rdrpcatch 0.0.3__tar.gz → 0.0.4__tar.gz

{rdrpcatch-0.0.3 → rdrpcatch-0.0.4}/.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;Update meta.yaml and .toml file&#10;Preparing for Pypi and Bioconda upload" />
     <option name="SHOW_DIALOG" value="false" />
     <option name="HIGHLIGHT_CONFLICTS" value="true" />
     <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
@@ -117,6 +115,7 @@
       <workItem from="1743013480572" duration="6846000" />
       <workItem from="1743683517488" duration="7013000" />
       <workItem from="1743714892367" duration="21775000" />
+      <workItem from="1744200654491" duration="635000" />
     </task>
     <task id="LOCAL-00001" summary="First commit: Script for benchmark">
       <option name="closed" value="true" />

{rdrpcatch-0.0.3 → rdrpcatch-0.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdrpcatch
-Version: 0.0.3
+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-0.0.3 → rdrpcatch-0.0.4}/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-0.0.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "rdrpcatch"
-version = "0.0.3"
+version = "0.0.4"
 authors = [
     {name = "Dimitris Karapliafis", email = "dimitris.karapliafis@wur.nl"},
     {name = "Uri Neri", email = "uneri@lbl.gov"},

{rdrpcatch-0.0.3 → rdrpcatch-0.0.4}/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-0.0.4}/rdrpcatch/rdrpcatch_wrapper.py

@@ -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)