Remove constant DRAGEN and replace usages for BCLCONVERT (#2843)(patch)

Fixes #2030. Remove all ambiguity between the constants `BclConverter.DRAGEN` and `BclConverter.BCLCONVERT`, removing de former and replacing all the usages with the latter. ### Changed - Removes `BclConverter.DRAGEN` and changes it with `BclConverter.BCLCONVERT`
Clinical-Genomics · Jan 16, 2024 · 274ed44 · 274ed44
1 parent b0d7c99
commit 274ed44
Show file tree

Hide file tree

Showing 13 changed files with 39 additions and 38 deletions.
diff --git a/cg/apps/demultiplex/demultiplex_api.py b/cg/apps/demultiplex/demultiplex_api.py
@@ -238,7 +238,7 @@ def start_demultiplexing(self, flow_cell: FlowCellDirectoryData):
                 number_tasks=18,
                 quality_of_service=self.slurm_quality_of_service,
             )
-        if flow_cell.bcl_converter == BclConverter.DRAGEN:
+        if flow_cell.bcl_converter == BclConverter.BCLCONVERT:
             sbatch_parameters: SbatchDragen = SbatchDragen(
                 account=self.slurm_account,
                 commands=commands,

diff --git a/cg/apps/demultiplex/sbatch.py b/cg/apps/demultiplex/sbatch.py
@@ -1,7 +1,9 @@
 # This one needs run_dir, out_dir, basemask and sample_sheet
 
+from cg.constants.demultiplexing import BclConverter
+
 DEMULTIPLEX_COMMAND = {
-    "bcl2fastq": """
+    BclConverter.BCL2FASTQ: """
 log "singularity exec --bind \
 /home/proj/{environment}/demultiplexed-runs,\
 /home/proj/{environment}/flow_cells,\
@@ -25,7 +27,7 @@
 touch {demux_completed_file}
 log "bcl2fastq finished!"
 """,
-    "dragen": """
+    BclConverter.BCLCONVERT: """
 log "dragen --bcl-conversion-only true \
 --bcl-input-directory {run_dir} \
 --output-directory {demux_dir} \

diff --git a/cg/apps/sequencing_metrics_parser/api.py b/cg/apps/sequencing_metrics_parser/api.py
@@ -18,7 +18,7 @@ def create_sample_lane_sequencing_metrics_for_flow_cell(
 ) -> list[SampleLaneSequencingMetrics]:
     """Parse the sequencing metrics data for the correct demultiplexing software
     into the sequencing statistics model."""
-    if bcl_converter == BclConverter.BCLCONVERT or bcl_converter == BclConverter.DRAGEN:
+    if bcl_converter == BclConverter.BCLCONVERT:
         return create_sample_lane_sequencing_metrics_from_bcl_convert_metrics_for_flow_cell(
             flow_cell_directory
         )

diff --git a/cg/constants/bcl_convert_metrics.py b/cg/constants/bcl_convert_metrics.py
@@ -33,13 +33,6 @@ class BclConvertQualityMetricsColumnNames(StrEnum):
             if column != "index2"
         ]
     ),
-    BclConverter.DRAGEN: ",".join(
-        [
-            column
-            for column in SampleSheetBCLConvertSections.Data.column_names()
-            if column != "index2"
-        ]
-    ),
 }
 
 

diff --git a/cg/constants/demultiplexing.py b/cg/constants/demultiplexing.py
@@ -11,7 +11,6 @@
 class BclConverter(StrEnum):
     """Define the BCL converter."""
 
-    DRAGEN: str = "dragen"
     BCL2FASTQ: str = "bcl2fastq"
     BCLCONVERT: str = "bcl_convert"
 
@@ -207,20 +206,20 @@ class IndexOverrideCycles(StrEnum):
 OPTION_BCL_CONVERTER = click.option(
     "-b",
     "--bcl-converter",
-    type=click.Choice(["bcl2fastq", "dragen"]),
+    type=click.Choice([BclConverter.BCL2FASTQ, BclConverter.BCLCONVERT]),
     default=None,
     help="Specify bcl conversion software. Choose between bcl2fastq and dragen. "
     "If not specified, the software will be determined automatically using the sequencer type.",
 )
 
 
 DEMUX_STATS_PATH: dict[str, dict[str, Path | None]] = {
-    "bcl2fastq": {
+    BclConverter.BCL2FASTQ: {
         "demultiplexing_stats": Path("Stats", "DemultiplexingStats.xml"),
         "conversion_stats": Path("Stats", "ConversionStats.xml"),
         "runinfo": None,
     },
-    "dragen": {
+    BclConverter.BCLCONVERT: {
         "demultiplexing_stats": Path("Reports", "Demultiplex_Stats.csv"),
         "conversion_stats": Path("Reports", "Demultiplex_Stats.csv"),
         "adapter_metrics_stats": Path("Reports", "Adapter_Metrics.csv"),

diff --git a/cg/models/flow_cell/flow_cell.py b/cg/models/flow_cell/flow_cell.py
@@ -41,7 +41,7 @@
     Sequencers.NOVASEQX: RunParametersNovaSeqX,
 }
 SAMPLE_MODEL_TO_BCL_CONVERTER: dict[Type[FlowCellSample], str] = {
-    FlowCellSampleBCLConvert: BclConverter.DRAGEN,
+    FlowCellSampleBCLConvert: BclConverter.BCLCONVERT,
     FlowCellSampleBcl2Fastq: BclConverter.BCL2FASTQ,
 }
 
@@ -60,7 +60,7 @@ def __init__(self, flow_cell_path: Path, bcl_converter: str | None = None):
         self.id: str = EMPTY_STRING
         self.position: Literal["A", "B"] = "A"
         self.parse_flow_cell_dir_name()
-        self.bcl_converter: str = bcl_converter or BclConverter.DRAGEN
+        self.bcl_converter: str = bcl_converter or BclConverter.BCLCONVERT
         self._sample_sheet_path_hk: Path | None = None
 
     def parse_flow_cell_dir_name(self):

diff --git a/tests/apps/demultiplex/test_sample_sheet_creator_factory.py b/tests/apps/demultiplex/test_sample_sheet_creator_factory.py
@@ -41,8 +41,9 @@ def test_sample_sheet_creator_factory_bcl_convert(
     novaseq_x_lims_samples: list[FlowCellSampleBCLConvert],
 ):
     """Test that a sample sheet creator defined with BCL convert data is BCL Convert."""
+
     # GIVEN a NovaSeqX flow cell and a list of NovaSeqX BCL Convert samples
-    assert novaseq_x_flow_cell.bcl_converter == BclConverter.DRAGEN
+    assert novaseq_x_flow_cell.bcl_converter == BclConverter.BCLCONVERT
 
     # WHEN defining the sample sheet creator
     sample_sheet_creator: SampleSheetCreator = get_sample_sheet_creator(

diff --git a/tests/cli/demultiplex/test_create_sample_sheet.py b/tests/cli/demultiplex/test_create_sample_sheet.py
@@ -89,7 +89,7 @@ def test_create_bcl2fastq_sample_sheet(
     # WHEN creating a sample sheet
     result = cli_runner.invoke(
         create_sheet,
-        [str(tmp_flow_cells_directory_no_sample_sheet), "--bcl-converter", "bcl2fastq"],
+        [str(tmp_flow_cells_directory_no_sample_sheet), "--bcl-converter", BclConverter.BCL2FASTQ],
         obj=sample_sheet_context,
     )
 
@@ -144,7 +144,7 @@ def test_create_dragen_sample_sheet(
     flow_cell_directory: Path = request.getfixturevalue(scenario.flow_cell_directory)
     # GIVEN a flow cell directory with some run parameters
     flow_cell: FlowCellDirectoryData = FlowCellDirectoryData(
-        flow_cell_directory, bcl_converter=BclConverter.DRAGEN
+        flow_cell_directory, bcl_converter=BclConverter.BCLCONVERT
     )
     assert flow_cell.run_parameters_path.exists()
 
@@ -166,7 +166,7 @@ def test_create_dragen_sample_sheet(
     # WHEN creating a sample sheet
     result = cli_runner.invoke(
         create_sheet,
-        [str(flow_cell_directory), "-b", BclConverter.DRAGEN],
+        [str(flow_cell_directory), "-b", BclConverter.BCLCONVERT],
         obj=sample_sheet_context,
     )
 
@@ -213,7 +213,11 @@ def test_incorrect_bcl2fastq_headers_samplesheet(
     # WHEN creating a sample sheet
     cli_runner.invoke(
         create_sheet,
-        [str(tmp_flow_cells_directory_malformed_sample_sheet), "--bcl-converter", "bcl2fastq"],
+        [
+            str(tmp_flow_cells_directory_malformed_sample_sheet),
+            "--bcl-converter",
+            BclConverter.BCL2FASTQ,
+        ],
         obj=sample_sheet_context,
     )
 

diff --git a/tests/cli/demultiplex/test_demultiplex_flowcell.py b/tests/cli/demultiplex/test_demultiplex_flowcell.py
@@ -46,7 +46,7 @@ def test_demultiplex_bcl2fastq_flow_cell_dry_run(
             str(tmp_flow_cells_directory_ready_for_demultiplexing_bcl2fastq),
             "--dry-run",
             "-b",
-            "bcl2fastq",
+            BclConverter.BCL2FASTQ,
         ],
         obj=demultiplexing_context_for_demux,
     )
@@ -90,7 +90,11 @@ def test_demultiplex_bcl2fastq_flow_cell(
     # WHEN starting demultiplexing from the CLI with dry run flag
     result: testing.Result = cli_runner.invoke(
         demultiplex_flow_cell,
-        [str(tmp_flow_cells_directory_ready_for_demultiplexing_bcl2fastq), "-b", "bcl2fastq"],
+        [
+            str(tmp_flow_cells_directory_ready_for_demultiplexing_bcl2fastq),
+            "-b",
+            BclConverter.BCL2FASTQ,
+        ],
         obj=demultiplexing_context_for_demux,
     )
 
@@ -110,7 +114,6 @@ def test_demultiplex_dragen_flowcell(
     cli_runner: testing.CliRunner,
     tmp_flow_cell_directory_bclconvert: Path,
     demultiplexing_context_for_demux: CGConfig,
-    tmp_demultiplexed_runs_directory: Path,
     caplog,
     mocker,
 ):
@@ -119,7 +122,7 @@ def test_demultiplex_dragen_flowcell(
     # GIVEN that all files are present for Dragen demultiplexing
 
     flow_cell: FlowCellDirectoryData = FlowCellDirectoryData(
-        flow_cell_path=tmp_flow_cell_directory_bclconvert, bcl_converter="dragen"
+        flow_cell_path=tmp_flow_cell_directory_bclconvert, bcl_converter=BclConverter.BCLCONVERT
     )
     add_sample_sheet_path_to_housekeeper(
         flow_cell_directory=tmp_flow_cell_directory_bclconvert,
@@ -142,7 +145,7 @@ def test_demultiplex_dragen_flowcell(
     # WHEN starting demultiplexing from the CLI
     result: testing.Result = cli_runner.invoke(
         demultiplex_flow_cell,
-        [str(tmp_flow_cell_directory_bclconvert), "-b", "dragen"],
+        [str(tmp_flow_cell_directory_bclconvert), "-b", BclConverter.BCLCONVERT],
         obj=demultiplexing_context_for_demux,
     )
 

diff --git a/tests/fixture_plugins/demultiplex_fixtures/flow_cell_fixtures.py b/tests/fixture_plugins/demultiplex_fixtures/flow_cell_fixtures.py
@@ -81,7 +81,7 @@ def novaseq_flow_cell_demultiplexed_with_bcl2fastq(
 def bcl_convert_flow_cell(bcl_convert_flow_cell_dir: Path) -> FlowCellDirectoryData:
     """Create a bcl_convert flow cell object with flow cell that is demultiplexed."""
     return FlowCellDirectoryData(
-        flow_cell_path=bcl_convert_flow_cell_dir, bcl_converter=BclConverter.DRAGEN
+        flow_cell_path=bcl_convert_flow_cell_dir, bcl_converter=BclConverter.BCLCONVERT
     )
 
 
@@ -95,7 +95,7 @@ def novaseq_6000_flow_cell(bcl_convert_flow_cell: FlowCellDirectoryData) -> Flow
 def novaseq_x_flow_cell(novaseq_x_flow_cell_directory: Path) -> FlowCellDirectoryData:
     """Create a NovaSeqX flow cell object with flow cell that is demultiplexed."""
     return FlowCellDirectoryData(
-        flow_cell_path=novaseq_x_flow_cell_directory, bcl_converter=BclConverter.DRAGEN
+        flow_cell_path=novaseq_x_flow_cell_directory, bcl_converter=BclConverter.BCLCONVERT
     )
 
 
@@ -142,7 +142,7 @@ def tmp_bcl_convert_flow_cell(
     """Create a flow cell object with flow cell that is demultiplexed."""
     return FlowCellDirectoryData(
         flow_cell_path=tmp_flow_cell_directory_bclconvert,
-        bcl_converter=BclConverter.DRAGEN,
+        bcl_converter=BclConverter.BCLCONVERT,
     )
 
 

diff --git a/tests/meta/demultiplex/conftest.py b/tests/meta/demultiplex/conftest.py
@@ -7,11 +7,9 @@
 import pytest
 
 from cg.apps.housekeeper.hk import HousekeeperAPI
-from cg.constants.demultiplexing import DemultiplexingDirsAndFiles
+from cg.constants.demultiplexing import BclConverter, DemultiplexingDirsAndFiles
 from cg.meta.demultiplex.demux_post_processing import DemuxPostProcessingAPI
-from cg.meta.demultiplex.housekeeper_storage_functions import (
-    add_sample_sheet_path_to_housekeeper,
-)
+from cg.meta.demultiplex.housekeeper_storage_functions import add_sample_sheet_path_to_housekeeper
 from cg.models.cg_config import CGConfig
 from cg.models.flow_cell.flow_cell import FlowCellDirectoryData
 from cg.store.api import Store
@@ -242,7 +240,7 @@ def flow_cell_name_demultiplexed_with_bcl_convert_on_sequencer() -> str:
 @pytest.fixture(scope="session")
 def bcl2fastq_folder_structure(tmp_path_factory, cg_dir: Path) -> Path:
     """Return a folder structure that resembles a bcl2fastq run folder."""
-    base_dir: Path = tmp_path_factory.mktemp("".join((str(cg_dir), "bcl2fastq")))
+    base_dir: Path = tmp_path_factory.mktemp("".join((str(cg_dir), BclConverter.BCL2FASTQ)))
     folders: list[str] = ["l1t21", "l1t11", "l2t11", "l2t21"]
 
     for folder in folders:

diff --git a/tests/meta/demultiplex/test_demux_post_processing.py b/tests/meta/demultiplex/test_demux_post_processing.py
@@ -34,7 +34,7 @@ class DemultiplexingScenario(BaseModel):
     flow_cell_directory: str
     flow_cell_name: str
     samples_ids: str
-    bcl_converter: str = BclConverter.DRAGEN
+    bcl_converter: str = BclConverter.BCLCONVERT
 
 
 @pytest.mark.parametrize(
@@ -209,7 +209,8 @@ def test_post_processing_tracks_undetermined_fastqs_for_bclconvert(
 
     # WHEN post processing the flow cell
     demux_post_processing_api.finish_flow_cell(
-        flow_cell_directory_name=bclconvert_flow_cell_dir_name, bcl_converter=BclConverter.DRAGEN
+        flow_cell_directory_name=bclconvert_flow_cell_dir_name,
+        bcl_converter=BclConverter.BCLCONVERT,
     )
 
     # THEN the undetermined fastqs were stored in housekeeper

diff --git a/tests/models/flow_cell/test_flowcell_model.py b/tests/models/flow_cell/test_flowcell_model.py
@@ -88,7 +88,7 @@ def test_get_bcl_converter_default(
     flow_cell = FlowCellDirectoryData(Path(flow_cell_directory_name_demultiplexed_with_bcl_convert))
 
     # THEN it sets the converter to BCLConverter
-    assert flow_cell.bcl_converter == BclConverter.DRAGEN
+    assert flow_cell.bcl_converter == BclConverter.BCLCONVERT
 
 
 def test_get_bcl_converter_bcl2fastq_flow_cell(