules identified"
+            },
+            "prefiltering_genome_coverage": {
+                "qc_values#.derived_from": "{name}",
+                "qc_values#.value": "{value:float}",
+                "qc_values#.key": "Pre-filtering Genome Coverage",
+                "qc_values#.tooltip": null
+            },
+            "prefiltering_number_of_reads_per_consensus_molecule": {
+                "qc_values#.derived_from": "{name}",
+                "qc_values#.value": "{value:integer}",
+                "qc_values#.key": "Pre-filtering Number of Reads per Consensus Molecule",
+                "qc_values#.tooltip": null
+            },
+            "postfiltering_number_of_consensus_molecules": {
+                "qc_values#.derived_from": "{name}",
+                "qc_values#.value": "{value:integer}",
+                "qc_values#.key": "Post-filtering Number of Consensus Molecules",
+                "qc_values#.tooltip": null
+            },
+            "fraction_prefiltering_molecules_passing_filters": {
+                "qc_values#.derived_from": "{name}",
+                "qc_values#.value": "{value:float}",
+                "qc_values#.key": "Fraction of Pre-filtering Consensus Molecules that Pass Filters",
+                "qc_values#.tooltip": null
+            },
+            "number_postfiltering_consensus_base_pairs": {
+                "qc_values#.derived_from": "{name}",
+                "qc_values#.value": "{value:integer}",
+                "qc_values#.key": "Number of Final Post-filtering Consensus Interrogated Base Pairs",
+                "qc_values#.tooltip": "After applying all filters for variant calling, e.e. Mapping quality, Low complexity regions, a4s2 duplex reconstruction criteria, etc."
+            },
+            "somatic_snv_count_by_molecule": {
+                "qc_values#.derived_from": "{name}",
+                "qc_values#.value": "{value:integer}",
+                "qc_values#.key": "Somatic SNV Count by Molecule",
+                "qc_values#.tooltip": null
+            },
+            "snv_mutation_burden_by_molecule": {
+                "qc_values#.derived_from": "{name}",
+                "qc_values#.value": "{value:float}",
+                "qc_values#.key": "Somatic SNV Mutation Burden by Molecule",
+                "qc_values#.tooltip": "Detected somatic mutation / final consensus interrogated base pairs"
+            }
+        },
+        "another_custom_column_mappings_here": {
+            "your_custom_column_name": {
+                "qc_values#.derived_from": "{name}",
+                "qc_values#.value": "{value}",
+                "qc_values#.key": "Your key for this column mapping",
+                "qc_values#.tooltip": "Your tooltip text for this column mapping"
+            }
+        }
+    }
+}