rdrpcatch 0.0.5__py3-none-any.whl → 0.0.6__py3-none-any.whl

rdrpcatch/cli/args.py

@@ -115,30 +115,30 @@ def cli():
 @click.option('-gen_code', '--gen_code',
               type=click.INT,
               default=1,
-              help='Genetic code to use for translation. (default: 1) Possible genetic codes (supported by seqkit translate) :      1: The Standard Code       \n'
-                     '2: The Vertebrate Mitochondrial Code      \n'
-                     '3: The Yeast Mitochondrial Code       \n'
-                     '4: The Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code        \n'
-                     '5: The Invertebrate Mitochondrial Code        \n'
-                     '6: The Ciliate, Dasycladacean and Hexamita Nuclear Code       \n'
-                     '9: The Echinoderm and Flatworm Mitochondrial Code     \n'
-                    '10: The Euplotid Nuclear Code      \n'
-                    '11: The Bacterial, Archaeal and Plant Plastid Code     \n'
-                    '12: The Alternative Yeast Nuclear Code     \n'
-                    '13: The Ascidian Mitochondrial Code        \n'
-                    '14: The Alternative Flatworm Mitochondrial Code        \n'
-                    '16: Chlorophycean Mitochondrial Code       \n'
-                    '21: Trematode Mitochondrial Code       \n'
-                    '22: Scenedesmus obliquus Mitochondrial Code        \n'
-                    '23: Thraustochytrium Mitochondrial Code        \n'
-                    '24: Pterobranchia Mitochondrial Code       \n'
-                    '25: Candidate Division SR1 and Gracilibacteria Code        \n'
-                    '26: Pachysolen tannophilus Nuclear Code        \n'
-                    '27: Karyorelict Nuclear        \n'
-                    '28: Condylostoma Nuclear       \n'
-                    '29: Mesodinium Nuclear     \n'
-                    '30: Peritrich Nuclear      \n'
-                    '31: Blastocrithidia Nuclear        \n')
+              help='Genetic code to use for translation. (default: 1) Possible genetic codes (supported by seqkit translate) : 1: The Standard Code, '
+                     '2: The Vertebrate Mitochondrial Code, '
+                     '3: The Yeast Mitochondrial Code, '
+                     '4: The Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code, '
+                     '5: The Invertebrate Mitochondrial Code, '
+                     '6: The Ciliate, Dasycladacean and Hexamita Nuclear Code, '
+                     '9: The Echinoderm and Flatworm Mitochondrial Code, '
+                    '10: The Euplotid Nuclear Code, '
+                    '11: The Bacterial, Archaeal and Plant Plastid Code, '
+                    '12: The Alternative Yeast Nuclear Code, '
+                    '13: The Ascidian Mitochondrial Code, '
+                    '14: The Alternative Flatworm Mitochondrial Code, '
+                    '16: Chlorophycean Mitochondrial Code, '
+                    '21: Trematode Mitochondrial Code, '
+                    '22: Scenedesmus obliquus Mitochondrial Code, '
+                    '23: Thraustochytrium Mitochondrial Code, '
+                    '24: Pterobranchia Mitochondrial Code, '
+                    '25: Candidate Division SR1 and Gracilibacteria Code, '
+                    '26: Pachysolen tannophilus Nuclear Code, '
+                    '27: Karyorelict Nuclear, '
+                    '28: Condylostoma Nuclear, '
+                    '29: Mesodinium Nuclear, '
+                    '30: Peritrich Nuclear, '
+                    '31: Blastocrithidia Nuclear, ')
 @click.option('-bundle', '--bundle',
               is_flag=True,
               default=False,
@@ -147,9 +147,14 @@ def cli():
               is_flag=True,
               default=False,
               help="Keep temporary files (Expert users) (default: False)")
+@click.option('-overwrite', '--overwrite',
+              is_flag=True,
+              default=False,
+              help="Force overwrite of existing output directory. (default: False)")
+
 @click.pass_context
 def scan(ctx, input, output, db_options, db_dir, custom_dbs, seq_type, verbose, evalue,
-         incevalue, domevalue, incdomevalue, zvalue, cpus, length_thr, gen_code, bundle, keep_tmp):
+         incevalue, domevalue, incdomevalue, zvalue, cpus, length_thr, gen_code, bundle, keep_tmp, overwrite):
     """Scan sequences for RdRps."""
 
     # Create a rich table for displaying parameters
@@ -175,6 +180,7 @@ def scan(ctx, input, output, db_options, db_dir, custom_dbs, seq_type, verbose,
     table.add_row("Genetic Code", str(gen_code))
     table.add_row("Bundle Output", "ON" if bundle else "OFF")
     table.add_row("Save Temporary Files", "ON" if keep_tmp else "OFF")
+    table.add_row("Force Overwrite", "ON" if overwrite else "OFF")
 
     console.print(Panel(table, title="Scan Configuration"))
 
@@ -207,7 +213,8 @@ def scan(ctx, input, output, db_options, db_dir, custom_dbs, seq_type, verbose,
         length_thr=length_thr,
         gen_code=gen_code,
         bundle=bundle,
-        keep_tmp=keep_tmp
+        keep_tmp=keep_tmp,
+        overwrite=overwrite
     )
 
 # @cli.command("download", help="Download RdRpCATCH databases.")

rdrpcatch/rdrpcatch_wrapper.py

@@ -53,7 +53,7 @@ def bundle_results(output_dir, prefix):
     
     return archive_path
 
-def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,incdomE,domE,incE,z, cpus, length_thr, gen_code, bundle, keep_tmp):
+def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,incdomE,domE,incE,z, cpus, length_thr, gen_code, bundle, keep_tmp, overwrite):
     """
     Run RdRpCATCH scan.
 
@@ -110,8 +110,16 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
     log_file = outputs.log_file
     if not os.path.exists(outputs.output_dir):
         os.makedirs(outputs.output_dir)
+    elif os.path.exists(outputs.output_dir) and overwrite:
+        # If the output directory already exists and force_overwrite is True, remove the existing directory
+        import shutil
+        shutil.rmtree(outputs.output_dir)
+        os.makedirs(outputs.output_dir)
+        outputs = paths.rdrpcatch_output(prefix, Path(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"
+                              f" or activate the -overwrite flag to overwrite the contents of the directory.")
+
     if not os.path.exists(outputs.log_dir):
         os.makedirs(outputs.log_dir)
 
@@ -160,6 +168,8 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
     if seq_type == 'prot':
         utils.fasta_checker(input_file, logger).check_seq_length(100000)
 
+    logger.loud_log("Fetching HMM databases...")
+
     ## Fetch HMM databases- RVMT, NeoRdRp, NeoRdRp.2.1, TSA_Olendraite, RDRP-scan, Lucaprot
     rvmt_hmm_db = fetch_dbs.db_fetcher(db_dir).fetch_hmm_db_path("RVMT")
     if verbose:
@@ -234,10 +244,9 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
 
     # Fetch mmseqs database
 
-    if verbose:
-        logger.loud_log("Fetching mmseqs databases.")
-    else:
-        logger.silent_log("Fetching mmseqs databases.")
+
+    logger.loud_log("Fetching Mmseqs2 databases...")
+
     mmseqs_db_path = fetch_dbs.db_fetcher(db_dir).fetch_mmseqs_db_path("mmseqs_refseq_riboviria_20250211")
 
     if verbose:
@@ -260,21 +269,17 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
     if not os.path.exists(outputs.tmp_dir):
         outputs.tmp_dir.mkdir(parents=True)
 
+    logger.loud_log("Databases fetched successfully.")
+
     if seq_type == 'nuc':
-        if verbose:
-            logger.loud_log("Nucleotide sequence detected.")
-        else:
-            logger.silent_log("Nucleotide sequence detected.")
+        logger.loud_log("Nucleotide sequence detected.")
 
         set_dict = {}
         translated_set_dict = {}
         df_list = []
 
         ## Filter out sequences with length less than 400 bp with seqkit
-        if verbose:
-            logger.loud_log("Filtering out sequences with length less than 400 bp.")
-        else:
-            logger.silent_log("Filtering out sequences with length less than 400 bp.")
+        logger.loud_log("Filtering out sequences with length less than 400 bp.")
 
         if not os.path.exists(outputs.seqkit_seq_output_dir):
             outputs.seqkit_seq_output_dir.mkdir(parents=True)
@@ -286,10 +291,7 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
             logger.silent_log(f"Filtered sequence written to: { outputs.seqkit_seq_output_path}")
 
         ## Translate nucleotide sequences to protein sequences with seqkit
-        if verbose:
-            logger.loud_log("Translating nucleotide sequences to protein sequences.")
-        else:
-            logger.silent_log("Translating nucleotide sequences to protein sequences.")
+        logger.loud_log("Translating nucleotide sequences to protein sequences.")
 
         if not os.path.exists(outputs.seqkit_translate_output_dir):
             outputs.seqkit_translate_output_dir.mkdir(parents=True)
@@ -302,6 +304,7 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
             logger.silent_log(f"Translated sequence written to: {outputs.seqkit_translate_output_path}")
 
         for db_name,db_path in zip(db_name_list, db_path_list):
+            logger.loud_log(f"Running HMMsearch for {db_name} database.")
 
             if verbose:
                 logger.loud_log(f"HMM output path: {outputs.hmm_output_path(db_name)}")
@@ -353,7 +356,9 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
             ])
             df_list.append(df)
 
+            logger.loud_log(f"HMMsearch for {db_name} completed.")
 
+        logger.loud_log("HMMsearch completed.")
 
         if not os.path.exists(outputs.plot_outdir):
             outputs.plot_outdir.mkdir(parents=True)
@@ -361,6 +366,7 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
         if not os.path.exists(outputs.tsv_outdir):
             outputs.tsv_outdir.mkdir(parents=True)
 
+        logger.loud_log("Consolidating results.")
 
         # Combine all the dataframes in the list
         combined_df = pl.concat(df_list, how='vertical_relaxed')
@@ -379,6 +385,8 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
             logger.loud_log("No hits found by RdRpCATCH. Exiting.")
             return None
 
+        # Generate upset plot
+        logger.loud_log("Generating plots.")
 
         if len(db_name_list) > 1:
             if verbose:
@@ -411,6 +419,8 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
         combined_set = set.union(*[value for value in set_dict.values()])
         translated_combined_set = set.union(*[value for value in translated_set_dict.values()])
 
+        logger.loud_log("Extracting RdRp contigs from the input file.")
+
         # Write a fasta file with all the contigs
         if not os.path.exists(outputs.fasta_output_dir):
             outputs.fasta_output_dir.mkdir(parents=True)
@@ -430,25 +440,21 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
         if verbose:
             logger.loud_log(f"Contigs written to: {outputs.fasta_nuc_out_path}")
             logger.loud_log(f"Translated contigs 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"Contigs written to: {outputs.fasta_nuc_out_path}")
             logger.silent_log(f"Translated contigs 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)
 
-        if verbose:
-            logger.loud_log("Running mmseqs easy-taxonomy for taxonomic annotation.")
-        else:
-            logger.silent_log("Running mmseqs easy-taxonomy for taxonomic annotation.")
+        logger.loud_log("Running mmseqs easy-taxonomy for taxonomic annotation.")
 
         mmseqs_tax.mmseqs(outputs.fasta_prot_out_path, mmseqs_db_path, outputs.mmseqs_tax_output_prefix,
                           outputs.mmseqs_tax_output_dir, 7, cpus, outputs.mmseqs_tax_log_path).run_mmseqs_easy_tax_lca()
 
-        if verbose:
-            logger.loud_log("Running mmseqs easy-search for taxonomic annotation.")
-        else:
-            logger.silent_log("Running mmseqs easy-search for taxonomic annotation.")
+        logger.loud_log("Running mmseqs easy-search for taxonomic annotation.")
 
         if not os.path.exists(outputs.mmseqs_e_search_output_dir):
             outputs.mmseqs_e_search_output_dir.mkdir(parents=True)
@@ -460,18 +466,17 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
         utils.mmseqs_parser(outputs.mmseqs_tax_output_lca_path, outputs.mmseqs_e_search_output_path).tax_to_rdrpcatch(
             outputs.rdrpcatch_output_tsv, outputs.extended_rdrpcatch_output, seq_type)
 
+        logger.loud_log("Taxonomic annotation completed.")
 
     elif seq_type == 'prot':
 
-        if verbose:
-            logger.loud_log("Protein sequence detected.")
-        else:
-            logger.silent_log("Protein sequence detected.")
+        logger.loud_log("Protein sequence detected.")
 
         set_dict = {}
         df_list = []
 
         for db_name,db_path in zip (db_name_list, db_path_list):
+            logger.loud_log(f"Running HMMsearch for {db_name} database.")
 
             if verbose:
                 logger.loud_log(f"HMM output path: {outputs.hmm_output_path(db_name)}")
@@ -519,12 +524,17 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
             ])
             df_list.append(df)
 
+            logger.loud_log(f"HMMsearch for {db_name} completed.")
+
+        logger.loud_log("HMMsearch completed.")
+
         if not os.path.exists(outputs.plot_outdir):
             outputs.plot_outdir.mkdir(parents=True)
 
         if not os.path.exists(outputs.tsv_outdir):
             outputs.tsv_outdir.mkdir(parents=True)
 
+        logger.loud_log("Consolidating results.")
 
         # Combine all the dataframes in the list
         combined_df = pl.concat(df_list, how='vertical_relaxed')
@@ -542,6 +552,9 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
             logger.loud_log("No hits found by RdRpCATCH. Exiting.")
             return None
 
+        # Generate upset plot
+        logger.loud_log("Generating plots.")
+
         if len(db_name_list) > 1:
             if verbose:
                 logger.loud_log("Generating upset plot.")
@@ -574,6 +587,9 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
         # Extract all the contigs
         combined_set = set.union(*[value for value in set_dict.values()])
         # Write a fasta file with all the contigs
+
+        logger.loud_log("Extracting RdRp contigs from the input file.")
+
         if not os.path.exists(outputs.fasta_output_dir):
             outputs.fasta_output_dir.mkdir(parents=True)
 
@@ -600,11 +616,7 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
         if not os.path.exists(outputs.mmseqs_tax_output_dir):
             outputs.mmseqs_tax_output_dir.mkdir(parents=True)
 
-        if verbose:
-            logger.loud_log("Running mmseqs easy-taxonomy for taxonomic annotation.")
-        else:
-            logger.silent_log("Running mmseqs easy-taxonomy for taxonomic annotation.")
-
+        logger.loud_log("Running mmseqs easy-taxonomy for taxonomic annotation.")
 
         mmseqs_tax.mmseqs(outputs.fasta_prot_out_path, mmseqs_db_path, outputs.mmseqs_tax_output_prefix,
                           outputs.mmseqs_tax_output_dir, 7, cpus, outputs.mmseqs_tax_log_path).run_mmseqs_easy_tax_lca()
@@ -612,10 +624,7 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
         if not os.path.exists(outputs.mmseqs_e_search_output_dir):
             outputs.mmseqs_e_search_output_dir.mkdir(parents=True)
 
-        if verbose:
-            logger.loud_log("Running mmseqs easy-search for taxonomic annotation.")
-        else:
-            logger.silent_log("Running mmseqs easy-search for taxonomic annotation.")
+        logger.loud_log("Running mmseqs easy-search for taxonomic annotation.")
 
         mmseqs_tax.mmseqs(outputs.fasta_prot_out_path, mmseqs_db_path, outputs.mmseqs_e_search_output_dir,
                           outputs.mmseqs_e_search_output_path, 7, cpus, outputs.mmseqs_e_search_log_path).run_mmseqs_e_search()
@@ -624,11 +633,7 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
             outputs.rdrpcatch_output_tsv, outputs.extended_rdrpcatch_output, seq_type)
 
 
-    end_time = logger.stop_timer(start_time, verbose)
-    if verbose:
-        logger.loud_log(f"Total Runtime: {end_time}")
-    else:
-        logger.silent_log(f"Total Runtime: {end_time}")
+
 
 
 
@@ -657,6 +662,11 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
         else:
             logger.silent_log(f"Results bundled into: {archive_path}")
 
+    end_time = logger.stop_timer(start_time, verbose)
+
+    logger.loud_log(f"Total Runtime: {end_time}")
+
+    logger.loud_log("RdRpCATCH completed successfully.")
 
 
     return outputs.extended_rdrpcatch_output

{rdrpcatch-0.0.5.dist-info → rdrpcatch-0.0.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdrpcatch
-Version: 0.0.5
+Version: 0.0.6
 Dynamic: Summary
 Project-URL: Home, https://github.com/dimitris-karapliafis/RdRpCATCH
 Project-URL: Source, https://github.com/dimitris-karapliafis/RdRpCATCH
@@ -205,7 +205,6 @@ Dimitris Karapliafis (dimitris.karapliafis@wur.nl), potentially via slack/teams
 
 ##TODO:
 - [ ] loud logging is linking to the utils.py file, not the actual line of code causing the error.
-- [ ] Add `overwrite` flag
 - [ ] drop `db_dir` argument and use global/environment/config variable that is set after running the `download` command
 
 

{rdrpcatch-0.0.5.dist-info → rdrpcatch-0.0.6.dist-info}/RECORD

@@ -1,7 +1,7 @@
 rdrpcatch/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-rdrpcatch/rdrpcatch_wrapper.py,sha256=bZ5w4NuTlCSUsCx9baEtJSk7jGiyp-6XthO80IKaMXI,30564
+rdrpcatch/rdrpcatch_wrapper.py,sha256=75jXdh9rUbo5ypISmfl1e9kLtk6mxg6ivPwLI3slH-U,31106
 rdrpcatch/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-rdrpcatch/cli/args.py,sha256=2E2gXY42hNasUP94HmPxpgVCA1glk_oN7D5ftbu6W2c,15805
+rdrpcatch/cli/args.py,sha256=PGU6SJeHU6B0e-r-PheUpdi5PwkDhBa_ixn7WgNmDRw,15933
 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=2_ERXFQK2lpVReWl0jwQdnKIObv_zq07uFJOzGsTHlo,25025
@@ -12,8 +12,8 @@ rdrpcatch/rdrpcatch_scripts/plot.py,sha256=Y1mZL7rkKHFKEs2D7T2Qj2kpfiORmFwRLq1LY
 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=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,,
+rdrpcatch-0.0.6.dist-info/METADATA,sha256=8HANk0HZEF3A1S9rB2wt7LG3SsI8ULMrcfIfaxWSvtc,13977
+rdrpcatch-0.0.6.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+rdrpcatch-0.0.6.dist-info/entry_points.txt,sha256=uiyoPO41jNz_KVOt2JdPak9NbVei-D8WQ6saMeMBFpE,53
+rdrpcatch-0.0.6.dist-info/licenses/LICENSE,sha256=3jm5vKRMIaiETEFfNN34-oyWUShxZtmDmL38PNAwlUI,1120
+rdrpcatch-0.0.6.dist-info/RECORD,,