ORForise 1.6.4__tar.gz → 1.6.5__tar.gz

{orforise-1.6.4 → orforise-1.6.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ORForise
-Version: 1.6.4
+Version: 1.6.5
 Summary: ORForise - A platform for analysing and comparing genome annotations.
 Author-email: Nicholas Dimonaco <nicholas@dimonaco.co.uk>
 License:                     GNU GENERAL PUBLIC LICENSE
@@ -662,7 +662,7 @@ Example output files from ```Annotation-Compare```, ```Aggregate-Compare```, ```
 For Help: ```Annotation-Compare -h ```
 
 ```python
-ORForise v1.6.4: Annotatione-Compare Run Parameters.
+ORForise v1.6.5: Annotatione-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -730,7 +730,7 @@ ORForise can be used as the example below.
 For Help: ```Aggregate-Compare -h ```
 
 ```python
-ORForise v1.6.4: Aggregate-Compare Run Parameters.
+ORForise v1.6.5: Aggregate-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -811,7 +811,7 @@ GFF-Adder combines two existing annotations (GFF or other tool formats).
 For Help: ```GFF-Adder -h ```
 
 ```python
-ORForise v1.6.4: GFF-Adder Run Parameters.
+ORForise v1.6.5: GFF-Adder Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -868,7 +868,7 @@ usage: Annotation_Intersector.py [-h] -ref REFERENCE_ANNOTATION -at
                                  [-cov COVERAGE] [--report-discordance]
                                  [--report-discordance-file REPORT_DISCORDANCE_FILE]
 
-ORForise v1.6.4: Annotation-Intersector Run Parameters
+ORForise v1.6.5: Annotation-Intersector Run Parameters
 
 options:
   -h, --help            show this help message and exit
@@ -939,7 +939,7 @@ Chromosome	EasyGene	CDS	70378	71265	.	.	.	Status=found_in_additional_but_below_c
 
 ```
 
-#### Convert-To-GFF: Converts tool-specific output files to standard GFF3 format for use in ORForise analyses.
+#### Convert-To-GFF: Converts tool-specific output files to standard GFF3 format for use in ORForise analyses (BETA!!!).
 For Help: ```Convert_To_GFF.py -h ```
 ```
 Thank you for using ORForise
@@ -947,7 +947,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 #####
 usage: Convert_To_GFF.py [-h] [-dna GENOME_DNA] -i INPUT_ANNOTATION -fmt FORMAT -o OUTPUT_DIR [-gi GENE_IDENT] [--verbose]
 
-ORForise v1.6.4: Convert-To-GFF Run Parameters
+ORForise v1.6.5: Convert-To-GFF Run Parameters
 
 Required Arguments:
   -dna GENOME_DNA      Genome DNA file (.fa)

{orforise-1.6.4 → orforise-1.6.5}/README.md

@@ -21,7 +21,7 @@ Example output files from ```Annotation-Compare```, ```Aggregate-Compare```, ```
 For Help: ```Annotation-Compare -h ```
 
 ```python
-ORForise v1.6.4: Annotatione-Compare Run Parameters.
+ORForise v1.6.5: Annotatione-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -89,7 +89,7 @@ ORForise can be used as the example below.
 For Help: ```Aggregate-Compare -h ```
 
 ```python
-ORForise v1.6.4: Aggregate-Compare Run Parameters.
+ORForise v1.6.5: Aggregate-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -170,7 +170,7 @@ GFF-Adder combines two existing annotations (GFF or other tool formats).
 For Help: ```GFF-Adder -h ```
 
 ```python
-ORForise v1.6.4: GFF-Adder Run Parameters.
+ORForise v1.6.5: GFF-Adder Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -227,7 +227,7 @@ usage: Annotation_Intersector.py [-h] -ref REFERENCE_ANNOTATION -at
                                  [-cov COVERAGE] [--report-discordance]
                                  [--report-discordance-file REPORT_DISCORDANCE_FILE]
 
-ORForise v1.6.4: Annotation-Intersector Run Parameters
+ORForise v1.6.5: Annotation-Intersector Run Parameters
 
 options:
   -h, --help            show this help message and exit
@@ -298,7 +298,7 @@ Chromosome	EasyGene	CDS	70378	71265	.	.	.	Status=found_in_additional_but_below_c
 
 ```
 
-#### Convert-To-GFF: Converts tool-specific output files to standard GFF3 format for use in ORForise analyses.
+#### Convert-To-GFF: Converts tool-specific output files to standard GFF3 format for use in ORForise analyses (BETA!!!).
 For Help: ```Convert_To_GFF.py -h ```
 ```
 Thank you for using ORForise
@@ -306,7 +306,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 #####
 usage: Convert_To_GFF.py [-h] [-dna GENOME_DNA] -i INPUT_ANNOTATION -fmt FORMAT -o OUTPUT_DIR [-gi GENE_IDENT] [--verbose]
 
-ORForise v1.6.4: Convert-To-GFF Run Parameters
+ORForise v1.6.5: Convert-To-GFF Run Parameters
 
 Required Arguments:
   -dna GENOME_DNA      Genome DNA file (.fa)

{orforise-1.6.4 → orforise-1.6.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ORForise"
-version = "1.6.4"
+version = "1.6.5"
 authors = [
     {name = "Nicholas Dimonaco", email = "nicholas@dimonaco.co.uk"}
 ]

{orforise-1.6.4 → orforise-1.6.5}/src/ORForise/Convert_To_GFF.py

@@ -4,13 +4,13 @@ from datetime import datetime
 import os
 import sys
 
+
 try:
     from .utils import *
-    from .Aux.TabToGFF.TabToGFF import TabToGFF
+    from .Tools.TabToGFF.TabToGFF import TabToGFF
 except (ImportError, ModuleNotFoundError):
     from utils import *
-    from ORForise.src.ORForise.Aux.TabToGFF import TabToGFF
-
+    from Tools.TabToGFF.TabToGFF import TabToGFF
 
 
 
@@ -50,10 +50,37 @@ def write_gff(outpath, genome_ID, genome_DNA, input_annotation, fmt, features):
             pos_ = pos.split(',')
             start = pos_[0]
             stop = pos_[-1]
-            strand = data['strand']
+            strand = data.get('strand', '.')
             if fmt == 'abricate': # Currently only supports abricate format
-                info = 'abricate_anotation;accession='+data['accession']+';database='+data['database']+';identity='+str(data['identity'])+';coverage='+str(data['coverage'])+';product='+data['product']+';resistance='+data['resistance']
-            entry = f"{data['seqid']}\t{fmt}\t{'CDS'}\t{start}\t{stop}\t.\t{strand}\t.\t{'ID='}{info}\n"
+                info = 'abricate_annotation;accession={};database={};identity={};coverage={};product={};resistance={}'.format(
+                    data.get('accession', 'unknown'),
+                    data.get('database', 'unknown'),
+                    data.get('identity', ''),
+                    data.get('coverage', ''),
+                    data.get('product', ''),
+                    data.get('resistance', '')
+                )
+            elif fmt in ('amrfinder', 'amrfinderplus', 'amr'):
+                # Build a compact attribute string for amrfinder-plus output
+                info = ('amrfinder_annotation;element={};element_name={};protein_id={};type={};class={};subclass={};method={};pct_cov={};pct_id={};closest_acc={};closest_name={}').format(
+                    data.get('element_symbol', ''),
+                    data.get('element_name', ''),
+                    data.get('protein_id', ''),
+                    data.get('type', ''),
+                    data.get('class', ''),
+                    data.get('subclass', ''),
+                    data.get('method', ''),
+                    data.get('pct_coverage', ''),
+                    data.get('pct_identity', ''),
+                    data.get('closest_accession', ''),
+                    data.get('closest_name', '')
+                )
+            else:
+                # Generic fallback: try to include any seqid/gene info if present
+                gene_id = data.get('gene') or data.get('ID') or ''
+                info = f"annotation;id={gene_id}"
+
+            entry = f"{data.get('seqid', genome_ID)}\t{fmt}\tCDS\t{start}\t{stop}\t.\t{strand}\t.\tID={info}\n"
             out.write(entry)
 
 
@@ -79,7 +106,7 @@ def main():
     required = parser.add_argument_group('Required Arguments')
 
     required.add_argument('-i', dest='input_annotation', required=True, help='Input annotation file (tabular)')
-    required.add_argument('-fmt', dest='format', required=True, help='Input format: blast, abricate, genemark')
+    required.add_argument('-fmt', dest='format', required=True, help='Input format: amrfinder, abricate, blast')
     required.add_argument('-o', dest='output_dir', required=True, help='Output directory')
 
     optional = parser.add_argument_group('Optional Arguments')

{orforise-1.6.4/src/ORForise/Aux → orforise-1.6.5/src/ORForise/Tools}/TabToGFF/TabToGFF.py

@@ -128,6 +128,76 @@ def parse_genemark(path, genome_seq, gene_ident=None):
     return results
 
 
+def parse_amrfinderplus(path, genome_seq, gene_ident=None):
+    """
+    Parse amrfinder-plus TSV (header line present). Produces an OrderedDict
+    keyed by "start,stop" -> attrs dict similar to parse_abricate.
+    """
+    results = collections.OrderedDict()
+    count = 0
+    with open(path, 'r') as fh:
+        header = None
+        header_map = {}
+        for i, line in enumerate(fh, 1):
+            line = line.rstrip('\n')
+            if not line:
+                continue
+            # Skip comment lines but treat the first non-empty non-comment line as header
+            if line.startswith('#'):
+                continue
+            if header is None:
+                header = line.split('\t')
+                header_map = {h.strip(): idx for idx, h in enumerate(header)}
+                continue
+            parts = line.split('\t')
+            # allow lines with fewer/more columns but avoid crashes
+            if header and len(parts) < len(header):
+                logging.warning(f"Line {i}: unexpected number of columns in amrfinder line")
+                continue
+            try:
+                start = int(parts[header_map.get('Start')])
+                end = int(parts[header_map.get('Stop')])
+            except Exception:
+                logging.warning(f"Line {i}: invalid Start/Stop in amrfinder line")
+                continue
+            strand = parts[header_map.get('Strand', '')]
+            seqid = parts[header_map.get('Contig id', '')]
+            protein_id = parts[header_map.get('Protein id', '')]
+            element_symbol = parts[header_map.get('Element symbol', '')]
+            element_name = parts[header_map.get('Element name', '')]
+            amr_type = parts[header_map.get('Type', '')]
+            amr_subtype = parts[header_map.get('Subtype', '')]
+            amr_class = parts[header_map.get('Class', '')]
+            amr_subclass = parts[header_map.get('Subclass', '')]
+            method = parts[header_map.get('Method', '')]
+            pct_cov = parts[header_map.get('% Coverage of reference', '')]
+            pct_id = parts[header_map.get('% Identity to reference', '')]
+            closest_acc = parts[header_map.get('Closest reference accession', '')]
+            closest_name = parts[header_map.get('Closest reference name', '')]
+
+            attrs = {
+                'seqid': seqid,
+                'start': start,
+                'end': end,
+                'strand': strand,
+                'protein_id': protein_id,
+                'element_symbol': element_symbol,
+                'element_name': element_name,
+                'type': amr_type,
+                'subtype': amr_subtype,
+                'class': amr_class,
+                'subclass': amr_subclass,
+                'method': method,
+                'pct_coverage': pct_cov,
+                'pct_identity': pct_id,
+                'closest_accession': closest_acc,
+                'closest_name': closest_name
+            }
+            results[f"{start},{end}"] = attrs
+            count += 1
+    return results
+
+
 def TabToGFF(input_file, genome_seq, gene_ident='CDS', fmt='blast'):
     # Should be cleaned up to use consistent format names
     fmt = fmt.lower()
@@ -137,4 +207,6 @@ def TabToGFF(input_file, genome_seq, gene_ident='CDS', fmt='blast'):
         return parse_abricate(input_file, genome_seq, gene_ident)
     if fmt in ('genemark', 'gene_mark'):
         return parse_genemark(input_file, genome_seq, gene_ident)
+    if fmt in ('amrfinder', 'amrfinderplus', 'amr'):
+        return parse_amrfinderplus(input_file, genome_seq, gene_ident)
     raise ValueError(f"Unknown format: {fmt}")

{orforise-1.6.4 → orforise-1.6.5}/src/ORForise/utils.py

@@ -4,7 +4,7 @@ import collections
 # Constants
 SHORT_ORF_LENGTH = 300
 MIN_COVERAGE = 75
-ORForise_Version = 'v1.6.4'
+ORForise_Version = 'v1.6.5'
 CLOSING=("\n####\nThank you for using ORForise\nPlease report any issues to: https://github.com/NickJD/ORForise/issues\n"
         "Please Cite: https://doi.org/10.1093/bioinformatics/btab827\n"
         "#####")

{orforise-1.6.4 → orforise-1.6.5}/src/ORForise.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ORForise
-Version: 1.6.4
+Version: 1.6.5
 Summary: ORForise - A platform for analysing and comparing genome annotations.
 Author-email: Nicholas Dimonaco <nicholas@dimonaco.co.uk>
 License:                     GNU GENERAL PUBLIC LICENSE
@@ -662,7 +662,7 @@ Example output files from ```Annotation-Compare```, ```Aggregate-Compare```, ```
 For Help: ```Annotation-Compare -h ```
 
 ```python
-ORForise v1.6.4: Annotatione-Compare Run Parameters.
+ORForise v1.6.5: Annotatione-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -730,7 +730,7 @@ ORForise can be used as the example below.
 For Help: ```Aggregate-Compare -h ```
 
 ```python
-ORForise v1.6.4: Aggregate-Compare Run Parameters.
+ORForise v1.6.5: Aggregate-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -811,7 +811,7 @@ GFF-Adder combines two existing annotations (GFF or other tool formats).
 For Help: ```GFF-Adder -h ```
 
 ```python
-ORForise v1.6.4: GFF-Adder Run Parameters.
+ORForise v1.6.5: GFF-Adder Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -868,7 +868,7 @@ usage: Annotation_Intersector.py [-h] -ref REFERENCE_ANNOTATION -at
                                  [-cov COVERAGE] [--report-discordance]
                                  [--report-discordance-file REPORT_DISCORDANCE_FILE]
 
-ORForise v1.6.4: Annotation-Intersector Run Parameters
+ORForise v1.6.5: Annotation-Intersector Run Parameters
 
 options:
   -h, --help            show this help message and exit
@@ -939,7 +939,7 @@ Chromosome	EasyGene	CDS	70378	71265	.	.	.	Status=found_in_additional_but_below_c
 
 ```
 
-#### Convert-To-GFF: Converts tool-specific output files to standard GFF3 format for use in ORForise analyses.
+#### Convert-To-GFF: Converts tool-specific output files to standard GFF3 format for use in ORForise analyses (BETA!!!).
 For Help: ```Convert_To_GFF.py -h ```
 ```
 Thank you for using ORForise
@@ -947,7 +947,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 #####
 usage: Convert_To_GFF.py [-h] [-dna GENOME_DNA] -i INPUT_ANNOTATION -fmt FORMAT -o OUTPUT_DIR [-gi GENE_IDENT] [--verbose]
 
-ORForise v1.6.4: Convert-To-GFF Run Parameters
+ORForise v1.6.5: Convert-To-GFF Run Parameters
 
 Required Arguments:
   -dna GENOME_DNA      Genome DNA file (.fa)

{orforise-1.6.4 → orforise-1.6.5}/src/ORForise.egg-info/SOURCES.txt

@@ -23,8 +23,6 @@ src/ORForise/Aux/StORF_Undetected/Completely_Undetected/Completey_Undetected.py
 src/ORForise/Aux/StORF_Undetected/Completely_Undetected/__init__.py
 src/ORForise/Aux/StORF_Undetected/unvitiated_Genes/__init__.py
 src/ORForise/Aux/StORF_Undetected/unvitiated_Genes/unvitiated_Missed_Genes.py
-src/ORForise/Aux/TabToGFF/TabToGFF.py
-src/ORForise/Aux/TabToGFF/__init__.py
 src/ORForise/ORForise_Analysis/__init__.py
 src/ORForise/ORForise_Analysis/cds_checker.py
 src/ORForise/ORForise_Analysis/gene_Lenghts.py
@@ -71,5 +69,7 @@ src/ORForise/Tools/Prokka/Prokka.py
 src/ORForise/Tools/Prokka/__init__.py
 src/ORForise/Tools/StORF-Reporter/StORF-Reporter.py
 src/ORForise/Tools/StORF-Reporter/__init__.py
+src/ORForise/Tools/TabToGFF/TabToGFF.py
+src/ORForise/Tools/TabToGFF/__init__.py
 src/ORForise/Tools/TransDecoder/TransDecoder.py
 src/ORForise/Tools/TransDecoder/__init__.py