minor update to v1.3.1

Author: raufs

README.md

@@ -340,14 +340,12 @@ options:
   -h, --help            show this help message and exit
   -g GENOMES [GENOMES ...], --genomes GENOMES [GENOMES ...]
                         Genome assembly file paths or paths to containing
-                        directories. Files should be in FASTA format and can be gzipped
-                        (accepted suffices are: *.fasta,
-                        *.fa, *.fas, or *.fna) [Optional].
+                        directories. Files should be in FASTA format (accepted suffices
+                        are: *.fasta, *.fa, *.fas, or *.fna) [Optional].
   -p PROTEOMES [PROTEOMES ...], --proteomes PROTEOMES [PROTEOMES ...]
                         Proteome file paths or paths to containing
-                        directories. Files should be in FASTA format and can be gzipped
-                        (accepted suffices are: *.fasta,
-                        *.fa, or *.faa) [Optional].
+                        directories. Files should be in FASTA format (accepted suffices
+                        are: *.fasta, *.fa, or *.faa) [Optional].
   -t TAXA_NAME, --taxa-name TAXA_NAME
                         Genus or species identifier from GTDB for which to
                         download genomes for and include in

bin/cidder

@@ -90,8 +90,8 @@ def create_parser():
 	metagenomic applications. Salamzade, Kottapalli, and Kalan, 2025.
     """, formatter_class=argparse.RawTextHelpFormatter)
 
-	parser.add_argument('-g', '--genomes', nargs='+', help='Genome assembly file paths or paths to containing\ndirectories. Files should be in FASTA format and can be gzipped\n(accepted suffices are: *.fasta,\n*.fa, *.fas, or *.fna) [Optional].', required=False, default=[])
-	parser.add_argument('-p', '--proteomes', nargs='+', help='Proteome file paths or paths to containing\ndirectories. Files should be in FASTA format and can be gzipped\n(accepted suffices are: *.fasta,\n*.fa, or *.faa) [Optional].', required=False, default=[])
+	parser.add_argument('-g', '--genomes', nargs='+', help='Genome assembly file paths or paths to containing\ndirectories. Files should be in FASTA format (accepted suffices\nare: *.fasta, *.fa, *.fas, or *.fna) [Optional].', required=False, default=[])
+	parser.add_argument('-p', '--proteomes', nargs='+', help='Proteome file paths or paths to containing\ndirectories. Files should be in FASTA format (accepted suffices\nare: *.fasta, *.fa, or *.faa) [Optional].', required=False, default=[])
 	parser.add_argument('-t', '--taxa-name', help='Genus or species identifier from GTDB for which to\ndownload genomes for and include in\ndereplication analysis [Optional].', required=False, default=None)
 	parser.add_argument('-a', '--new-proteins-needed', type=int, help="The number of new protein clusters needed to add [Default is 0].", required=False, default=0)
 	parser.add_argument('-ts', '--total-saturation', type=float, help="The percentage of total proteins clusters needed to stop representative\ngenome selection [Default is 90.0].", required=False, default=90.0)
@@ -268,7 +268,7 @@ def cidder_main():
 	proteome_name_to_path = {}
 	if len(proteomes) > 0:
 		try:
-			proteome_name_to_path = util.processInputProteomes(proteomes, combined_proteome_faa, genome_name_to_path, logObject, sanity_check=sanity_check_flag)
+			proteome_name_to_path = util.processInputProteomes(proteomes, combined_proteome_faa, genome_name_to_path, logObject, sanity_check=sanity_check_flag, allow_gzipped=False)
 		except Exception as e:
 			msg = 'Error: issues processing user-provided proteomes. Exiting ...'
 			sys.stderr.write(msg + '\n')

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "skDER"
 authors = [{name="Rauf Salamzade", email="salamzader@gmail.com"}]
-version = "1.3.0"
+version = "1.3.1"
 description = "Program to select distinct representatives from an input set of microbial genomes."
 
 [build-system]

src/skDER/util.py

@@ -204,7 +204,7 @@ def downloadGTDBGenomes(taxa_name, gtdb_release, outdir, genome_listing_file, lo
 		sys.stdout.write(msg + '\n')
 		logObject.info(msg)
 
-def processInputProteomes(proteomes, combined_proteome_faa, genome_to_path, logObject, sanity_check=False):
+def processInputProteomes(proteomes, combined_proteome_faa, genome_to_path, logObject, sanity_check=False, allow_gzipped=True):
 	combined_proteome_handle = open(combined_proteome_faa, 'a+')
 	proteome_name_to_path = {}
 	for p in proteomes:
@@ -217,7 +217,11 @@ def processInputProteomes(proteomes, combined_proteome_faa, genome_to_path, logO
 				if proteome_file.endswith('.gz'):
 					proteome_name = '.'.join(proteome_file.split('/')[-1][:-3].split('.')[:-1])
 					suffix = proteome_file[:-3].split('.')[-1].lower()
-				
+					if not allow_gzipped:
+						msg = 'Warning: proteome %s is gzipped. Skipping ...' % proteome_file
+						sys.stderr.write(msg + '\n')
+						logObject.warning(msg)
+						continue
 				if proteome_name in genome_to_path:
 					msg = 'Warning: proteome %s has the same name as a genome. Skipping ...' % proteome_file
 					logObject.warning(msg)
@@ -262,7 +266,11 @@ def processInputProteomes(proteomes, combined_proteome_faa, genome_to_path, logO
 			if proteome_file.endswith('.gz'):
 				proteome_name = '.'.join(proteome_file.split('/')[-1][:-3].split('.')[:-1])
 				suffix = proteome_file.split('/')[-1][:-3].split('.')[-1].lower()
-				
+				if not allow_gzipped:
+					msg = 'Warning: proteome %s is gzipped. Skipping ...' % proteome_file
+					sys.stderr.write(msg + '\n')
+					logObject.warning(msg)
+					continue
 			if proteome_name in genome_to_path:
 				msg = 'Warning: proteome %s has the same name as a genome. Skipping ...' % proteome_file
 				logObject.warning(msg)