Fix NMD prediction

Makefile

@@ -38,11 +38,11 @@ format:	\
 
 .PHONY: format-isort
 format-isort:
-	pipenv run isort --profile=black --line-length 110 $(DIRS_PYTHON)
+	pipenv run isort --profile=black --line-length 100 $(DIRS_PYTHON)
 
 .PHONY: format-black
 format-black:
-	pipenv run black --line-length 110 $(DIRS_PYTHON)
+	pipenv run black --line-length 100 $(DIRS_PYTHON)
 
 .PHONY: lint
 lint: \
@@ -53,15 +53,15 @@ lint: \
 
 .PHONY: lint-isort
 lint-isort:
-	pipenv run isort --profile=black --line-length 110 --check-only --diff $(DIRS_PYTHON)
+	pipenv run isort --profile=black --line-length 100 --check-only --diff $(DIRS_PYTHON)
 
 .PHONY: lint-black
 lint-black:
-	pipenv run black --check --line-length 110 --diff $(DIRS_PYTHON)
+	pipenv run black --check --line-length 100 --diff $(DIRS_PYTHON)
 
 .PHONY: lint-flake8
 flake8:
-	pipenv run flake8 --max-line-length 110 $(DIRS_PYTHON)
+	pipenv run flake8 --max-line-length 100 $(DIRS_PYTHON)
 
 .PHONY: lint-mypy
 lint-mypy:

src/api/annonars.py

@@ -20,7 +20,9 @@ class AnnonarsClient:
     def __init__(self, *, api_base_url: Optional[str] = None):
         self.api_base_url = api_base_url or ANNONARS_API_BASE_URL
 
-    def get_variant_from_range(self, seqvar: SeqVar, start: int, stop: int) -> AnnonarsRangeResponse:
+    def get_variant_from_range(
+        self, seqvar: SeqVar, start: int, stop: int
+    ) -> AnnonarsRangeResponse:
         """Pull all variants within a range.
 
         Args:

src/api/dotty.py

@@ -18,7 +18,9 @@ class DottyClient:
     def __init__(self, *, api_base_url: Optional[str] = None):
         self.api_base_url = api_base_url or DOTTI_API_BASE_URL
 
-    def to_spdi(self, query: str, assembly: GenomeRelease = GenomeRelease.GRCh38) -> DottySpdiResponse | None:
+    def to_spdi(
+        self, query: str, assembly: GenomeRelease = GenomeRelease.GRCh38
+    ) -> DottySpdiResponse | None:
         """
         Converts a variant to SPDI format.
 

src/api/mehari.py

@@ -34,8 +34,8 @@ def get_seqvar_transcripts(self, seqvar: SeqVar) -> TranscriptsSeqVar:
             f"genome_release={seqvar.genome_release.name.lower()}"
             f"&chromosome={seqvar.chrom}"
             f"&position={seqvar.pos}"
-            f"&reference={seqvar.insert}"
-            f"&alternative={seqvar.delete}"
+            f"&reference={seqvar.delete}"
+            f"&alternative={seqvar.insert}"
         )
         logger.debug("GET request to: {}", url)
         response = requests.get(url)

src/auto_acmg.py

@@ -112,7 +112,9 @@ def predict(self):
             )
             self.seqvar: SeqVar = variant
             self.seqvar_pvs1_prediction: PVS1Prediction = PVS1Prediction.NotSet
-            self.seqvar_pvs1_prediction_path: PVS1PredictionSeqVarPath = PVS1PredictionSeqVarPath.NotSet
+            self.seqvar_pvs1_prediction_path: PVS1PredictionSeqVarPath = (
+                PVS1PredictionSeqVarPath.NotSet
+            )
             self.seqvar_ps1: Optional[bool] = None
             self.seqvar_pm5: Optional[bool] = None
 

src/auto_ps1_pm5.py

@@ -23,7 +23,9 @@
 class AutoPS1PM5:
     """Predicts PS1 criteria for sequence variants."""
 
-    def __init__(self, seqvar: SeqVar, genome_release: GenomeRelease, *, config: Optional[Config] = None):
+    def __init__(
+        self, seqvar: SeqVar, genome_release: GenomeRelease, *, config: Optional[Config] = None
+    ):
         #: Configuration to use.
         self.config = config or Config()
         # Attributes to be set
@@ -113,8 +115,14 @@ def predict(self) -> Optional[PS1PM5]:
             self.prediction = PS1PM5()
 
             primary_info = self._get_variant_info(self.seqvar)
-            if not primary_info or not primary_info.result.dbnsfp or not primary_info.result.dbnsfp.HGVSp_VEP:
-                raise MissingDataError("No valid primary variant information for PS1/PM5 prediction.")
+            if (
+                not primary_info
+                or not primary_info.result.dbnsfp
+                or not primary_info.result.dbnsfp.HGVSp_VEP
+            ):
+                raise MissingDataError(
+                    "No valid primary variant information for PS1/PM5 prediction."
+                )
 
             primary_aa_change = self._parse_HGVSp(primary_info.result.dbnsfp.HGVSp_VEP)
             if not primary_aa_change:

src/core/config.py

@@ -7,7 +7,9 @@
 class Settings(BaseSettings):
     """Settings for the autopvs1 CLI."""
 
-    model_config = SettingsConfigDict(env_file=".env", env_file_encoding="utf-8", case_sensitive=True)
+    model_config = SettingsConfigDict(
+        env_file=".env", env_file_encoding="utf-8", case_sensitive=True
+    )
 
     # --- app-specific settings ---
 
@@ -48,5 +50,7 @@ def _set_base_urls(cls, data: Any) -> Any:
         if isinstance(data, dict):
             data["api_base_url"] = data.get("api_base_url", settings.API_REEV_URL)
             for key in ("annonars", "mehari", "dotty"):
-                data[f"api_base_url_{key}"] = data.get(f"api_base_url_{key}", f"{data['api_base_url']}/{key}")
+                data[f"api_base_url_{key}"] = data.get(
+                    f"api_base_url_{key}", f"{data['api_base_url']}/{key}"
+                )
         return data

src/defs/auto_pvs1.py

@@ -14,6 +14,26 @@ class AlteredRegionMode(AutoAcmgBaseEnum):
     Exon = auto()
 
 
+class GenomicStrand(AutoAcmgBaseEnum):
+    """Enumeration for genomic strand."""
+
+    Plus = auto()
+    Minus = auto()
+
+    @staticmethod
+    def from_string(value: str):
+        """Converts string to enum member if possible, otherwise returns None."""
+        strand_mapping = {
+            "STRAND_PLUS": "Plus",
+            "STRAND_MINUS": "Minus",
+        }
+        value_mapped = strand_mapping.get(value, value)
+        for member in GenomicStrand:
+            if member.name == value_mapped:
+                return member
+        return None
+
+
 class TranscriptInfo(BaseModel):
     """Information about a transcript."""
 
@@ -143,7 +163,9 @@ class PVS1PredictionStrucVarPath(AutoAcmgBaseEnum):
 
 
 #: Mapping of PVS1 prediction path to description for sequence variant
-PVS1PredictionPathMapping: Dict[Union[PVS1PredictionSeqVarPath, PVS1PredictionStrucVarPath], str] = {
+PVS1PredictionPathMapping: Dict[
+    Union[PVS1PredictionSeqVarPath, PVS1PredictionStrucVarPath], str
+] = {
     PVS1PredictionSeqVarPath.NotSet: "Not Set",
     PVS1PredictionSeqVarPath.PTEN: "Special guideline for PTEN -> Predicted to undergo NMD",
     PVS1PredictionSeqVarPath.NF1: (
@@ -153,7 +175,8 @@ class PVS1PredictionStrucVarPath(AutoAcmgBaseEnum):
         "Predicted to undergo NMD -> Exon is absent from biologically-relevant transcript(s)"
     ),
     PVS1PredictionSeqVarPath.NF3: (
-        "Not predicted to undergo NMD -> " "Truncated/altered region is critical to protein function"
+        "Not predicted to undergo NMD -> "
+        "Truncated/altered region is critical to protein function"
     ),
     PVS1PredictionSeqVarPath.NF4: (
         "Not predicted to undergo NMD -> "

src/defs/seqvar.py

@@ -31,7 +31,9 @@
 #: Regular expression for dbSNP
 REGEX_DBSNP_ID = re.compile(r"^rs\d+$", re.IGNORECASE)
 #: Regular expression for ClinVar
-REGEX_CLINVAR_ID = re.compile(r"^(?P<accession>(?:RCV|VCV)\d{9})(?:\.(?P<version>\d+))?$", re.IGNORECASE)
+REGEX_CLINVAR_ID = re.compile(
+    r"^(?P<accession>(?:RCV|VCV)\d{9})(?:\.(?P<version>\d+))?$", re.IGNORECASE
+)
 
 
 class SeqVar:
@@ -52,7 +54,9 @@ def __init__(
         self.delete = delete.upper()
         self.insert = insert.upper()
         self.user_repr = (
-            user_repr if user_repr else f"{genome_release.name}-{self.chrom}-{pos}-{delete}-{insert}"
+            user_repr
+            if user_repr
+            else f"{genome_release.name}-{self.chrom}-{pos}-{delete}-{insert}"
         )
 
     def _normalize_chromosome(self, chrom: str) -> str:
@@ -140,7 +144,9 @@ def _parse_separated_seqvar(
             raise ParseError(f"Unable to parse colon/hyphen separated seqvar: {value}")
 
         genome_build_value = match.group("genome_build")
-        genome_build = GenomeRelease[genome_build_value] if genome_build_value else default_genome_release
+        genome_build = (
+            GenomeRelease[genome_build_value] if genome_build_value else default_genome_release
+        )
         chrom = self._normalize_chrom(match.group("chrom"))
         pos = int(match.group("pos"))
         delete = match.group("delete").upper()
@@ -173,7 +179,7 @@ def _parse_canonical_spdi_seqvar(self, value: str) -> SeqVar:
             raise ParseError(f"Unable to parse canonical SPDI variant: {value}")
 
         sequence = match.group("sequence").upper()
-        pos = int(match.group("pos"))
+        pos = int(match.group("pos")) + 1  # SPDI is 0-based
         delete = match.group("delete").upper()
         insert = match.group("insert").upper()
 

src/defs/strucvar.py

@@ -51,7 +51,9 @@ def __init__(
         self.start = start
         self.stop = stop
         self.user_repr = (
-            user_repr if user_repr else f"{sv_type.name}-{genome_release.name}-{self.chrom}-{start}-{stop}"
+            user_repr
+            if user_repr
+            else f"{sv_type.name}-{genome_release.name}-{self.chrom}-{start}-{stop}"
         )
 
     def _normalize_chromosome(self, chrom: str) -> str:

src/pvs1/auto_pvs1.py

@@ -80,7 +80,9 @@ def predict(
                 strucvar_pvs1 = StrucVarPVS1(self.strucvar)
                 strucvar_pvs1.initialize()
                 strucvar_pvs1.verify_PVS1()
-                self.strucvar_prediction, self.strucvar_prediction_path = strucvar_pvs1.get_prediction()
+                self.strucvar_prediction, self.strucvar_prediction_path = (
+                    strucvar_pvs1.get_prediction()
+                )
                 return self.strucvar_prediction, self.strucvar_prediction_path
             except AutoAcmgBaseException as e:
                 logger.exception("Error occurred: {}", e)