rdrpcatch 0.0.1.post1__py3-none-any.whl → 0.0.3__py3-none-any.whl

rdrpcatch/rdrpcatch_scripts/format_pyhmmer_out.py

@@ -491,11 +491,10 @@ class hmmsearch_output_writter:
         :rtype: list
         """
         # Convert the path to use combined.tsv instead of rdrpcatch_output.tsv
-        combined_file = str(Path(rdrpcatch_out).parent / Path(rdrpcatch_out))
         if self.logger:
-            self.logger.silent_log(f"Reading coordinates from {combined_file}")
+            self.logger.silent_log(f"Reading coordinates from {rdrpcatch_out}")
         
-        df = pl.read_csv(combined_file, separator='\t')
+        df = pl.read_csv(rdrpcatch_out, separator='\t')
         if self.logger:
             self.logger.silent_log(f"Found {len(df)} rows in combined file")
             self.logger.silent_log(f"Column names: {df.columns}")

rdrpcatch/rdrpcatch_scripts/paths.py

@@ -139,7 +139,7 @@ class rdrpcatch_output:
         return self.fasta_output_dir / f"{self.prefix}_full_aminoacid_contigs.fasta"
 
     @property
-    def rdrpcatch_output(self):
+    def rdrpcatch_output_tsv(self):
         return self.tsv_outdir / f"{self.prefix}_rdrpcatch_output.tsv"
 
     @property

rdrpcatch/rdrpcatch_wrapper.py

@@ -423,8 +423,8 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
         if not os.path.exists(outputs.gff_output_dir):
             outputs.gff_output_dir.mkdir(parents=True)
         hmm_writer = format_pyhmmer_out.hmmsearch_output_writter(logger)
-        hmm_writer.write_hmmsearch_hits(outputs.combined_tsv_path, seq_type, outputs.rdrpcatch_output, outputs.gff_output_path)
-        rdrp_coords_list = hmm_writer.get_rdrp_coords(outputs.rdrpcatch_output,seq_type)
+        hmm_writer.write_hmmsearch_hits(outputs.combined_tsv_path, seq_type, outputs.rdrpcatch_output_tsv, outputs.gff_output_path)
+        rdrp_coords_list = hmm_writer.get_rdrp_coords(outputs.rdrpcatch_output_tsv,seq_type)
         utils.fasta(outputs.seqkit_translate_output_path, logger).write_fasta_coords(rdrp_coords_list,outputs.fasta_trimmed_out_path, seq_type)
 
         if verbose:
@@ -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':
@@ -589,8 +589,8 @@ def run_scan(input_file, output_dir, db_options, db_dir, seq_type, verbose, e,in
             outputs.gff_output_dir.mkdir(parents=True)
 
         hmm_writer = format_pyhmmer_out.hmmsearch_output_writter(logger)
-        hmm_writer.write_hmmsearch_hits(outputs.combined_tsv_path, seq_type, outputs.rdrpcatch_output, outputs.gff_output_path)
-        rdrp_coords_list = hmm_writer.get_rdrp_coords(outputs.rdrpcatch_output,seq_type)
+        hmm_writer.write_hmmsearch_hits(outputs.combined_tsv_path, seq_type, outputs.rdrpcatch_output_tsv, outputs.gff_output_path)
+        rdrp_coords_list = hmm_writer.get_rdrp_coords(outputs.rdrpcatch_output_tsv,seq_type)
         utils.fasta(input_file, logger).write_fasta_coords(rdrp_coords_list,outputs.fasta_trimmed_out_path, seq_type)
 
         if verbose:
@@ -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-0.0.1.post1.dist-info → rdrpcatch-0.0.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdrpcatch
-Version: 0.0.1.post1
+Version: 0.0.3
 Dynamic: Summary
 Project-URL: Home, https://github.com/dimitris-karapliafis/RdRpCATCH
 Project-URL: Source, https://github.com/dimitris-karapliafis/RdRpCATCH
@@ -38,7 +38,7 @@ that were positive for each sequence across all pHMM databases, and taxonomic in
 
 ![rdrpcatch_flowchart_v0.png](images%2Frdrpcatch_flowchart_v0.png)
 
-Supported databases
+### Supported databases
 - NeoRdRp <sup>1</sup> : 1182 pHMMs 
 - NeoRdRp2 <sup>2</sup>: 19394 pHMMs  
 - RVMT <sup>3</sup>: 710 pHMMs  
@@ -83,7 +83,7 @@ Create a new conda environment and install the dependencies:
 ```bash
 conda create -n rdrpcatch python=3.12
 conda activate rdrpcatch
-conda install -c bioconda mmseqs2==17.17.b804f seqkit==2.10.0
+conda install -c bioconda mmseqs2==17.b804f seqkit==2.10.0
 ```
 Install the tool from pip:
 ```bash
@@ -98,7 +98,8 @@ rdrpcatch download --destination_dir path/to/store/databases
 ```
 
 * Note 1: The databases are large files and may take some time to download (~ 3 GB).
-* Note 2: The databases are stored in the specified directory, and the path is required to run RdRpCATCH. 
+* Note 2: The databases are stored in the specified directory, and the path is required to run RdRpCATCH.
+* Note 3: If you encounter an SSL error while downloading, please try again. The error seems to appear sporadically during testing, and a simple re-initiation of the downloading process seems to fix it. 
 
 ## Usage
 RdRpCATCH can be used as a CLI tool as follows:
@@ -163,7 +164,7 @@ rdrpcatch scan will create a folder with the following structure:
 | `{prefix}_rdrpcatch_fasta` | A directory containing the sequences that were identified as RdRp sequences. |
 | `{prefix}_rdrpcatch_plots` | A directory containing the plots generated during the analysis.              |
 | `{prefix}_gff_files` | A directory containing the GFF files generated during the analysis. (For now only based on protein sequences) |
-| `tmp` | A directory containing temporary files generated during the analysis. (Only available if the -keep_tmp flag is used |
+| `tmp` | A directory containing temporary files generated during the analysis. (Only available if the -keep_tmp flag is used )|
 
 #### Output table fields
 A summary of the results is stored in the `{prefix}_rdrpcatch_output_annotated.tsv` file, which contains the following fields:
@@ -194,10 +195,10 @@ A summary of the results is stored in the `{prefix}_rdrpcatch_output_annotated.t
 ## Citations
 Manuscript still in preparation. If you use RdRpCATCH, please cite this GitHub repository 
 A precompiled version of the used databases is available at Zenodo DOI: [10.5281/zenodo.14358348](https://doi.org/10.5281/zenodo.14358348).  
-If you use RdRpCATCH, please cite the following third party databases:
+If you use RdRpCATCH, please cite the [underlying third party databases](#supported-databases) :
 
 ## Acknowledgements
-RdRpCATCH is a collaborative effort and we would like to thank all the authors and developers of the underling databases. 
+RdRpCATCH is a collaborative effort and we would like to thank all the authors and developers of the underlying databases. 
 
 ## Contact
 Dimitris Karapliafis (dimitris.karapliafis@wur.nl), potentially via slack/teams or an issue in the main repo.

{rdrpcatch-0.0.1.post1.dist-info → rdrpcatch-0.0.3.dist-info}/RECORD

@@ -1,19 +1,19 @@
 rdrpcatch/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-rdrpcatch/rdrpcatch_wrapper.py,sha256=PLj8KSJ2wbXVKlGhCaQEhGgoFBOMXBKQS9DnukHOgAs,30501
+rdrpcatch/rdrpcatch_wrapper.py,sha256=skWDoNCTEKc_7eA6HjBIGe8jk-J1xnzU-zyOzCiA_jo,30525
 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=w4I_7W-fvuT4JmKvZmbJ07Dewm3CBQuQmpMvQutdOqo,25112
+rdrpcatch/rdrpcatch_scripts/format_pyhmmer_out.py,sha256=uah2XPrGNkkeptCv_WWBz_qTn5AtDTfVm6XjbCmNO00,25033
 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=Nq08P8GGPKPrzX6u4wQ2Xwn-kQP-pue_yOGMuRjrLdY,4706
+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-0.0.1.post1.dist-info/METADATA,sha256=u56mpzcXGlFbZN3Gxx7fmF6KhgT6usc9HGM0xDi2N9Q,13774
-rdrpcatch-0.0.1.post1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-rdrpcatch-0.0.1.post1.dist-info/entry_points.txt,sha256=uiyoPO41jNz_KVOt2JdPak9NbVei-D8WQ6saMeMBFpE,53
-rdrpcatch-0.0.1.post1.dist-info/licenses/LICENSE,sha256=3jm5vKRMIaiETEFfNN34-oyWUShxZtmDmL38PNAwlUI,1120
-rdrpcatch-0.0.1.post1.dist-info/RECORD,,
+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,,