rdrpcatch 0.0.3__tar.gz → 0.0.5__tar.gz

{rdrpcatch-0.0.3 → rdrpcatch-0.0.5}/.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="Updates:&#10;Update meta.yaml and .toml file&#10;Preparing for Pypi and Bioconda upload">
-      <change beforePath="$PROJECT_DIR$/meta.yaml" beforeDir="false" afterPath="$PROJECT_DIR$/meta.yaml" afterDir="false" />
-    </list>
+    <list default="true" id="d849e6fa-87f9-4e92-9c33-abef7cc975d3" name="Changes" comment="Updates:&#10;Fixed bug that crushed the script when at least one  pHMM DB does not have a match against the sequence database also for nuc branch" />
     <option name="SHOW_DIALOG" value="false" />
     <option name="HIGHLIGHT_CONFLICTS" value="true" />
     <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
@@ -38,22 +36,22 @@
     <option name="hideEmptyMiddlePackages" value="true" />
     <option name="showLibraryContents" value="true" />
   </component>
-  <component name="PropertiesComponent">{
-  &quot;keyToString&quot;: {
-    &quot;ASKED_ADD_EXTERNAL_FILES&quot;: &quot;true&quot;,
-    &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/ColaB-Scan/testing&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;,
-    &quot;node.js.selected.package.tslint&quot;: &quot;(autodetect)&quot;,
-    &quot;nodejs_package_manager_path&quot;: &quot;npm&quot;,
-    &quot;settings.editor.selected.configurable&quot;: &quot;preferences.pluginManager&quot;,
-    &quot;vue.rearranger.settings.migration&quot;: &quot;true&quot;
+  <component name="PropertiesComponent"><![CDATA[{
+  "keyToString": {
+    "ASKED_ADD_EXTERNAL_FILES": "true",
+    "RunOnceActivity.OpenProjectViewOnStart": "true",
+    "RunOnceActivity.ShowReadmeOnStart": "true",
+    "ignore.virus.scanning.warn.message": "true",
+    "last_opened_file_path": "C:/Users/karso/PycharmProjects/rdrpcatch_benchmarks",
+    "node.js.detected.package.eslint": "true",
+    "node.js.detected.package.tslint": "true",
+    "node.js.selected.package.eslint": "(autodetect)",
+    "node.js.selected.package.tslint": "(autodetect)",
+    "nodejs_package_manager_path": "npm",
+    "settings.editor.selected.configurable": "preferences.pluginManager",
+    "vue.rearranger.settings.migration": "true"
   }
-}</component>
+}]]></component>
   <component name="RecentsManager">
     <key name="CopyFile.RECENT_KEYS">
       <recent name="C:\Users\karso\PycharmProjects\ColaB-Scan\testing" />
@@ -117,6 +115,8 @@
       <workItem from="1743013480572" duration="6846000" />
       <workItem from="1743683517488" duration="7013000" />
       <workItem from="1743714892367" duration="21775000" />
+      <workItem from="1744200654491" duration="635000" />
+      <workItem from="1744241097621" duration="28249000" />
     </task>
     <task id="LOCAL-00001" summary="First commit: Script for benchmark">
       <option name="closed" value="true" />
@@ -334,7 +334,31 @@
       <option name="project" value="LOCAL" />
       <updated>1743738696182</updated>
     </task>
-    <option name="localTasksCounter" value="28" />
+    <task id="LOCAL-00028" summary="Updates:&#10;Optimize fasta writer from O(n*m) to O(n+m)">
+      <option name="closed" value="true" />
+      <created>1744246540802</created>
+      <option name="number" value="00028" />
+      <option name="presentableId" value="LOCAL-00028" />
+      <option name="project" value="LOCAL" />
+      <updated>1744246540804</updated>
+    </task>
+    <task id="LOCAL-00029" summary="Updates:&#10;Polishing ReadME&#10;Fixed bug that crushed the script when at least one  pHMM DB does not have a match against the sequence database">
+      <option name="closed" value="true" />
+      <created>1744793957201</created>
+      <option name="number" value="00029" />
+      <option name="presentableId" value="LOCAL-00029" />
+      <option name="project" value="LOCAL" />
+      <updated>1744793957201</updated>
+    </task>
+    <task id="LOCAL-00030" summary="Updates:&#10;Fixed bug that crushed the script when at least one  pHMM DB does not have a match against the sequence database also for nuc branch">
+      <option name="closed" value="true" />
+      <created>1744796108058</created>
+      <option name="number" value="00030" />
+      <option name="presentableId" value="LOCAL-00030" />
+      <option name="project" value="LOCAL" />
+      <updated>1744796108058</updated>
+    </task>
+    <option name="localTasksCounter" value="31" />
     <servers />
   </component>
   <component name="TypeScriptGeneratedFilesManager">
@@ -352,7 +376,6 @@
     </option>
   </component>
   <component name="VcsManagerConfiguration">
-    <MESSAGE value="First commit: Script for benchmark" />
     <MESSAGE value="Commit: Plots and result summary" />
     <MESSAGE value="Commit: File name change" />
     <MESSAGE value="Commit: Upload script and results" />
@@ -375,6 +398,9 @@
     <MESSAGE value="Updates:&#10;Refactor Database installation to support download and automatic update&#10;Handle empty files &#10;General bug fixes" />
     <MESSAGE value="Updates:&#10;Change test case" />
     <MESSAGE value="Updates:&#10;Update meta.yaml and .toml file&#10;Preparing for Pypi and Bioconda upload" />
-    <option name="LAST_COMMIT_MESSAGE" value="Updates:&#10;Update meta.yaml and .toml file&#10;Preparing for Pypi and Bioconda upload" />
+    <MESSAGE value="Updates:&#10;Optimize fasta writer from O(n*m) to O(n+m)" />
+    <MESSAGE value="Updates:&#10;Polishing ReadME&#10;Fixed bug that crushed the script when at least one  pHMM DB does not have a match against the sequence database" />
+    <MESSAGE value="Updates:&#10;Fixed bug that crushed the script when at least one  pHMM DB does not have a match against the sequence database also for nuc branch" />
+    <option name="LAST_COMMIT_MESSAGE" value="Updates:&#10;Fixed bug that crushed the script when at least one  pHMM DB does not have a match against the sequence database also for nuc branch" />
   </component>
 </project>

{rdrpcatch-0.0.3 → rdrpcatch-0.0.5}/PKG-INFO

@@ -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 → rdrpcatch-0.0.5}/README.md

@@ -59,7 +59,7 @@ 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 → rdrpcatch-0.0.5}/meta.yaml

@@ -1,5 +1,5 @@
 {% set name = "RdRpCATCH" %}
-{% set version = "0.0.2" %}
+{% set version = "0.0.1" %}
 {% set sha256 = "6454b1a6f98e461ca82d181b1595e5f06448786540b6daa2c4de31c38b255412" %}
 
 package:
@@ -13,7 +13,7 @@ source:
 build:
   number: 0
   noarch: python
-  script: {{ PYTHON }} -m pip install . -vv
+  script: {{ PYTHON }} -m pip install . --no-deps --no-build-isolation --no-cache-dir -vvv
   run_exports:
     - {{ pin_compatible('rdrpcatch', max_pin='x.x.x') }}
   entry_points:
@@ -26,17 +26,17 @@ requirements:
     - pip
   run:
     - python >=3.12
-    - mmseqs2 =17.b804f
-    - seqkit =2.10.0
-    - pyhmmer =0.11.0
-    - needletail =0.6.3
-    - polars =1.26.0
-    - rich =13.9.4
-    - rich-click =1.8.8
-    - upsetplot =0.9.0
-    - matplotlib-base =3.10.1
-    - altair =5.5.0
-    - requests =2.32.3
+    - mmseqs2 ==17.b804f
+    - seqkit ==2.10.0
+    - pyhmmer ==0.11.0
+    - needletail ==0.6.3
+    - polars ==1.26.0
+    - rich ==13.9.4
+    - rich-click ==1.8.8
+    - upsetplot ==0.9.0
+    - matplotlib-base ==3.10.1
+    - altair ==5.5.0
+    - requests ==2.32.3
 
 test:
   commands:
@@ -49,7 +49,7 @@ about:
   license: MIT
   license_family: MIT
   license_file: LICENSE
-  summary: RNA virus RdRp sequence scanner
+  summary: "RNA virus RdRp sequence scanner."
   description: |
     RdRpCATCH (RNA-dependent RNA polymerase Collaborative Analysis Tool with Collections of pHMMs) 
     is a tool for scanning sequences for RNA-dependent RNA polymerases (RdRps) using profile HMMs.

{rdrpcatch-0.0.3 → rdrpcatch-0.0.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "rdrpcatch"
-version = "0.0.3"
+version = "0.0.5"
 authors = [
     {name = "Dimitris Karapliafis", email = "dimitris.karapliafis@wur.nl"},
     {name = "Uri Neri", email = "uneri@lbl.gov"},

{rdrpcatch-0.0.3 → rdrpcatch-0.0.5}/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-0.0.3 → rdrpcatch-0.0.5}/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-0.0.3 → rdrpcatch-0.0.5}/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)