Merge branch 'master' into refactor-sql-addhandler

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 54.5.3
+current_version = 54.10.0
 commit = True
 tag = True
 tag_name = v{new_version}

.github/workflows/tests_and_coverage.yml

@@ -37,7 +37,7 @@ jobs:
 
       - name: Test with pytest & Coveralls
         run: |
-          pytest --cov=cg/
+          pytest -n auto --cov=cg/
           coveralls
         env:
           COVERALLS_REPO_TOKEN: ${{ secrets.COVERALLS_REPO_TOKEN }}

cg/__init__.py

@@ -1,2 +1,2 @@
 __title__ = "cg"
-__version__ = "54.5.3"
+__version__ = "54.10.0"

cg/apps/demultiplex/sample_sheet/create.py

@@ -1,8 +1,10 @@
 import logging
 
-from cg.apps.demultiplex.sample_sheet.models import FlowCellSample
+from cg.apps.demultiplex.sample_sheet.sample_models import (
+    FlowCellSampleBcl2Fastq,
+    FlowCellSampleBCLConvert,
+)
 from cg.apps.demultiplex.sample_sheet.sample_sheet_creator import (
-    SampleSheetCreator,
     SampleSheetCreatorBcl2Fastq,
     SampleSheetCreatorBCLConvert,
 )
@@ -14,9 +16,9 @@
 
 def get_sample_sheet_creator(
     flow_cell: FlowCellDirectoryData,
-    lims_samples: list[FlowCellSample],
+    lims_samples: list[FlowCellSampleBcl2Fastq | FlowCellSampleBCLConvert],
     force: bool,
-) -> SampleSheetCreator:
+) -> SampleSheetCreatorBcl2Fastq | SampleSheetCreatorBCLConvert:
     """Returns an initialised sample sheet creator according to the demultiplexing software."""
     if flow_cell.bcl_converter == BclConverter.BCL2FASTQ:
         return SampleSheetCreatorBcl2Fastq(
@@ -27,16 +29,19 @@ def get_sample_sheet_creator(
 
 def create_sample_sheet(
     flow_cell: FlowCellDirectoryData,
-    lims_samples: list[FlowCellSample],
+    lims_samples: list[FlowCellSampleBcl2Fastq | FlowCellSampleBCLConvert],
     force: bool = False,
 ) -> list[list[str]]:
     """Create a sample sheet for a flow cell."""
-    sample_sheet_creator: SampleSheetCreator = get_sample_sheet_creator(
-        flow_cell=flow_cell,
-        lims_samples=lims_samples,
-        force=force,
+    sample_sheet_creator: SampleSheetCreatorBcl2Fastq | SampleSheetCreatorBCLConvert = (
+        get_sample_sheet_creator(
+            flow_cell=flow_cell,
+            lims_samples=lims_samples,
+            force=force,
+        )
     )
     LOG.info(
-        f"Constructing a {flow_cell.bcl_converter} sample sheet for the {flow_cell.sequencer_type} flow cell {flow_cell.id}"
+        f"Constructing a {flow_cell.bcl_converter} sample sheet "
+        f"for the {flow_cell.sequencer_type} flow cell {flow_cell.id}"
     )
     return sample_sheet_creator.construct_sample_sheet()

cg/apps/demultiplex/sample_sheet/index.py

@@ -3,13 +3,8 @@
 
 from pydantic import BaseModel
 
-from cg.apps.demultiplex.sample_sheet.models import (
-    FlowCellSample,
-    FlowCellSampleBcl2Fastq,
-    FlowCellSampleBCLConvert,
-)
 from cg.constants.constants import FileFormat
-from cg.constants.sequencing import Sequencers
+from cg.constants.symbols import DASH
 from cg.io.controller import ReadFile
 from cg.resources import VALID_INDEXES_PATH
 from cg.utils.utils import get_hamming_distance
@@ -25,7 +20,7 @@
 
 def is_dual_index(index: str) -> bool:
     """Determines if an index in the raw sample sheet is dual index or not."""
-    return "-" in index
+    return DASH in index
 
 
 class Index(BaseModel):
@@ -51,20 +46,14 @@ def get_valid_indexes(dual_indexes_only: bool = True) -> list[Index]:
     return indexes
 
 
-def get_index_pair(sample: FlowCellSample) -> tuple[str, str]:
-    """Returns a sample index separated into index 1 and index 2."""
-    if is_dual_index(sample.index):
-        index_1, index_2 = sample.index.split("-")
-        return index_1.strip().replace("NNNNNNNNN", ""), index_2.strip()
-    return sample.index.replace("NNNNNNNNN", ""), sample.index2
-
-
-def is_padding_needed(index_cycles: int, sample_index_length: int) -> bool:
+def is_padding_needed(index1_cycles: int, index2_cycles: int, sample_index_length: int) -> bool:
     """Returns whether a sample needs padding or not given the sample index length.
-    A sample needs padding if its adapted index length is shorter than the number of index cycles
-    reads stated in the run parameters file of the sequencing. This happens when the sample index
-    is 8 nucleotides long and the number of index cycles read is 10 nucleotides.
+    A sample from a NovaSeq6000 flow cell needs padding if its adapted index lengths are shorter
+    than the number of index cycles reads stated in the run parameters file for both indexes.
+    This happens when the sample index is 8 nucleotides long and the number of index cycles read is
+    10 nucleotides long.
     """
+    index_cycles: int | None = index1_cycles if index1_cycles == index2_cycles else None
     return index_cycles == LONG_INDEX_CYCLE_NR and sample_index_length == SHORT_SAMPLE_INDEX_LENGTH
 
 
@@ -95,81 +84,3 @@ def get_hamming_distance_for_indexes(sequence_1: str, sequence_2: str) -> int:
     return get_hamming_distance(
         str_1=sequence_1[:shortest_index_length], str_2=sequence_2[:shortest_index_length]
     )
-
-
-def update_barcode_mismatch_values_for_sample(
-    sample_to_update: FlowCellSampleBCLConvert,
-    samples_to_compare_to: list[FlowCellSampleBCLConvert],
-) -> None:
-    """Updates the sample's barcode mismatch values.
-    If a sample index has a hamming distance to any other sample lower than the threshold
-    (3 nucleotides), the barcode mismatch value for that index is set to zero."""
-    index_1_sample_to_update, index_2_sample_to_update = get_index_pair(sample=sample_to_update)
-    for sample_to_compare_to in samples_to_compare_to:
-        if sample_to_update.sample_id == sample_to_compare_to.sample_id:
-            continue
-        index_1, index_2 = get_index_pair(sample=sample_to_compare_to)
-        if (
-            get_hamming_distance_for_indexes(
-                sequence_1=index_1_sample_to_update, sequence_2=index_1
-            )
-            < MINIMUM_HAMMING_DISTANCE
-        ):
-            LOG.debug(
-                f"Turning barcode mismatch for index 1 to 0 for sample {sample_to_update.sample_id}"
-            )
-            sample_to_update.barcode_mismatches_1 = 0
-        if (
-            get_hamming_distance_for_indexes(
-                sequence_1=index_2_sample_to_update,
-                sequence_2=index_2,
-            )
-            < MINIMUM_HAMMING_DISTANCE
-        ):
-            LOG.debug(
-                f"Turning barcode mismatch for index 2 to 0 for sample {sample_to_update.sample_id}"
-            )
-            sample_to_update.barcode_mismatches_2 = 0
-
-
-def pad_and_reverse_complement_sample_indexes(
-    sample: FlowCellSample, index_cycles: int, perform_reverse_complement: bool
-) -> None:
-    """Adapts the indexes of sample.
-    1. Pad indexes if needed so that all indexes have a length equal to the number of index reads
-    2. Takes the reverse complement of index 2 in case of the new NovaSeq software control version
-    (1.7) in combination with the new reagent kit (version 1.5).
-    3. Assigns the indexes to the sample attributes index and index2."""
-    index1, index2 = get_index_pair(sample=sample)
-    index_length = len(index1)
-    if isinstance(sample, FlowCellSampleBcl2Fastq) and is_padding_needed(
-        index_cycles=index_cycles, sample_index_length=index_length
-    ):
-        LOG.debug("Padding indexes")
-        index1 = pad_index_one(index_string=index1)
-        index2 = pad_index_two(index_string=index2, reverse_complement=perform_reverse_complement)
-    LOG.debug(f"Padding not necessary for sample {sample.sample_id}")
-    if perform_reverse_complement:
-        index2 = get_reverse_complement_dna_seq(index2)
-    sample.index = index1
-    sample.index2 = index2
-
-
-def update_indexes_for_samples(
-    samples: list[FlowCellSampleBCLConvert | FlowCellSampleBcl2Fastq],
-    index_cycles: int,
-    perform_reverse_complement: bool,
-    sequencer: str,
-) -> None:
-    """Updates the values to the fields index1 and index 2 of samples."""
-    for sample in samples:
-        if sequencer != Sequencers.NOVASEQ:
-            index1, index2 = get_index_pair(sample=sample)
-            sample.index = index1
-            sample.index2 = index2
-        else:
-            pad_and_reverse_complement_sample_indexes(
-                sample=sample,
-                index_cycles=index_cycles,
-                perform_reverse_complement=perform_reverse_complement,
-            )

cg/apps/demultiplex/sample_sheet/read_sample_sheet.py

@@ -4,17 +4,14 @@
 
 from pydantic import TypeAdapter
 
-from cg.apps.demultiplex.sample_sheet.models import (
+from cg.apps.demultiplex.sample_sheet.sample_models import (
     FlowCellSample,
     FlowCellSampleBcl2Fastq,
     FlowCellSampleBCLConvert,
-    SampleSheet,
 )
+from cg.apps.demultiplex.sample_sheet.sample_sheet_models import SampleSheet
 from cg.constants.constants import FileFormat
-from cg.constants.demultiplexing import (
-    SampleSheetBcl2FastqSections,
-    SampleSheetBCLConvertSections,
-)
+from cg.constants.demultiplexing import SampleSheetBcl2FastqSections, SampleSheetBCLConvertSections
 from cg.exc import SampleSheetError
 from cg.io.controller import ReadFile