rdrpcatch 0.0.2__py3-none-any.whl → 0.0.4__py3-none-any.whl

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

@@ -458,7 +458,7 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
                           outputs.mmseqs_e_search_output_path, 7, cpus, outputs.mmseqs_e_search_log_path).run_mmseqs_e_search()
 
         utils.mmseqs_parser(outputs.mmseqs_tax_output_lca_path, outputs.mmseqs_e_search_output_path).tax_to_rdrpcatch(
-            outputs.rdrpcatch_output, outputs.extended_rdrpcatch_output, seq_type)
+            outputs.rdrpcatch_output_tsv, outputs.extended_rdrpcatch_output, seq_type)
 
 
     elif seq_type == 'prot':
@@ -581,9 +581,9 @@ 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 +594,9 @@ 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)
@@ -622,7 +622,7 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
                           outputs.mmseqs_e_search_output_path, 7, cpus, outputs.mmseqs_e_search_log_path).run_mmseqs_e_search()
 
         utils.mmseqs_parser(outputs.mmseqs_tax_output_lca_path, outputs.mmseqs_e_search_output_path).tax_to_rdrpcatch(
-            outputs.rdrpcatch_output, outputs.extended_rdrpcatch_output, seq_type)
+            outputs.rdrpcatch_output_tsv, outputs.extended_rdrpcatch_output, seq_type)
 
 
     end_time = logger.stop_timer(start_time, verbose)

{rdrpcatch-0.0.2.dist-info → rdrpcatch-0.0.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdrpcatch
-Version: 0.0.2
+Version: 0.0.4
 Dynamic: Summary
 Project-URL: Home, https://github.com/dimitris-karapliafis/RdRpCATCH
 Project-URL: Source, https://github.com/dimitris-karapliafis/RdRpCATCH

{rdrpcatch-0.0.2.dist-info → rdrpcatch-0.0.4.dist-info}/RECORD

@@ -1,5 +1,5 @@
 rdrpcatch/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-rdrpcatch/rdrpcatch_wrapper.py,sha256=HrC2IqxLYFTroJwH1gDcU1QQU0gzs4YfBDzIN64Zc0A,30517
+rdrpcatch/rdrpcatch_wrapper.py,sha256=PUMzQ3tIU0VuBY6XrRXupo-NruszwHreyxWXzEARjM4,30550
 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
@@ -11,9 +11,9 @@ rdrpcatch/rdrpcatch_scripts/paths.py,sha256=roTZ2QPF4Fii7jtHkS9I6INJg1Vu78Dc_ieQ
 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-0.0.2.dist-info/METADATA,sha256=JtS1E35XYcWSNu98shFxcpirpz021Ja4pxjjx0Izyz0,14000
-rdrpcatch-0.0.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-rdrpcatch-0.0.2.dist-info/entry_points.txt,sha256=uiyoPO41jNz_KVOt2JdPak9NbVei-D8WQ6saMeMBFpE,53
-rdrpcatch-0.0.2.dist-info/licenses/LICENSE,sha256=3jm5vKRMIaiETEFfNN34-oyWUShxZtmDmL38PNAwlUI,1120
-rdrpcatch-0.0.2.dist-info/RECORD,,
+rdrpcatch/rdrpcatch_scripts/utils.py,sha256=jvpyPxchAMn6BeLV7HOFECSY_a3nbkxDBBL8tunmM8A,16938
+rdrpcatch-0.0.4.dist-info/METADATA,sha256=rhb3kvfpy5zj9dUgIB1MbRfv9NNPZeQlOS1YDB7ZkrA,14000
+rdrpcatch-0.0.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+rdrpcatch-0.0.4.dist-info/entry_points.txt,sha256=uiyoPO41jNz_KVOt2JdPak9NbVei-D8WQ6saMeMBFpE,53
+rdrpcatch-0.0.4.dist-info/licenses/LICENSE,sha256=3jm5vKRMIaiETEFfNN34-oyWUShxZtmDmL38PNAwlUI,1120
+rdrpcatch-0.0.4.dist-info/RECORD,,