doc string fix

Author: Muhammed Hasan Celik

src/decima/cli/vep.py

@@ -32,7 +32,7 @@
     "-v",
     "--variants",
     type=click.Path(exists=True),
-    help="Path to the variant file .vcf file. VCF file need to be normalized. Try normalizing th vcf file incase of an error. `bcftools norm -f ref.fasta input.vcf.gz -o output.vcf.gz`",
+    help="Path to the variant .vcf file. VCF file needs to be normalized. Try normalizing th vcf file in case of an error. `bcftools norm -f ref.fasta input.vcf.gz -o output.vcf.gz`",
 )
 @click.option("-o", "--output_pq", type=click.Path(), help="Path to the output parquet file.")
 @click.option("--tasks", type=str, default=None, help="Tasks to predict. If not provided, all tasks will be predicted.")

src/decima/cli/vep_attribution.py

@@ -13,7 +13,7 @@
     "-v",
     "--variants",
     type=click.Path(exists=True),
-    help="Path to the variant file .vcf file. VCF file need to be normalized. Try normalizing th vcf file incase of an error. `bcftools norm -f ref.fasta input.vcf.gz -o output.vcf.gz`",
+    help="Path to the variant .vcf file. VCF file needs to be normalized. Try normalizing the vcf file in case of an error. `bcftools norm -f ref.fasta input.vcf.gz -o output.vcf.gz`",
 )
 @click.option("-o", "--output_prefix", type=click.Path(), help="Path to the output prefix.")
 @click.option("--tasks", type=str, default=None, help="Tasks to predict. If not provided, all tasks will be predicted.")

src/decima/core/attribution.py

@@ -548,7 +548,7 @@ def __sub__(self, other):
             or (self.pattern_type != other.pattern_type)
         ):
             warnings.warn(
-                "`threshold`, `min_seqlet_len`, `max_seqlet_len`, `additional_flanks`, and `pattern_type` are not same overriding "
+                "`threshold`, `min_seqlet_len`, `max_seqlet_len`, `additional_flanks`, and `pattern_type` are not the same, overriding "
                 "them with the values of the first attribution object."
             )
 
@@ -623,7 +623,6 @@ def open(self):
                 self.model_name.append(h5.attrs["model_name"])
         else:
             self.h5 = h5py.File(str(self.attribution_h5), "r")
-            self.genes = self.h5["genes"][:].astype("U100")
             self.model_name = self.h5.attrs["model_name"]
             self.genome = self.h5.attrs["genome"]
             self.genes = self.h5["genes"][:].astype("U100")

src/decima/vep/vep.py

@@ -262,7 +262,7 @@ def _log_vep_warnings(warning_counter: Counter, num_variants: int, genome_path:
         if warning == WarningType.ALLELE_MISMATCH_WITH_REFERENCE_GENOME.value:
             logger.warning(
                 f"{warning}: {count} alleles out of {num_variants} predictions mismatched with the genome file {genome_path}."
-                "If this is not expected, please check if you are using the correct genome version."
+                " If this is not expected, please check if you are using the correct genome version."
             )
         elif warning == "no_overlap_found_for_chunk":
             logger.warning(f"{warning}: {count} chunks with no overlap found with genes.")