rdrpcatch 0.0.8__tar.gz → 0.0.9__tar.gz

{rdrpcatch-0.0.8 → rdrpcatch-0.0.9}/.idea/workspace.xml

@@ -4,9 +4,7 @@
     <option name="autoReloadType" value="SELECTIVE" />
   </component>
   <component name="ChangeListManager">
-    <list default="true" id="d849e6fa-87f9-4e92-9c33-abef7cc975d3" name="Changes" comment="Polish README.md">
-      <change beforePath="$PROJECT_DIR$/README.md" beforeDir="false" afterPath="$PROJECT_DIR$/README.md" afterDir="false" />
-    </list>
+    <list default="true" id="d849e6fa-87f9-4e92-9c33-abef7cc975d3" name="Changes" comment="Bug fixes" />
     <option name="SHOW_DIALOG" value="false" />
     <option name="HIGHLIGHT_CONFLICTS" value="true" />
     <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
@@ -44,7 +42,7 @@
     &quot;RunOnceActivity.OpenProjectViewOnStart&quot;: &quot;true&quot;,
     &quot;RunOnceActivity.ShowReadmeOnStart&quot;: &quot;true&quot;,
     &quot;ignore.virus.scanning.warn.message&quot;: &quot;true&quot;,
-    &quot;last_opened_file_path&quot;: &quot;C:/Users/karso/PycharmProjects/testing_approaches&quot;,
+    &quot;last_opened_file_path&quot;: &quot;C:/Users/karso/PycharmProjects/bioconda_recipes&quot;,
     &quot;node.js.detected.package.eslint&quot;: &quot;true&quot;,
     &quot;node.js.detected.package.tslint&quot;: &quot;true&quot;,
     &quot;node.js.selected.package.eslint&quot;: &quot;(autodetect)&quot;,
@@ -129,7 +127,13 @@
       <workItem from="1750247217114" duration="128000" />
       <workItem from="1750854909876" duration="599000" />
       <workItem from="1751007640706" duration="596000" />
-      <workItem from="1751535404721" duration="16934000" />
+      <workItem from="1751535404721" duration="19179000" />
+      <workItem from="1751979275998" duration="99000" />
+      <workItem from="1752554982335" duration="3354000" />
+      <workItem from="1752590986032" duration="642000" />
+      <workItem from="1753197756503" duration="3070000" />
+      <workItem from="1755379572482" duration="1765000" />
+      <workItem from="1770303390426" duration="217000" />
     </task>
     <task id="LOCAL-00001" summary="First commit: Script for benchmark">
       <option name="closed" value="true" />
@@ -419,7 +423,31 @@
       <option name="project" value="LOCAL" />
       <updated>1751587669980</updated>
     </task>
-    <option name="localTasksCounter" value="37" />
+    <task id="LOCAL-00037" summary="Polish meta.yml">
+      <option name="closed" value="true" />
+      <created>1751623835098</created>
+      <option name="number" value="00037" />
+      <option name="presentableId" value="LOCAL-00037" />
+      <option name="project" value="LOCAL" />
+      <updated>1751623835098</updated>
+    </task>
+    <task id="LOCAL-00038" summary="Update rdrpcatch to version 0.0.8">
+      <option name="closed" value="true" />
+      <created>1751625641622</created>
+      <option name="number" value="00038" />
+      <option name="presentableId" value="LOCAL-00038" />
+      <option name="project" value="LOCAL" />
+      <updated>1751625641622</updated>
+    </task>
+    <task id="LOCAL-00039" summary="Bug fixes">
+      <option name="closed" value="true" />
+      <created>1755380495287</created>
+      <option name="number" value="00039" />
+      <option name="presentableId" value="LOCAL-00039" />
+      <option name="project" value="LOCAL" />
+      <updated>1755380495287</updated>
+    </task>
+    <option name="localTasksCounter" value="40" />
     <servers />
   </component>
   <component name="TypeScriptGeneratedFilesManager">
@@ -437,9 +465,6 @@
     </option>
   </component>
   <component name="VcsManagerConfiguration">
-    <MESSAGE value="Script progress:&#10;GUI implementation with tkinter&#10;Summarised ColabScan output added&#10;Improvement of command line arguments&#10;General fixes" />
-    <MESSAGE value="Script progress:&#10;Reimplementation of argument parsing to support 3 modes: Scan, Download and GUI&#10;Implementation of runtime calculation&#10;Rename seqkit.py to run_seqkit.py" />
-    <MESSAGE value="Script progress:&#10;Introduce test for Fasta seq length to avoid crushing pyHMMER&#10;Add RdRp coordinates to output and Fasta file (only for aminoacid sequences)&#10;Correction of scores calculation for coverage &#10;Fix scaling of e-value plot (converted to log-scale)&#10;Introduce saving intermidiate files to tmp directory" />
     <MESSAGE value="Major refactoring&#10;Formatted as a conda package&#10;Removal of redundant files and directories&#10;Addition of annotation via mmseqs easy-taxonomy and mmseqs easy-search&#10;Tidy up output directories&#10;Addition of requirements.txt and" />
     <MESSAGE value="Major refactoring&#10;Formatted as a conda package&#10;Removal of redundant files and directories&#10;Addition of annotation via mmseqs easy-taxonomy and mmseqs easy-search&#10;Tidy up output directories&#10;Addition of requirements.txt and conda .yaml file for dependencies" />
     <MESSAGE value="Updates:&#10;Drop GUI&#10;Minor fixes" />
@@ -462,6 +487,9 @@
     <MESSAGE value="Updates:&#10;Update .toml" />
     <MESSAGE value="Updates:&#10;&#10;&#10;Command line argument parsing without underscore characters&#10;&#10;Module download renamed to databases&#10;&#10;Implementation of integration of custom databases&#10;&#10;Fixed bug with reading the directories of Lucaprot_HMM and Zayed_HMM&#10;&#10;Update .toml" />
     <MESSAGE value="Polish README.md" />
-    <option name="LAST_COMMIT_MESSAGE" value="Polish README.md" />
+    <MESSAGE value="Polish meta.yml" />
+    <MESSAGE value="Update rdrpcatch to version 0.0.8" />
+    <MESSAGE value="Bug fixes" />
+    <option name="LAST_COMMIT_MESSAGE" value="Bug fixes" />
   </component>
 </project>

{rdrpcatch-0.0.8 → rdrpcatch-0.0.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdrpcatch
-Version: 0.0.8
+Version: 0.0.9
 Dynamic: Summary
 Project-URL: Home, https://github.com/dimitris-karapliafis/RdRpCATCH
 Project-URL: Source, https://github.com/dimitris-karapliafis/RdRpCATCH
@@ -109,16 +109,18 @@ Activate the environment and download the RdRpCATCH databases:
 
 ```bash 
 conda activate rdrpcatch
-rdrpcatch databases --destination_dir path/to/store/databases
+rdrpcatch databases --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 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. 
-
-
-
-
+* Note 4: If the SSL error persists, or there is any other error related to downloading the databases, please let us know by raising an issue. In this case, you can download the pre-compiled databases manually via the zenodo repository  
+[10.5281/zenodo.15463729](https://doi.org/10.5281/zenodo.15463729) Save the repository to a local directory of your preferance, and then use the following command:
+```bash 
+tar -xvf rdrpcatch_dbs.tar
+```
+  
 ## Usage
 RdRpCATCH can be used as a CLI tool as follows:
 
@@ -133,7 +135,7 @@ rdrpcatch scan -i path/to/input.fasta -o path/to/output_dir -db-dir path/to/data
 ## Input description
 The input file can be one or more nucleotide or protein sequences in multi-fasta format. 
 The output directory is where the results will be stored. We recommend specifying the type of the sequence in the command line,
-An optional argument `--seq_type` (nuc or prot) can be used to specify if the input fasta file sequences are nucleotide or amino acid.
+An optional argument `--seq-type` (nuc or prot) can be used to specify if the input fasta file sequences are nucleotide or amino acid.
 
 
 ## Setting up custom pHMM databases
@@ -154,7 +156,7 @@ rdrpcatch databases --add-custom-db path/to/my_custom_rdrp_database --destinatio
 - The custom database can then be used with the `rdrpcatch scan` command by specifying the `--custom-dbs` argument as follows:
 - 
 ```bash
-rdrpcatch scan -i path/to/input.fasta -o path/to/output_dir -db_dir path/to/database --custom-dbs custom_database_name
+rdrpcatch scan -i path/to/input.fasta -o path/to/output_dir -db-dir path/to/database --custom-dbs custom_database_name
 ```
 
 - The `custom_database_name` should be the name of the directory that contains the custom pHMM files, without the path.
@@ -164,7 +166,7 @@ rdrpcatch scan -i path/to/input.fasta -o path/to/output_dir -db_dir path/to/data
 - For example, if you want to use the NeoRdRp and RVMT databases along with your custom database, you would use the following command:
 
 ```bash
-rdrpcatch scan -i path/to/input.fasta -o path/to/output_dir -db_dir path/to/database --db_options NeoRdRp,RVMT --custom-dbs my_custom_rdrp_database
+rdrpcatch scan -i path/to/input.fasta -o path/to/output_dir -db-dir path/to/database --db-options NeoRdRp,RVMT --custom-dbs my_custom_rdrp_database
 ```
 
 - Note: By default, RdRpCATCH will search against all pre-compiled databases if no `--db_options` argument is specified. If you want to use only the custom databases, you can specify `--db_options none` to avoid searching against the pre-compiled databases.

{rdrpcatch-0.0.8 → rdrpcatch-0.0.9}/README.md

@@ -87,16 +87,18 @@ Activate the environment and download the RdRpCATCH databases:
 
 ```bash 
 conda activate rdrpcatch
-rdrpcatch databases --destination_dir path/to/store/databases
+rdrpcatch databases --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 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. 
-
-
-
-
+* Note 4: If the SSL error persists, or there is any other error related to downloading the databases, please let us know by raising an issue. In this case, you can download the pre-compiled databases manually via the zenodo repository  
+[10.5281/zenodo.15463729](https://doi.org/10.5281/zenodo.15463729) Save the repository to a local directory of your preferance, and then use the following command:
+```bash 
+tar -xvf rdrpcatch_dbs.tar
+```
+  
 ## Usage
 RdRpCATCH can be used as a CLI tool as follows:
 
@@ -111,7 +113,7 @@ rdrpcatch scan -i path/to/input.fasta -o path/to/output_dir -db-dir path/to/data
 ## Input description
 The input file can be one or more nucleotide or protein sequences in multi-fasta format. 
 The output directory is where the results will be stored. We recommend specifying the type of the sequence in the command line,
-An optional argument `--seq_type` (nuc or prot) can be used to specify if the input fasta file sequences are nucleotide or amino acid.
+An optional argument `--seq-type` (nuc or prot) can be used to specify if the input fasta file sequences are nucleotide or amino acid.
 
 
 ## Setting up custom pHMM databases
@@ -132,7 +134,7 @@ rdrpcatch databases --add-custom-db path/to/my_custom_rdrp_database --destinatio
 - The custom database can then be used with the `rdrpcatch scan` command by specifying the `--custom-dbs` argument as follows:
 - 
 ```bash
-rdrpcatch scan -i path/to/input.fasta -o path/to/output_dir -db_dir path/to/database --custom-dbs custom_database_name
+rdrpcatch scan -i path/to/input.fasta -o path/to/output_dir -db-dir path/to/database --custom-dbs custom_database_name
 ```
 
 - The `custom_database_name` should be the name of the directory that contains the custom pHMM files, without the path.
@@ -142,7 +144,7 @@ rdrpcatch scan -i path/to/input.fasta -o path/to/output_dir -db_dir path/to/data
 - For example, if you want to use the NeoRdRp and RVMT databases along with your custom database, you would use the following command:
 
 ```bash
-rdrpcatch scan -i path/to/input.fasta -o path/to/output_dir -db_dir path/to/database --db_options NeoRdRp,RVMT --custom-dbs my_custom_rdrp_database
+rdrpcatch scan -i path/to/input.fasta -o path/to/output_dir -db-dir path/to/database --db-options NeoRdRp,RVMT --custom-dbs my_custom_rdrp_database
 ```
 
 - Note: By default, RdRpCATCH will search against all pre-compiled databases if no `--db_options` argument is specified. If you want to use only the custom databases, you can specify `--db_options none` to avoid searching against the pre-compiled databases.

{rdrpcatch-0.0.8 → rdrpcatch-0.0.9}/meta.yaml

@@ -1,6 +1,6 @@
 {% set name = "RdRpCATCH" %}
-{% set version = "0.0.1" %}
-{% set sha256 = "6454b1a6f98e461ca82d181b1595e5f06448786540b6daa2c4de31c38b255412" %}
+{% set version = "0.0.9" %}
+{% set sha256 = "a4e6015fbcd74df5050ac2ee94a3c2a2b2587b3d167f40742b3f2e782ab06511" %}
 
 package:
   name: {{ name|lower }}
@@ -42,7 +42,7 @@ test:
   commands:
     - rdrpcatch --help
     - rdrpcatch scan --help
-    - rdrpcatch download --help
+    - rdrpcatch databases --help
 
 about:
   home: https://github.com/dimitris-karapliafis/RdRpCATCH

{rdrpcatch-0.0.8 → rdrpcatch-0.0.9}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "rdrpcatch"
-version = "0.0.8"
+version = "0.0.9"
 authors = [
     {name = "Dimitris Karapliafis", email = "dimitris.karapliafis@wur.nl"},
     {name = "Uri Neri", email = "uneri@lbl.gov"},

{rdrpcatch-0.0.8 → rdrpcatch-0.0.9}/rdrpcatch/cli/args.py

@@ -76,7 +76,7 @@ def cli():
                    " TSA_Olendraite_fam, TSA_Olendraite_gen, RDRP-scan,Lucaprot_HMM, Zayed_HMM, all, none. ")
 @click.option("--custom-dbs",
               help="Path to directory containing custom MSAs/pHMM files to use as additional databases")
-@click.option("-seq_type", "--seq_type",
+@click.option("-seq-type", "--seq-type",
               type=click.STRING,
               default=None,
               help="Type of sequence to search against: (prot,nuc) Default: unknown")
@@ -107,11 +107,11 @@ def cli():
               type=click.INT,
               default=1,
               help="Number of CPUs to use for HMMsearch. (default: 1)")
-@click.option('-length_thr', '--length_thr',
+@click.option('-length-thr', '--length-thr',
               type=click.INT,
               default=400,
               help="Minimum length threshold for seqkit seq. (default: 400)")
-@click.option('-gen-code', '--gen_code',
+@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, '
@@ -142,7 +142,7 @@ def cli():
               is_flag=True,
               default=False,
               help="Bundle the output files into a single archive. (default: False)")
-@click.option('-keep-tmp', '--keep_tmp',
+@click.option('-keep-tmp', '--keep-tmp',
               is_flag=True,
               default=False,
               help="Keep temporary files (Expert users) (default: False)")

{rdrpcatch-0.0.8 → rdrpcatch-0.0.9}/rdrpcatch/rdrpcatch_wrapper.py

@@ -237,7 +237,7 @@ def run_scan(input_file, output_dir, db_options, db_dir, custom_dbs,  seq_type,
             elif db == "NeoRdRp".lower():
                 db_name_list.append("NeoRdRp")
                 db_path_list.append(neordrp_hmm_db)
-            elif db == "NeoRdRp.2.1":
+            elif db == "NeoRdRp.2.1".lower():
                 db_name_list.append("NeoRdRp.2.1".lower())
                 db_path_list.append(neordrp_2_hmm_db)
             elif db == "TSA_Olendraite_fam".lower():