Fixes in allele calling module

taranis/__main__.py

@@ -278,7 +278,7 @@ def analyze_schema(
     "--eval-cluster/--no-eval-cluster",
     required=False,
     default=True,
-    help="Evaluate if the reference alleles match against blast with a 90% identity",
+    help="Evaluate if the reference alleles match against blast with the identity set in eval-identity param",
 )
 @click.option(
     "-k",
@@ -304,6 +304,14 @@ def analyze_schema(
     default=0.75,
     help="Resolution value used for clustering.",
 )
+@click.option(
+    "-e",
+    "--eval-identity",
+    required=False,
+    type=float,
+    default=85,
+    help="Resolution value used for clustering.",
+)
 @click.option(
     "--seed",
     required=False,
@@ -332,6 +340,7 @@ def reference_alleles(
     kmer_size: int,
     sketch_size: int,
     cluster_resolution: float,
+    eval_identity: float,
     seed: int,
     cpus: int,
     force: bool,
@@ -362,6 +371,7 @@ def reference_alleles(
                 kmer_size,
                 sketch_size,
                 cluster_resolution,
+                eval_identity,
                 seed,
             )
             for f_file in schema_files
@@ -404,12 +414,12 @@ def reference_alleles(
 )
 @click.option(
     "-t",
-    "--threshold",
+    "--hit_lenght_perc",
     required=False,
     nargs=1,
     default=0.8,
     type=float,
-    help="Threshold value to consider in blast. Values from 0 to 1. default 0.8",
+    help="Threshold value to consider in blast hit percentage regarding the reference length. Values from 0 to 1. default 0.8",
 )
 @click.option(
     "-p",
@@ -484,7 +494,7 @@ def allele_calling(
     reference: str,
     annotation: str,
     assemblies: list,
-    threshold: float,
+    hit_lenght_perc: float,
     perc_identity: int,
     output: str,
     force: bool,
@@ -507,7 +517,6 @@ def allele_calling(
     if not force:
         _ = taranis.utils.prompt_user_if_folder_exists(output)
     # Filter fasta files from reference folder
-    # ref_alleles = glob.glob(os.path.join(reference, "*.fasta"))
     max_cpus = taranis.utils.cpus_available()
     if cpus > max_cpus:
         stderr.print("[red] Number of CPUs bigger than the CPUs available")
@@ -536,7 +545,7 @@ def allele_calling(
                 schema,
                 prediction_data,
                 schema_ref_files,
-                threshold,
+                hit_lenght_perc,
                 perc_identity,
                 output,
                 inf_allele_obj,
@@ -553,32 +562,13 @@ def allele_calling(
             except Exception as e:
                 print(e)
                 continue
-    """
-    for assembly_file in assemblies:
-        results.append(
-            taranis.allele_calling.parallel_execution(
-                assembly_file,
-                schema,
-                prediction_data,
-                schema_ref_files,
-                threshold,
-                perc_identity,
-                output,
-                inf_allele_obj,
-                snp,
-                alignment,
-                proteine_threshold,
-                increase_sequence,
-            )
-        )
-    """
+
     _ = taranis.allele_calling.collect_data(
         results, output, snp, alignment, schema_ref_files, cpus
     )
     finish = time.perf_counter()
     print(f"Allele calling finish in {round((finish-start)/60, 2)} minutes")
     log.info("Allele calling finish in %s minutes", round((finish - start) / 60, 2))
-    # sample_allele_obj.analyze_sample()
 
 
 @taranis_cli.command(help_priority=3)