Merge branch 'master' into add-illumina-run-model

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 60.7.19
+current_version = 60.7.21
 commit = True
 tag = True
 tag_name = v{new_version}

.github/workflows/tests_and_coverage.yml

@@ -8,7 +8,7 @@ on:
 
 jobs:
   tests-coverage:
-    runs-on: ubuntu-latest
+    runs-on: Beefy_Linux
 
     steps:
       - name: Checkout Repository
@@ -37,7 +37,7 @@ jobs:
 
       - name: Test with pytest & Coveralls
         run: |
-          pytest -n auto --cov=cg/
+          pytest -n logical --cov=cg/
           coveralls
         env:
           COVERALLS_REPO_TOKEN: ${{ secrets.COVERALLS_REPO_TOKEN }}

cg/__init__.py

@@ -1,2 +1,2 @@
 __title__ = "cg"
-__version__ = "60.7.19"
+__version__ = "60.7.21"

cg/constants/report.py

@@ -41,6 +41,9 @@
 NO_FIELD: str = "Nej"
 PRECISION: int = 2
 
+RIN_MAX_THRESHOLD: int = 10
+RIN_MIN_THRESHOLD: int = 1
+
 REPORT_GENDER: dict[str, str] = {
     "unknown": "Okänd",
     "female": "Kvinna",

cg/models/report/metadata.py

@@ -1,12 +1,12 @@
-from pydantic import BaseModel, BeforeValidator
+from pydantic import BaseModel, BeforeValidator, field_validator
 from typing_extensions import Annotated
 
-from cg.constants import NA_FIELD
+from cg.constants import NA_FIELD, RIN_MIN_THRESHOLD, RIN_MAX_THRESHOLD
 from cg.models.report.validators import (
     get_float_as_percentage,
-    get_float_as_string,
     get_gender_as_string,
     get_report_string,
+    get_number_as_string,
 )
 
 
@@ -19,8 +19,8 @@ class SampleMetadataModel(BaseModel):
         duplicates: fraction of mapped sequence that is marked as duplicate; source: workflow
     """
 
-    million_read_pairs: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    duplicates: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
+    million_read_pairs: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    duplicates: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
 
 
 class MipDNASampleMetadataModel(SampleMetadataModel):
@@ -36,9 +36,9 @@ class MipDNASampleMetadataModel(SampleMetadataModel):
 
     bait_set: Annotated[str, BeforeValidator(get_report_string)] = NA_FIELD
     gender: Annotated[str, BeforeValidator(get_gender_as_string)] = NA_FIELD
-    mapped_reads: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    mean_target_coverage: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    pct_10x: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
+    mapped_reads: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    mean_target_coverage: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    pct_10x: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
 
 
 class BalsamicSampleMetadataModel(SampleMetadataModel):
@@ -49,8 +49,8 @@ class BalsamicSampleMetadataModel(SampleMetadataModel):
             fold_80: fold 80 base penalty; source: workflow
     """
 
-    mean_insert_size: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    fold_80: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
+    mean_insert_size: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    fold_80: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
 
 
 class BalsamicTargetedSampleMetadataModel(BalsamicSampleMetadataModel):
@@ -66,10 +66,10 @@ class BalsamicTargetedSampleMetadataModel(BalsamicSampleMetadataModel):
 
     bait_set: Annotated[str, BeforeValidator(get_report_string)] = NA_FIELD
     bait_set_version: Annotated[str, BeforeValidator(get_report_string)] = NA_FIELD
-    median_target_coverage: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    pct_250x: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    pct_500x: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    gc_dropout: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
+    median_target_coverage: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    pct_250x: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    pct_500x: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    gc_dropout: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
 
 
 class BalsamicWGSSampleMetadataModel(BalsamicSampleMetadataModel):
@@ -81,10 +81,10 @@ class BalsamicWGSSampleMetadataModel(BalsamicSampleMetadataModel):
             pct_60x: fraction of bases that attained at least 15X sequence coverage; source: workflow
     """
 
-    median_coverage: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    pct_15x: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    pct_60x: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    pct_reads_improper_pairs: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
+    median_coverage: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    pct_15x: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    pct_60x: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    pct_reads_improper_pairs: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
 
 
 class SequencingSampleMetadataModel(SampleMetadataModel):
@@ -96,7 +96,7 @@ class SequencingSampleMetadataModel(SampleMetadataModel):
     """
 
     gc_content: Annotated[str, BeforeValidator(get_float_as_percentage)] = NA_FIELD
-    mean_length_r1: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
+    mean_length_r1: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
 
 
 class WTSSampleMetadataModel(SequencingSampleMetadataModel):
@@ -115,16 +115,24 @@ class WTSSampleMetadataModel(SequencingSampleMetadataModel):
         uniquely_mapped_reads: percentage of mapped reads; source: workflow
     """
 
-    bias_5_3: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    input_amount: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    mrna_bases: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    pct_adapter: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    pct_surviving: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
+    bias_5_3: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    input_amount: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    mrna_bases: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    pct_adapter: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    pct_surviving: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
     q20_rate: Annotated[str, BeforeValidator(get_float_as_percentage)] = NA_FIELD
     q30_rate: Annotated[str, BeforeValidator(get_float_as_percentage)] = NA_FIELD
     ribosomal_bases: Annotated[str, BeforeValidator(get_float_as_percentage)] = NA_FIELD
-    rin: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    uniquely_mapped_reads: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
+    rin: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    uniquely_mapped_reads: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+
+    @field_validator("rin")
+    def ensure_rin_thresholds(cls, rin: str) -> str:
+        if rin != NA_FIELD:
+            rin_number = float(rin)
+            if RIN_MIN_THRESHOLD <= rin_number <= RIN_MAX_THRESHOLD:
+                return str(rin_number)
+        return NA_FIELD
 
 
 class RnafusionSampleMetadataModel(WTSSampleMetadataModel):
@@ -136,8 +144,8 @@ class RnafusionSampleMetadataModel(WTSSampleMetadataModel):
         mapped_reads: percentage of reads aligned to the reference sequence; source: workflow
     """
 
-    insert_size: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    insert_size_peak: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
+    insert_size: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    insert_size_peak: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
     mapped_reads: Annotated[str, BeforeValidator(get_float_as_percentage)] = NA_FIELD
 
 
@@ -151,10 +159,10 @@ class TaxprofilerSampleMetadataModel(SequencingSampleMetadataModel):
         million_read_pairs_after_filtering: number of reads after filtering; source: workflow
     """
 
-    average_read_length: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    mapped_reads: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    mean_length_r2: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    million_read_pairs_after_filtering: Annotated[str, BeforeValidator(get_float_as_string)] = (
+    average_read_length: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    mapped_reads: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    mean_length_r2: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    million_read_pairs_after_filtering: Annotated[str, BeforeValidator(get_number_as_string)] = (
         NA_FIELD
     )
 
@@ -167,5 +175,5 @@ class TomteSampleMetadataModel(WTSSampleMetadataModel):
         pct_intronic_bases: proportion of genomic bases within intronic regions; source: workflow
     """
 
-    pct_intergenic_bases: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
-    pct_intronic_bases: Annotated[str, BeforeValidator(get_float_as_string)] = NA_FIELD
+    pct_intergenic_bases: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
+    pct_intronic_bases: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD

cg/models/report/validators.py

@@ -33,14 +33,26 @@ def get_boolean_as_string(value: bool | None) -> str:
     return NA_FIELD
 
 
-def get_float_as_string(value: float | None) -> str:
-    """Return string representation of a float value."""
-    return str(round(float(value), PRECISION)) if value or isinstance(value, float) else NA_FIELD
+def get_number_as_string(value: Any) -> str:
+    """
+    Return string representation of a number. If None is provided, then it returns N/A.
+
+    Raises:
+        ValueError: If the input value cannot be converted to a float.
+    """
+    try:
+        result: str = str(round(float(value), PRECISION))
+        return result
+    except TypeError:
+        return NA_FIELD
+    except ValueError:
+        LOG.error(f"Value {value} cannot be converted to float")
+        raise
 
 
 def get_float_as_percentage(value: float | None) -> str:
     """Return string percentage representation of a float value."""
-    return get_float_as_string(value * 100) if value or isinstance(value, float) else NA_FIELD
+    return get_number_as_string(value * 100) if value or isinstance(value, float) else NA_FIELD
 
 
 def get_date_as_string(date: datetime | None) -> str:

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "cg"
-version = "60.7.19"
+version = "60.7.21"
 description = "Clinical Genomics command center"
 authors = ["Clinical Genomics <support@clinicalgenomics.se>"]
 readme = "README.md"

tests/meta/report/test_rnafusion_api.py

@@ -1,17 +1,22 @@
 """Test module for the Rnafusion delivery report API."""
 
+import pytest
+from pytest_mock import MockFixture
+
+from cg.constants import NA_FIELD, RIN_MAX_THRESHOLD, RIN_MIN_THRESHOLD
 from cg.meta.report.rnafusion import RnafusionReportAPI
 from cg.models.analysis import NextflowAnalysis
 from cg.models.report.metadata import RnafusionSampleMetadataModel
 from cg.store.models import Case, Sample
+from tests.mocks.limsmock import MockLimsAPI
 
 
 def test_get_sample_metadata(
     report_api_rnafusion: RnafusionReportAPI,
     sample_id: str,
     rnafusion_case_id: str,
     rnafusion_validated_metrics: dict[str, str],
-    rnafusion_mock_analysis_finish,
+    rnafusion_mock_analysis_finish: None,
 ):
     """Test Rnafusion sample metadata extraction."""
 
@@ -33,3 +38,46 @@ def test_get_sample_metadata(
 
     # THEN the sample metadata should be correctly retrieved and match the expected validated metrics
     assert sample_metadata.model_dump() == rnafusion_validated_metrics
+
+
+@pytest.mark.parametrize(
+    "input_rin, expected_rin",
+    [
+        (RIN_MAX_THRESHOLD, str(float(RIN_MAX_THRESHOLD))),  # Test for a valid integer input
+        (RIN_MAX_THRESHOLD + 1, NA_FIELD),  # Test for an integer above the allowed threshold
+        (RIN_MIN_THRESHOLD - 1, NA_FIELD),  # Test for an integer below the allowed threshold
+        (None, NA_FIELD),  # Test for a None input
+    ],
+)
+def test_ensure_rin_thresholds(
+    rnafusion_case_id: str,
+    sample_id: str,
+    input_rin: int | float,
+    expected_rin: str,
+    report_api_rnafusion: RnafusionReportAPI,
+    rnafusion_mock_analysis_finish: None,
+    mocker: MockFixture,
+):
+    """Test Rnafusion RIN value validation."""
+
+    # GIVEN a Rnafusion case and associated sample
+    case: Case = report_api_rnafusion.status_db.get_case_by_internal_id(
+        internal_id=rnafusion_case_id
+    )
+    sample: Sample = report_api_rnafusion.status_db.get_sample_by_internal_id(internal_id=sample_id)
+
+    # GIVEN an analysis metadata object
+    latest_metadata: NextflowAnalysis = report_api_rnafusion.analysis_api.get_latest_metadata(
+        case_id=rnafusion_case_id
+    )
+
+    # GIVEN a specific RIN value
+    mocker.patch.object(MockLimsAPI, "get_sample_rin", return_value=input_rin)
+
+    # WHEN getting the sample metadata
+    sample_metadata: RnafusionSampleMetadataModel = report_api_rnafusion.get_sample_metadata(
+        case=case, sample=sample, analysis_metadata=latest_metadata
+    )
+
+    # THEN the sample RIN value should match the expected RIN value
+    assert sample_metadata.rin == expected_rin

tests/models/report/test_validators.py

@@ -18,13 +18,13 @@
     get_boolean_as_string,
     get_date_as_string,
     get_delivered_files_as_file_names,
-    get_float_as_percentage,
-    get_float_as_string,
     get_gender_as_string,
     get_list_as_string,
     get_path_as_string,
     get_prep_category_as_string,
     get_report_string,
+    get_number_as_string,
+    get_float_as_percentage,
 )
 
 
@@ -63,30 +63,36 @@ def test_get_boolean_as_string():
     assert validated_not_bool_field == NA_FIELD
 
 
-def test_get_float_as_string():
-    """Test the validation of a float value."""
-
-    # GIVEN a valid float input
-    float_value: float = 12.3456789
-
-    # WHEN performing the validation
-    validated_float_value: str = get_float_as_string(float_value)
-
-    # THEN check if the input value was formatted correctly
-    assert validated_float_value == "12.35"
+@pytest.mark.parametrize(
+    "input_value, expected_output",
+    [
+        (12.3456789, "12.35"),  # Test for a valid float input
+        (0.0, "0.0"),  # Test for float zero input
+        (5, "5.0"),  # Test for a valid integer input
+        (0, "0.0"),  # Test for integer zero input
+        (None, NA_FIELD),  # Test for None input
+        ("1.2", "1.2"),  # Test for valid string input
+        ("invalid", ValueError),  # Test for an invalid string input
+    ],
+)
+def test_get_number_as_string(input_value: Any, expected_output: str, caplog: LogCaptureFixture):
+    """Test the validation and formatting of numbers."""
 
+    # GIVEN a list of number inputs and their expected values
 
-def test_get_float_as_string_zero_input():
-    """Tests the validation of a float value when input is zero."""
+    if expected_output == ValueError:
+        # WHEN getting a string representation of a number
+        with pytest.raises(ValueError):
+            get_number_as_string(input_value)
 
-    # GIVEN a valid float input
-    float_value: float = 0.0
+        # THEN a ValueError should have been raised for an invalid number input
+        assert f"Value {input_value} cannot be converted to float" in caplog.text
+    else:
+        # WHEN getting a string representation of a number
+        validated_float_value = get_number_as_string(input_value)
 
-    # WHEN performing the validation
-    validated_float_value: str = get_float_as_string(float_value)
-
-    # THEN check if the input value was formatted correctly
-    assert validated_float_value == "0.0"
+        # THEN the expected output should be correctly formatted
+        assert validated_float_value == expected_output
 
 
 def test_get_float_as_percentage():