Udpated code with latest comment in PR

.github/workflows/tests.yml

@@ -16,7 +16,7 @@ jobs:
       - name: Set up Miniconda
         uses: conda-incubator/setup-miniconda@v2
         with:
-          activate-environment: myenv
+          activate-environment: taranis_env
           environment-file: environment.yml
 
       - name: Verify Conda environment
@@ -25,7 +25,7 @@ jobs:
       - name: Run your script
         run: |
           source $CONDA/etc/profile.d/conda.sh
-          conda activate myenv
+          conda activate taranis_env
           pip install .
           taranis analyze-schema -i  test/MLST_listeria -o analyze_schema_test  --cpus 1
           

taranis/__main__.py

@@ -381,7 +381,7 @@ def allele_calling(
         try:
             os.makedirs(output)
         except OSError as e:
-            log.info("Unable to create folder at %s because %s", output, e)
+            log.info("Unable to create folder at %s with error %s", output, e)
             stderr.print("[red] ERROR. Unable to create folder  " + output)
             sys.exit(1)
     # Filter fasta files from reference folder

taranis/analyze_schema.py

@@ -8,7 +8,7 @@
 
 from Bio import SeqIO
 
-from collections import OrderedDict
+from collections import OrderedDict, defaultdict
 
 import taranis.utils
 
@@ -140,11 +140,10 @@ def check_allele_quality(self, prokka_annotation: dict) -> OrderedDict:
         # get the unique sequences and compare the length with all sequences
         unique_seq = list(set(list(allele_seq.values())))
         if len(unique_seq) < len(allele_seq):
-            tmp_dict = {}
+            value_to_keys = defaultdict(list)
             for rec_id, seq_value in allele_seq.items():
-                if seq_value not in tmp_dict:
-                    tmp_dict[seq_value] = 0
-                else:
+                value_to_keys[seq_value].append(rec_id)
+                if len(value_to_keys[seq_value]) > 1:
                     a_quality[rec_id]["quality"] = "Bad quality"
                     a_quality[rec_id]["reason"] = "Duplicate allele"
                     if self.remove_duplicated:

taranis/blast.py

@@ -6,7 +6,6 @@
 
 from pathlib import Path
 from Bio.Blast.Applications import NcbiblastnCommandline
-import pdb
 
 log = logging.getLogger(__name__)
 stderr = rich.console.Console(
@@ -54,36 +53,37 @@ def create_blastdb(self, file_name, blast_dir):
 
     def run_blast(
         self,
-        query,
-        evalue=0.001,
-        perc_identity=90,
-        reward=1,
-        penalty=-2,
-        gapopen=1,
-        gapextend=1,
-        max_target_seqs=10,
-        max_hsps=10,
-        num_threads=1,
-    ):
-        """_summary_
-            blastn -outfmt "6 , qseqid , sseqid , pident ,  qlen , length , mismatch , gapopen , evalue , bitscore , sstart , send , qstart , qend , sseq , qseq" -query /media/lchapado/Reference_data/proyectos_isciii/taranis/documentos_antiguos/pasteur_schema/lmo0002.fasta -db /media/lchapado/Reference_data/proyectos_isciii/taranis/test/blastdb/RA-L2073_R1/RA-L2073_R1 -evalue 0.001 -penalty -2 -reward 1 -gapopen 1 -gapextend 1  -perc_identity 100 > /media/lchapado/Reference_data/proyectos_isciii/taranis/test/blast_sample_locus002.txt
+        query: str,
+        evalue: float = 0.001,
+        perc_identity: int = 90,
+        reward: int = 1,
+        penalty: int = -2,
+        gapopen: int = 1,
+        gapextend: int = 1,
+        max_target_seqs: int = 1000,
+        max_hsps: int = 10,
+        num_threads: int = 1,
+    ) -> list:
+        """blast command is executed, returning a list of each match found
 
         Args:
-            query (_type_): _description_
-            evalue (float, optional): _description_. Defaults to 0.001.
-            perc_identity (int, optional): _description_. Defaults to 90.
-            reward (int, optional): _description_. Defaults to 1.
-            penalty (int, optional): _description_. Defaults to -2.
-            gapopen (int, optional): _description_. Defaults to 1.
-            gapextend (int, optional): _description_. Defaults to 1.
-            max_target_seqs (int, optional): _description_. Defaults to 10.
-            max_hsps (int, optional): _description_. Defaults to 10.
-            num_threads (int, optional): _description_. Defaults to 1.
+            query (str): file path which contains the fasta sequence to query
+            evalue (float, optional): filtering results on e-value. Defaults to 0.001.
+            perc_identity (int, optional): percentage of identity. Defaults to 90.
+            reward (int, optional): value for rewardin. Defaults to 1.
+            penalty (int, optional): penalty value. Defaults to -2.
+            gapopen (int, optional): value for gap open. Defaults to 1.
+            gapextend (int, optional): value for gap extended. Defaults to 1.
+            max_target_seqs (int, optional): max target to output. Defaults to 1000.
+            max_hsps (int, optional): max hsps. Defaults to 10.
+            num_threads (int, optional): number of threads. Defaults to 1.
+
+        Returns:
+            list: list of strings containing blast results
         """
         blast_parameters = '"6 , qseqid , sseqid , pident ,  qlen , length , mismatch , gapopen , evalue , bitscore , sstart , send , qstart , qend , sseq , qseq"'
-        pdb.set_trace()
-        # db=self.blast_dir, evalue=evalue, perc_identity=perc_identity_ref, reward=reward, penalty=penalty, gapopen=gapopen, gapextend=gapextend, outfmt=blast_parameters, max_target_seqs=max_target_seqs, max_hsps=max_hsps, num_threads=num_threads, query=core_reference_allele_path)
         cline = NcbiblastnCommandline(
+            task="blastn",
             db=self.out_blast_dir,
             evalue=evalue,
             perc_identity=perc_identity,