formatted code

prp/cli.py

@@ -6,12 +6,11 @@
 import click
 from pydantic import ValidationError
 
-from .models.metadata import SoupVersion, SoupType
-from .models.phenotype import ElementType, ElementStressSubtype
+from .models.metadata import SoupType, SoupVersion
+from .models.phenotype import ElementStressSubtype, ElementType
 from .models.qc import QcMethodIndex
 from .models.sample import MethodIndex, PipelineResult
 from .models.typing import TypingMethod
-from .parse.metadata import get_database_info, parse_run_info
 from .parse import (
     parse_amrfinder_amr_pred,
     parse_amrfinder_vir_pred,
@@ -27,6 +26,7 @@
     parse_tbprofiler_lineage_results,
     parse_virulencefinder_vir_pred,
 )
+from .parse.metadata import get_database_info, parse_run_info
 
 logging.basicConfig(
     level=logging.INFO, format="[%(asctime)s] %(levelname)s in %(module)s: %(message)s"
@@ -55,7 +55,6 @@ def cli():
     "-d",
     "--process-metadata",
     type=click.File(),
-    required=True,
     multiple=True,
     help="Nextflow processes metadata from the pipeline in json format",
 )
@@ -181,6 +180,15 @@ def create_output(
     if mykrobe:
         LOG.info("Parse mykrobe results")
         pred_res = json.load(mykrobe)
+
+        # verify that sample id is in prediction result
+        if not sample_id in pred_res:
+            LOG.warning(
+                "Sample id %s is not in Mykrobe result, possible sample mixup",
+                sample_id,
+            )
+            raise click.Abort()
+
         results["run_metadata"]["databases"].append(
             SoupVersion(
                 name="mykrobe-predictor",

prp/models/base.py

@@ -1,5 +1,5 @@
 """Generic database objects of which several other models are based on."""
-from pydantic import ConfigDict, BaseModel
+from pydantic import BaseModel, ConfigDict
 
 
 class RWModel(BaseModel):  # pylint: disable=too-few-public-methods

prp/models/phenotype.py

@@ -60,6 +60,7 @@ class ElementVirulenceSubtype(Enum):
 
     VIR = "VIRULENCE"
 
+
 class DatabaseReference(RWModel):
     """Refernece to a database."""
 

prp/parse/metadata.py

@@ -1,8 +1,9 @@
 """Parse metadata passed to pipeline."""
-from ..models.metadata import SoupVersion, RunInformation, RunMetadata
-from typing import List, TextIO
 import json
 import logging
+from typing import List, TextIO
+
+from ..models.metadata import RunInformation, RunMetadata, SoupVersion
 
 LOG = logging.getLogger(__name__)
 

prp/parse/phenotype/amrfinder.py

@@ -1,7 +1,7 @@
 """Parse AMRfinder plus result."""
+import logging
 from typing import Tuple
 
-import logging
 import pandas as pd
 
 from ...models.phenotype import ElementType, ElementTypeResult
@@ -65,9 +65,9 @@ def parse_amrfinder_amr_pred(file: str, element_type: ElementType) -> ElementTyp
         hits = hits.drop(columns=["Protein identifier", "HMM id", "HMM description"])
         hits = hits.where(pd.notnull(hits), None)
         # group predictions based on their element type
-        predictions = (hits
-                        .loc[lambda row: row.element_type == element_type]
-                        .to_dict(orient="records"))
+        predictions = hits.loc[lambda row: row.element_type == element_type].to_dict(
+            orient="records"
+        )
         results: ElementTypeResult = _parse_amrfinder_amr_results(predictions)
     return MethodIndex(type=element_type, result=results, software=Software.AMRFINDER)
 

prp/parse/phenotype/mykrobe.py

@@ -1,7 +1,7 @@
 """Parse Mykrobe results."""
 import logging
 import re
-from typing import Tuple, Dict, Any
+from typing import Any, Dict, Tuple
 
 from ...models.metadata import SoupVersions
 from ...models.phenotype import ElementTypeResult

prp/parse/phenotype/resfinder.py

@@ -1,10 +1,15 @@
 """Parse resfinder results."""
 import logging
-from typing import Any, Dict, Tuple, List
-
 from itertools import chain
+from typing import Any, Dict, List, Tuple
+
 from ...models.metadata import SoupVersions
-from ...models.phenotype import ElementType, ElementAmrSubtype, ElementStressSubtype, ElementTypeResult
+from ...models.phenotype import (
+    ElementAmrSubtype,
+    ElementStressSubtype,
+    ElementType,
+    ElementTypeResult,
+)
 from ...models.phenotype import PredictionSoftware as Software
 from ...models.phenotype import ResistanceGene, ResistanceVariant, VariantType
 from ...models.sample import MethodIndex
@@ -19,12 +24,15 @@
         "ethidium bromide",
         "chlorhexidine",
         "cetylpyridinium chloride",
-        "hydrogen peroxide"], 
-    ElementStressSubtype.HEAT: ["temperature"]
+        "hydrogen peroxide",
+    ],
+    ElementStressSubtype.HEAT: ["temperature"],
 }
 
 
-def _assign_res_subtype(prediction: Dict[str, Any], element_type: ElementType) -> ElementStressSubtype | None:
+def _assign_res_subtype(
+    prediction: Dict[str, Any], element_type: ElementType
+) -> ElementStressSubtype | None:
     """Assign element subtype from resfindere prediction."""
     assigned_subtype = None
     if element_type == ElementType.STRESS:
@@ -161,7 +169,7 @@ def parse_resfinder_amr_pred(
     stress_factors = list(chain(*STRESS_FACTORS.values()))
     categories = {
         ElementType.STRESS: stress_factors,
-        ElementType.AMR: list(set(prediction["phenotypes"]) - set(stress_factors))
+        ElementType.AMR: list(set(prediction["phenotypes"]) - set(stress_factors)),
     }
     # parse resistance
     sr_profile = _get_resfinder_amr_sr_profie(