Update pydantic qcmetrics (#3875)

### Update Pydantic model for qc metrics and Balsamic

cg/models/analysis.py

@@ -1,4 +1,4 @@
-from pydantic.v1 import BaseModel
+from pydantic import BaseModel, ConfigDict
 
 from cg.models.raredisease.raredisease import RarediseaseQCMetrics
 from cg.models.rnafusion.rnafusion import RnafusionQCMetrics
@@ -9,8 +9,7 @@
 class AnalysisModel(BaseModel):
     """Metadata analysis model"""
 
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
 
 class NextflowAnalysis(AnalysisModel):

cg/models/balsamic/config.py

@@ -1,7 +1,7 @@
 from datetime import datetime
 from pathlib import Path
 
-from pydantic.v1 import BaseModel, validator
+from pydantic import BaseModel, field_validator, ValidationInfo
 
 from cg.constants.constants import SampleType
 
@@ -47,16 +47,17 @@ class BalsamicConfigReference(BaseModel):
     """
 
     reference_genome: Path
-    reference_genome_version: str | None
+    reference_genome_version: str | None = None
 
-    @validator("reference_genome_version", always=True)
-    def extract_genome_version_from_path(cls, value: str | None, values: dict) -> str:
+    @field_validator("reference_genome_version")
+    @classmethod
+    def extract_genome_version_from_path(cls, _, info: ValidationInfo) -> str:
         """
         Return the genome version from the reference path:
         /home/proj/stage/cancer/balsamic_cache/X.X.X/hg19/genome/human_g1k_v37.fasta
         """
 
-        return str(values["reference_genome"]).split("/")[-3]
+        return str(info.data.get("reference_genome")).split("/")[-3]
 
 
 class BalsamicConfigPanel(BaseModel):
@@ -70,23 +71,24 @@ class BalsamicConfigPanel(BaseModel):
     """
 
     capture_kit: str
-    capture_kit_version: str | None
+    capture_kit_version: str | None = None
     chrom: list[str]
     pon_cnn: str | None = None
 
-    @validator("capture_kit", pre=True)
+    @field_validator("capture_kit", mode="before")
+    @classmethod
     def get_filename_from_path(cls, path: str) -> str:
         """Return the base name of the provided file path."""
         return Path(path).name
 
-    @validator("capture_kit_version", always=True)
-    def get_panel_version_from_filename(
-        cls, capture_kit_version: str | None, values: dict[str, str | None]
-    ) -> str:
+    @field_validator("capture_kit_version")
+    @classmethod
+    def get_panel_version_from_filename(cls, _, info: ValidationInfo) -> str:
         """Return the panel bed version from its filename (e.g. gicfdna_3.1_hg19_design.bed)."""
-        return values["capture_kit"].split("_")[-3]
+        return info.data.get("capture_kit").split("_")[-3]
 
-    @validator("pon_cnn", pre=True)
+    @field_validator("pon_cnn", mode="before")
+    @classmethod
     def get_pon_cnn_name_version_from_filename(cls, pon_cnn: str | None) -> str:
         """Return the CNVkit PON name and version from its filename (gmsmyeloid_5.3_hg19_design_CNVkit_PON_reference_v1.cnn)."""
         pon_cnn_filename_split: list[str] = Path(pon_cnn).stem.split("_")
@@ -110,12 +112,12 @@ class BalsamicConfigQC(BaseModel):
     """
 
     picard_rmdup: bool
-    adapter: str | None
+    adapter: str | None = None
     quality_trim: bool
     adapter_trim: bool
     umi_trim: bool
-    min_seq_length: str | None
-    umi_trim_length: str | None
+    min_seq_length: str | None = None
+    umi_trim_length: str | None = None
 
 
 class BalsamicVarCaller(BaseModel):
@@ -149,7 +151,7 @@ class BalsamicConfigJSON(BaseModel):
     analysis: BalsamicConfigAnalysis
     samples: list[BalsamicConfigSample]
     reference: BalsamicConfigReference
-    panel: BalsamicConfigPanel | None
+    panel: BalsamicConfigPanel | None = None
     QC: BalsamicConfigQC
     vcf: dict[str, BalsamicVarCaller]
     bioinfo_tools_version: dict[str, list[str]]

cg/models/balsamic/metrics.py

@@ -1,4 +1,4 @@
-from pydantic.v1 import validator
+from pydantic import field_validator
 
 from cg.models.deliverables.metric_deliverables import MetricCondition, MetricsBase
 from cg.models.qc_metrics import QCMetrics
@@ -17,60 +17,56 @@ class BalsamicMetricsBase(MetricsBase):
         condition: balsamic metric validation condition
     """
 
-    condition: MetricCondition | None
+    condition: MetricCondition | None = None
 
 
 class BalsamicQCMetrics(QCMetrics):
     """BALSAMIC common QC metrics"""
 
-    fold_80_base_penalty: float | None
-    mean_insert_size: float | None
-    percent_duplication: float | None
+    fold_80_base_penalty: float | None = None
+    mean_insert_size: float | None = None
+    percent_duplication: float | None = None
 
-    _percent_duplication = validator("percent_duplication", allow_reuse=True)(
-        percent_value_validation
-    )
+    _percent_duplication: float = field_validator("percent_duplication")(percent_value_validation)
 
 
 class BalsamicTargetedQCMetrics(BalsamicQCMetrics):
     """BALSAMIC targeted QC metrics"""
 
-    mean_target_coverage: float | None
-    median_target_coverage: float | None
-    pct_target_bases_50x: float | None
-    pct_target_bases_100x: float | None
-    pct_target_bases_250x: float | None
-    pct_target_bases_500x: float | None
-    pct_target_bases_1000x: float | None
-    pct_off_bait: float | None
-    gc_dropout: float | None
-
-    _pct_values = validator(
+    mean_target_coverage: float | None = None
+    median_target_coverage: float | None = None
+    pct_target_bases_50x: float | None = None
+    pct_target_bases_100x: float | None = None
+    pct_target_bases_250x: float | None = None
+    pct_target_bases_500x: float | None = None
+    pct_target_bases_1000x: float | None = None
+    pct_off_bait: float | None = None
+    gc_dropout: float | None = None
+
+    _pct_values: float = field_validator(
         "pct_target_bases_50x",
         "pct_target_bases_100x",
         "pct_target_bases_250x",
         "pct_target_bases_500x",
         "pct_target_bases_1000x",
         "pct_off_bait",
-        allow_reuse=True,
     )(percent_value_validation)
 
 
 class BalsamicWGSQCMetrics(BalsamicQCMetrics):
     """BALSAMIC WGS QC metrics"""
 
-    median_coverage: float | None
-    pct_15x: float | None
-    pct_30x: float | None
-    pct_60x: float | None
-    pct_100x: float | None
-    pct_pf_reads_improper_pairs: float | None
+    median_coverage: float | None = None
+    pct_15x: float | None = None
+    pct_30x: float | None = None
+    pct_60x: float | None = None
+    pct_100x: float | None = None
+    pct_pf_reads_improper_pairs: float | None = None
 
-    _pct_values = validator(
+    _pct_values: float = field_validator(
         "pct_15x",
         "pct_30x",
         "pct_60x",
         "pct_100x",
         "pct_pf_reads_improper_pairs",
-        allow_reuse=True,
     )(percent_value_validation)

cg/models/deliverables/metric_deliverables.py

@@ -1,8 +1,7 @@
 import operator
 from typing import Annotated, Any, Callable
 
-from pydantic import BaseModel, Field, field_validator
-from pydantic_core.core_schema import ValidationInfo
+from pydantic import BaseModel, Field, ValidationInfo, field_validator
 
 from cg.constants import PRECISION
 from cg.exc import CgError, MetricsQCError

cg/models/delivery_report/metadata.py

@@ -151,6 +151,7 @@ class WTSSampleMetadataModel(SequencingSampleMetadataModel):
     uniquely_mapped_reads: Annotated[str, BeforeValidator(get_number_as_string)] = NA_FIELD
 
     @field_validator("rin")
+    @classmethod
     def ensure_rin_thresholds(cls, rin: str) -> str:
         if rin != NA_FIELD:
             rin_number = float(rin)

cg/models/qc_metrics.py

@@ -1,4 +1,4 @@
-from pydantic.v1 import BaseModel
+from pydantic import BaseModel
 
 
 class QCMetrics(BaseModel):

tests/meta/workflow/test_rnafusion.py

@@ -24,7 +24,7 @@ def test_parse_analysis(
     analysis_model: NextflowAnalysis = analysis_api.parse_analysis(qc_metrics_raw=qc_metrics)
 
     # THEN the analysis model and its content should have been correctly extracted
-    assert analysis_model.sample_metrics[sample_id] == rnafusion_metrics
+    assert analysis_model.sample_metrics[sample_id].model_dump() == rnafusion_metrics
 
 
 def test_get_latest_metadata(