rdrpcatch 0.0.3__py3-none-any.whl → 0.0.5__py3-none-any.whl

rdrpcatch/rdrpcatch_scripts/format_pyhmmer_out.py

@@ -68,7 +68,7 @@ class hmmsearch_formatter:
         # Check if the dataframe is empty
         if data_df.is_empty():
             title_line= ['Contig_name', 'Translated_contig_name (frame)', 'Sequence_length(AA)', 'Profile_name',
-                         'Profile_length', 'E-value', 'score', 'acc', 'norm_bitscore_profile',
+                         'Profile_length', 'E-value', 'score','norm_bitscore_profile',
                          'norm_bitscore_contig', 'ID_score', 'RdRp_from(AA)', 'RdRp_to(AA)', 'profile_coverage',
                          'contig_coverage']
             data_df = pl.DataFrame({col: [] for col in title_line})

rdrpcatch/rdrpcatch_scripts/utils.py

@@ -255,33 +255,48 @@ class fasta:
             self.logger.silent_log(f"Processing {len(rdrp_coords_list)} coordinates")
             self.logger.silent_log(f"First few coordinates: {rdrp_coords_list[:3]}")
 
+        contig_dict = {}
+        for contig_name, rdrp_from, rdrp_to in rdrp_coords_list:
+            contig_key = str(contig_name).strip()
+            if contig_key not in contig_dict:
+                contig_dict[contig_key] = []
+            contig_dict[contig_key].append((rdrp_from, rdrp_to))
+
         reader = needletail.parse_fastx_file(self.fasta_file)
         matches_found = 0
         with open(outfile, 'w') as out_handle:
             for record in reader:
-                # pyhmmer uses the first word of the header as the ID, so split on whitespace
+                # Get the record ID
                 record_id = record.id.strip().split(" ")[0]
-                if self.logger:
-                    self.logger.silent_log(f"Processing record with ID: '{record_id}'")
-                for contig_name, rdrp_from, rdrp_to in rdrp_coords_list:
-                    contig_name = str(contig_name).strip()
+
+                # Check if this record matches any of our target contigs
+                if record_id in contig_dict:
                     if self.logger:
-                        self.logger.silent_log(f"Comparing record '{record_id}' with contig '{contig_name}'")
-                    if record_id == contig_name:
-                        matches_found += 1
-                        seq = record.seq[rdrp_from-1:rdrp_to]
+                        self.logger.silent_log(f"Match found for record ID: '{record_id}'")
+
+                    # Process all matching coordinates for this contig
+                    for rdrp_from, rdrp_to in contig_dict[record_id]:
+                        seq = record.seq[rdrp_from - 1:rdrp_to]
                         fasta_header = f"{record_id}_RdRp_{rdrp_from}-{rdrp_to}"
                         out_handle.write(f">{fasta_header}\n{seq}\n")
+                        matches_found += 1
+
+                    # Remove the processed contig to avoid future checks
+                    del contig_dict[record_id]
+
+                    # If all contigs have been found, exit early
+                    if not contig_dict:
                         if self.logger:
-                            self.logger.silent_log(f"Match found! Writing sequence of length {len(seq)}")
-                    else:
-                        if self.logger:
-                            self.logger.silent_log(f"No match - lengths: {len(record_id)}|{len(contig_name)}, "
-                                                 f"record_id bytes: {record_id.encode()}, contig bytes: {contig_name.encode()}")
-        
+                            self.logger.silent_log("All contigs processed. Exiting early.")
+                        break
+
         if self.logger:
             self.logger.silent_log(f"Total matches found: {matches_found}")
 
+        return matches_found
+
+
+
 
 class mmseqs_parser:
 

rdrpcatch/rdrpcatch_wrapper.py

@@ -111,7 +111,7 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
     if not os.path.exists(outputs.output_dir):
         os.makedirs(outputs.output_dir)
     else:
-        raise FileExistsError(f"Output directory already exists: {outputs.output_dir}, please choose a different directory.")
+        raise FileExistsError(f"Output directory already exists: {outputs.output_dir}, Please choose a different directory.")
     if not os.path.exists(outputs.log_dir):
         os.makedirs(outputs.log_dir)
 
@@ -363,7 +363,7 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
 
 
         # Combine all the dataframes in the list
-        combined_df = pl.concat(df_list, how='vertical')
+        combined_df = pl.concat(df_list, how='vertical_relaxed')
         # Write the combined dataframe to a tsv file
         for col in ['E-value', 'score', 'norm_bitscore_profile', 'norm_bitscore_contig',
                     'ID_score', 'profile_coverage', 'contig_coverage']:
@@ -526,9 +526,8 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
             outputs.tsv_outdir.mkdir(parents=True)
 
 
-
         # Combine all the dataframes in the list
-        combined_df = pl.concat(df_list, how='vertical')
+        combined_df = pl.concat(df_list, how='vertical_relaxed')
         # Write the combined dataframe to a tsv file
         for col in ['E-value', 'score', 'norm_bitscore_profile', 'norm_bitscore_contig',
                     'ID_score', 'profile_coverage', 'contig_coverage']:
@@ -581,9 +580,9 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
         utils.fasta(input_file).write_fasta(utils.fasta(input_file).extract_contigs(combined_set), outputs.fasta_prot_out_path)
 
         if verbose:
-            logger.loud_log(f"Contigs written to: {outputs.fasta_prot_out_path}")
+            logger.loud_log(f"Full aminoacid contigs written to: {outputs.fasta_prot_out_path}")
         else:
-            logger.silent_log(f"Contigs written to: {outputs.fasta_prot_out_path}")
+            logger.silent_log(f" Full aminoacid contigs written to: {outputs.fasta_prot_out_path}")
 
         if not os.path.exists(outputs.gff_output_dir):
             outputs.gff_output_dir.mkdir(parents=True)
@@ -594,9 +593,9 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
         utils.fasta(input_file, logger).write_fasta_coords(rdrp_coords_list,outputs.fasta_trimmed_out_path, seq_type)
 
         if verbose:
-            logger.loud_log(f"RdRpCATCH output file written to: {outputs.fasta_prot_out_path}")
+            logger.loud_log(f"Trimmed contigs written to: {outputs.fasta_trimmed_out_path}")
         else:
-            logger.silent_log(f"RdRpCATCH output file written to: {outputs.fasta_prot_out_path}")
+            logger.silent_log(f"Trimmed contigs written to: {outputs.fasta_trimmed_out_path}")
 
         if not os.path.exists(outputs.mmseqs_tax_output_dir):
             outputs.mmseqs_tax_output_dir.mkdir(parents=True)

{rdrpcatch-0.0.3.dist-info → rdrpcatch-0.0.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdrpcatch
-Version: 0.0.3
+Version: 0.0.5
 Dynamic: Summary
 Project-URL: Home, https://github.com/dimitris-karapliafis/RdRpCATCH
 Project-URL: Source, https://github.com/dimitris-karapliafis/RdRpCATCH
@@ -81,7 +81,7 @@ The dependencies can be installed using conda or mamba. Follow these steps:
 
 Create a new conda environment and install the dependencies:
 ```bash
-conda create -n rdrpcatch python=3.12
+conda env create -n rdrpcatch python=3.12
 conda activate rdrpcatch
 conda install -c bioconda mmseqs2==17.b804f seqkit==2.10.0
 ```

{rdrpcatch-0.0.3.dist-info → rdrpcatch-0.0.5.dist-info}/RECORD

@@ -1,19 +1,19 @@
 rdrpcatch/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-rdrpcatch/rdrpcatch_wrapper.py,sha256=skWDoNCTEKc_7eA6HjBIGe8jk-J1xnzU-zyOzCiA_jo,30525
+rdrpcatch/rdrpcatch_wrapper.py,sha256=bZ5w4NuTlCSUsCx9baEtJSk7jGiyp-6XthO80IKaMXI,30564
 rdrpcatch/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 rdrpcatch/cli/args.py,sha256=2E2gXY42hNasUP94HmPxpgVCA1glk_oN7D5ftbu6W2c,15805
 rdrpcatch/rdrpcatch_scripts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 rdrpcatch/rdrpcatch_scripts/fetch_dbs.py,sha256=e9ShColfLgBvWSZpGOvY3zKhEgIg3rw1IIV__KX7N-g,11054
-rdrpcatch/rdrpcatch_scripts/format_pyhmmer_out.py,sha256=uah2XPrGNkkeptCv_WWBz_qTn5AtDTfVm6XjbCmNO00,25033
+rdrpcatch/rdrpcatch_scripts/format_pyhmmer_out.py,sha256=2_ERXFQK2lpVReWl0jwQdnKIObv_zq07uFJOzGsTHlo,25025
 rdrpcatch/rdrpcatch_scripts/gui.py,sha256=he8kx_4VJWB7SVv9XSQPk0DmkOjEFIg-uGMAtDp3t-w,10576
 rdrpcatch/rdrpcatch_scripts/mmseqs_tax.py,sha256=bwzuCxu8nHQ5OC0Yr5Lyvhcyk9OWjuamInqe0T0lc38,3809
 rdrpcatch/rdrpcatch_scripts/paths.py,sha256=roTZ2QPF4Fii7jtHkS9I6INJg1Vu78Dc_ieQGKjOCP4,4710
 rdrpcatch/rdrpcatch_scripts/plot.py,sha256=Y1mZL7rkKHFKEs2D7T2Qj2kpfiORmFwRLq1LYWqwcJI,5938
 rdrpcatch/rdrpcatch_scripts/run_pyhmmer.py,sha256=9zcMzaIwQ4_-NgYzG9kejxOBaDi-gbzaqpvZti8ZXA4,9008
 rdrpcatch/rdrpcatch_scripts/run_seqkit.py,sha256=5y7DtJ6NLa4sRoBQOcjBfczKlqG_LibNrEqNmKLrHu0,4361
-rdrpcatch/rdrpcatch_scripts/utils.py,sha256=Wx1GXhAPBfJw7x67sOu7WclZzMo0N3O-hxNYTVxc3v4,16780
-rdrpcatch-0.0.3.dist-info/METADATA,sha256=8tUKJfUQb2uEdha9EQuhI1OyEjXnWD4byUM6lzFBlZE,14000
-rdrpcatch-0.0.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-rdrpcatch-0.0.3.dist-info/entry_points.txt,sha256=uiyoPO41jNz_KVOt2JdPak9NbVei-D8WQ6saMeMBFpE,53
-rdrpcatch-0.0.3.dist-info/licenses/LICENSE,sha256=3jm5vKRMIaiETEFfNN34-oyWUShxZtmDmL38PNAwlUI,1120
-rdrpcatch-0.0.3.dist-info/RECORD,,
+rdrpcatch/rdrpcatch_scripts/utils.py,sha256=jvpyPxchAMn6BeLV7HOFECSY_a3nbkxDBBL8tunmM8A,16938
+rdrpcatch-0.0.5.dist-info/METADATA,sha256=X3wolDh_nUrk7caPG4jFMvsF7FHZCvYuGzjPLZnC4VA,14004
+rdrpcatch-0.0.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+rdrpcatch-0.0.5.dist-info/entry_points.txt,sha256=uiyoPO41jNz_KVOt2JdPak9NbVei-D8WQ6saMeMBFpE,53
+rdrpcatch-0.0.5.dist-info/licenses/LICENSE,sha256=3jm5vKRMIaiETEFfNN34-oyWUShxZtmDmL38PNAwlUI,1120
+rdrpcatch-0.0.5.dist-info/RECORD,,