PyamilySeq 1.3.2__py3-none-any.whl → 1.3.3__py3-none-any.whl

PyamilySeq/PyamilySeq.py

@@ -1,6 +1,3 @@
-import argparse
-#from config import config_params
-
 try:
     from .PyamilySeq_Species import cluster as species_cluster
     from .PyamilySeq_Genus import cluster as genus_cluster
@@ -12,10 +9,11 @@ except (ModuleNotFoundError, ImportError, NameError, TypeError) as error:
     from constants import *
     from utils import *
 
-
-
+import traceback
+import sys
 
 def run_cd_hit(options, input_file, clustering_output, clustering_mode):
+    logger = logging.getLogger("PyamilySeq.PyamilySeq")
     cdhit_command = [
         clustering_mode,
         '-i', input_file,
@@ -29,14 +27,25 @@ def run_cd_hit(options, input_file, clustering_output, clustering_mode):
         '-sc', "1",
         '-sf', "1"
     ]
-    if options.verbose == True:
-        subprocess.run(cdhit_command)
-    else:
-        subprocess.run(cdhit_command, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
+    logger.debug("CD-HIT command: %s", " ".join(cdhit_command))
+    try:
+        if options.verbose:
+            ret = subprocess.run(cdhit_command)
+        else:
+            ret = subprocess.run(cdhit_command, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
+        if ret.returncode != 0:
+            logger.error("cd-hit returned non-zero exit code %s", ret.returncode)
+        else:
+            logger.info("cd-hit completed successfully: %s", clustering_output)
+    except Exception as e:
+        logger.exception("Failed to run cd-hit: %s", e)
 
 
 def main():
-    parser = argparse.ArgumentParser(description=f"PyamilySeq {PyamilySeq_Version}: A tool for gene clustering and analysis.")
+    # Initial console-only logger so welcome and parser.description are logged before argparse outputs.
+    early_logger = configure_logger("PyamilySeq.PyamilySeq", enable_file=False, log_dir=None, verbose=False)
+    # Use LoggingArgumentParser so usage/errors are emitted via logger
+    parser = LoggingArgumentParser(logger_name="PyamilySeq.PyamilySeq")#, description="PyamilySeq entrypoint")
 
     # Add subparsers for Full and Partial modes
     subparsers = parser.add_subparsers(dest="run_mode", required=True, help="Choose a mode: 'Full' or 'Partial'.")
@@ -109,28 +118,28 @@ def main():
         subparser.add_argument("-T", type=int, default=8, dest="threads", required=False,
                                  help="Number of threads for clustering/alignment - CD-HIT parameter '-T' | MAFFT parameter '--thread'.")
 
-        # Miscellaneous Arguments
-        subparser.add_argument("-verbose", action="store_true",
-                            help="Print verbose output.")
-        subparser.add_argument("-v", "--version", action="version",
-                            version=f"PyamilySeq {PyamilySeq_Version}: Exiting.")
+    # Miscellaneous Arguments
+    # Global logging options (user controls logfile creation)
+    parser.add_argument("--log", action="store_true", dest="log", help="Create a timestamped logfile for this run.")
+    parser.add_argument("--log-dir", dest="log_dir", default=None,
+                        help="Directory for logfile (default: output dir or cwd).")
+    parser.add_argument("-verbose", action="store_true",
+                        help="Print verbose output.")
+    parser.add_argument("-v", "--version", action="version",
+                        version=f"PyamilySeq {PyamilySeq_Version}: Exiting.")
 
     # Parse Arguments
     options = parser.parse_args()
-    ## Configuration
 
+    # Setup logger once we know output paths/options
+    # after we resolve output_path / options.output_dir:
+    resolved_log_dir = options.log_dir if getattr(options, "log_dir", None) else (os.path.abspath(options.output_dir) if getattr(options, "output_dir", None) else os.getcwd())
+    logger = configure_logger("PyamilySeq.PyamilySeq", enable_file=getattr(options, "log", False), log_dir=resolved_log_dir, verbose=options.verbose)
+    logger.info("Running PyamilySeq %s in %s mode", PyamilySeq_Version, getattr(options, "run_mode", "N/A"))
+    if options.verbose:
+        logger.debug("Options: %s", vars(options))
 
-    if options.write_groups != None and options.write_individual_groups == False:
-        options.write_individual_groups = True
 
-    # Example of conditional logic based on selected mode
-    print(f"Running PyamilySeq {PyamilySeq_Version} in {options.run_mode} mode:")
-    if options.run_mode == "Full" and options.verbose == True:
-        print("Processing Full mode with options:", vars(options))
-    elif options.run_mode == "Partial" and options.verbose == True:
-        print("Processing Partial mode with options:", vars(options))
-
-    ### Checking all required parameters are provided by user #!!# Doesn't seem to work
     if options.run_mode == 'Full':
         options.clustering_format = 'CD-HIT'
         if getattr(options, 'reclustered', None) is not None:
@@ -145,6 +154,7 @@ def main():
             missing_options = [opt for opt in
                                ['input_type', 'input_dir', 'name_split_gff', 'clustering_format', 'pident', 'len_diff'] if
                                not options.__dict__.get(opt)]
+            logger.error("Missing required options for Full mode: %s", ', '.join(missing_options))
             sys.exit(f"Missing required options for Full mode: {', '.join(missing_options)}")
         if options.align_core:
             options.write_individual_groups = True
@@ -176,34 +186,28 @@ def main():
     ##MAFFT
     if options.align_core == True:
         if is_tool_installed('mafft'):
-            if options.verbose == True:
-                print("mafft is installed. Proceeding with alignment.")
+            logger.info("mafft is installed. Proceeding with alignment.")
         else:
+            logger.error("mafft is not installed. Please install mafft to proceed.")
             exit("mafft is not installed. Please install mafft to proceed.")
     ##CD-HIT
     if options.run_mode == 'Full':
         if is_tool_installed('cd-hit'):
-            if options.verbose == True:
-                print("cd-hit is installed. Proceeding with clustering.")
+            logger.info("cd-hit is installed. Proceeding with clustering.")
             if options.sequence_type == 'DNA':
                 clustering_mode = 'cd-hit-est'
             elif options.sequence_type == 'AA':
                 clustering_mode = 'cd-hit'
             if options.fast_mode == True:
                 options.fast_mode = 1
-                if options.verbose == True:
-                    print("Running CD-HIT in fast mode.")
+                logger.info("Running CD-HIT in fast mode.")
             else:
                 options.fast_mode = 0
-                if options.verbose == True:
-                    print("Running CD-HIT in accurate mode.")
+                logger.info("Running CD-HIT in accurate mode.")
         else:
+            logger.error("cd-hit is not installed. Please install cd-hit to proceed.")
             exit("cd-hit is not installed. Please install cd-hit to proceed.")
 
-
-    # if options.write_groups != None and options.original_fasta == False:
-    #     exit("-fasta must br provided if -w is used")
-
     if hasattr(options, 'cluster_file') and options.cluster_file:
         options.cluster_file = fix_path(options.cluster_file)
     if hasattr(options, 'reclustered') and options.reclustered:
@@ -308,10 +312,29 @@ def main():
 
 
     if options.group_mode == 'Species':
-        species_cluster(clustering_options)
+        try:
+            species_cluster(clustering_options)
+            logger.info("Invoked species clustering.")
+        except FileNotFoundError as e:
+            logger.error("File not found during species clustering: %s", e)
+            logger.debug("Traceback:\n%s", traceback.format_exc())
+            sys.exit(1)
+        except Exception as e:
+            logger.error("Unexpected error during species clustering: %s", e)
+            logger.debug("Traceback:\n%s", traceback.format_exc())
+            sys.exit(1)
     elif options.group_mode == 'Genus':
-        genus_cluster((clustering_options))
-
+        try:
+            genus_cluster(clustering_options)
+            logger.info("Invoked genus clustering.")
+        except FileNotFoundError as e:
+            logger.error("File not found during genus clustering: %s", e)
+            logger.debug("Traceback:\n%s", traceback.format_exc())
+            sys.exit(1)
+        except Exception as e:
+            logger.error("Unexpected error during genus clustering: %s", e)
+            logger.debug("Traceback:\n%s", traceback.format_exc())
+            sys.exit(1)
 
     # Save arguments to a text file
     from datetime import datetime
@@ -319,9 +342,9 @@ def main():
         outfile.write(f"Timestamp: {datetime.now().isoformat()}\n")
         for arg, value in vars(options).items():
             outfile.write(f"{arg}: {value}\n")
+    logger.info("Saved parameters to %s", os.path.join(output_path, "PyamilySeq_params.txt"))
+
 
-    print("Thank you for using PyamilySeq -- A detailed user manual can be found at https://github.com/NickJD/PyamilySeq\n"
-          "Please report any issues to: https://github.com/NickJD/PyamilySeq/issues\n#####")
 
 if __name__ == "__main__":
     main()

PyamilySeq/PyamilySeq_Genus.py

@@ -88,7 +88,7 @@ def calc_single_First_extended_Second_only_core(cluster, First_num, cores, Secon
     except KeyError:
         cores['extended_genera_>'].append(cluster)
 #@profile
-def calc_multi_First_extended_Second_only_core(cluster, First_num, cores, Second_num): # Count seperately those gene families extended with StORF_Reporter but combined >1 PEP
+def calc_multi_First_extended_Second_only_core(cluster, First_num, cores, Second_num): # Count seperately those gene families extended with StORF-Reporter but combined >1 PEP
     group = First_num + Second_num
     try:
         cores['combined_genera_' + str(group)].append(cluster)

PyamilySeq/PyamilySeq_Species.py

@@ -9,7 +9,7 @@ except (ModuleNotFoundError, ImportError, NameError, TypeError) as error:
     from utils import *
 
 
-def gene_presence_absence_output(options, genome_dict, pangenome_clusters_First_sorted,
+def gene_presence_absence_output(options, genome_dict,
                                  pangenome_clusters_First_sequences_sorted,
                                  combined_pangenome_clusters_First_Second_clustered=None,
                                  combined_pangenome_clusters_Second_sequences_sorted=None):
@@ -137,48 +137,6 @@ def gene_presence_absence_output(options, genome_dict, pangenome_clusters_First_
     if options.reclustered is not None:
         print(f"Merged Second cluster IDs: {len(merged_second_cluster_ids)}")
 
-# def gene_presence_absence_output(options, genome_dict, pangenome_clusters_First_sorted, pangenome_clusters_First_sequences_sorted):
-#     print("Outputting gene_presence_absence file")
-#     output_dir = os.path.abspath(options.output_dir)
-#     #in_name = options.clusters.split('.')[0].split('/')[-1]
-#     gpa_outfile = os.path.join(output_dir, 'gene_presence_absence.csv')
-#     gpa_outfile = open(gpa_outfile, 'w')
-#     genome_dict = OrderedDict(sorted(genome_dict.items()))
-#     gpa_outfile.write('"Gene","Non-unique Gene name","Annotation","No. isolates","No. sequences","Avg sequences per isolate","Genome Fragment","Order within Fragment",'
-#                      '"Accessory Fragment","Accessory Order with Fragment","QC","Min group size nuc","Max group size nuc","Avg group size nuc","')
-#     gpa_outfile.write('","'.join(genome_dict.keys()))
-#     gpa_outfile.write('"\n')
-#     for cluster, sequences in pangenome_clusters_First_sequences_sorted.items():
-#         average_sequences_per_genome = len(sequences) / len(pangenome_clusters_First_sorted[cluster])
-#         gpa_outfile.write('"group_'+str(cluster)+'","","","'+str(len(pangenome_clusters_First_sorted[cluster]))+'","'+str(len(sequences))+'","'+str(average_sequences_per_genome)+
-#                          '","","","","","","","",""')
-#
-#
-#         for genome in genome_dict.keys():
-#             full_out = ''
-#             tmp_list = []
-#             for value in sequences:
-#                 if value.split('|')[0] == genome:
-#                     tmp_list.append(value.split('|')[1])
-#             if tmp_list:
-#                 full_out += ',"'+'  '.join(tmp_list)+'"'
-#             else:
-#                 full_out = ',""'
-#             gpa_outfile.write(full_out)
-#         gpa_outfile.write('\n')
-
-### Below is some unfinished code
-    # edge_list_outfile = open(in_name+'_edge_list.csv','w')
-    # for cluster, sequences in pangenome_clusters_First_sequences_sorted.items():
-    #     output = []
-    #     for entry in sequences:
-    #         # Split each entry at '|'
-    #         genome, gene = entry.split('|')
-    #         # Format the result as "gene  genome"
-    #         output.append(f"{gene}\t{genome}")
-    #     for line in output:
-    #         edge_list_outfile.write(line + '\n')
-
 
 
 
@@ -209,7 +167,7 @@ def get_cores(options,genome_dict):
             cores[only_second_core_group] = []
     return cores, groups
 
-#@profile
+
 def calc_First_only_core(cluster, First_num, groups, cores):
     groups_as_list = list(groups.values())
     for idx in (idx for idx, (sec, fir) in enumerate(groups_as_list) if sec <= int(First_num) <= fir):
@@ -217,7 +175,7 @@ def calc_First_only_core(cluster, First_num, groups, cores):
     family_group = list(groups)[res]
     cores['First_core_'+family_group].append(cluster)
 
-#@profile
+
 def calc_single_First_extended_Second_only_core(cluster, First_num, groups, cores, Second_num): # Count gene families extended with StORFs
     groups_as_list = list(groups.values())
     for idx in (idx for idx, (sec, fir) in enumerate(groups_as_list) if sec <= First_num+Second_num <= fir):
@@ -227,8 +185,8 @@ def calc_single_First_extended_Second_only_core(cluster, First_num, groups, core
     cores['extended_core_' + family_group].append(cluster)
 
 
-#@profile
-def calc_multi_First_extended_Second_only_core(cluster, First_num, groups, cores, Second_num): # Count seperately those gene families extended with StORF_Reporter but combined >1 PEP
+
+def calc_multi_First_extended_Second_only_core(cluster, First_num, groups, cores, Second_num): # Count seperately those gene families extended with StORF-Reporter but combined >1 PEP
     groups_as_list = list(groups.values())
     # Looping through the list to find the matching condition
     for idx, (sec, fir) in enumerate(groups_as_list):
@@ -239,7 +197,7 @@ def calc_multi_First_extended_Second_only_core(cluster, First_num, groups, cores
     cores['combined_core_' + family_group].append(cluster)
 
 
-#@profile
+
 def calc_Second_only_core(cluster, Second_num, groups, cores):
     groups_as_list = list(groups.values())
     for idx in (idx for idx, (sec, fir) in enumerate(groups_as_list) if sec <= Second_num <= fir):
@@ -247,7 +205,7 @@ def calc_Second_only_core(cluster, Second_num, groups, cores):
     family_group = list(groups)[res]
     cores['Second_core_' + family_group].append(cluster)
 
-#@profile
+
 def calc_only_Second_only_core(cluster, Second_num, groups, cores): # only count the true storf onlies
     try:
         groups_as_list = list(groups.values())
@@ -259,7 +217,7 @@ def calc_only_Second_only_core(cluster, Second_num, groups, cores): # only count
         sys.exit("Error in calc_only_Second_only_core")
 
 
-#@profile
+
 def cluster(options):
 
     if options.cluster_format == 'CD-HIT':
@@ -273,18 +231,17 @@ def cluster(options):
     cores, groups = get_cores(options, genome_dict)
     ###
 
-    if options.reclustered != None: #FIX
+    if options.reclustered != None: # Combined clustering
         if options.cluster_format == 'CD-HIT':
             combined_pangenome_clusters_First_Second_clustered, not_Second_only_cluster_ids, combined_pangenome_clusters_Second, combined_pangenome_clusters_Second_sequences = combined_clustering_CDHIT(options, genome_dict, '|')
         elif 'TSV' in options.cluster_format or 'CSV' in options.cluster_format:
-            #Fix
             combined_pangenome_clusters_First_Second_clustered, not_Second_only_cluster_ids, combined_pangenome_clusters_Second, combined_pangenome_clusters_Second_sequences  = combined_clustering_Edge_List(options, '|')
 
         pangenome_clusters_Type = combined_clustering_counting(options, pangenome_clusters_First, reps, combined_pangenome_clusters_First_Second_clustered, pangenome_clusters_First_genomes, combined_pangenome_clusters_Second, combined_pangenome_clusters_Second_sequences,  '|')
 
         # Sort First clusters
         sorted_First_keys = sort_keys_by_values(pangenome_clusters_First, pangenome_clusters_First_sequences)
-        pangenome_clusters_First_sorted = reorder_dict_by_keys(pangenome_clusters_First, sorted_First_keys)
+        #pangenome_clusters_First_sorted = reorder_dict_by_keys(pangenome_clusters_First, sorted_First_keys)
         pangenome_clusters_First_sequences_sorted = reorder_dict_by_keys(pangenome_clusters_First_sequences, sorted_First_keys)
         pangenome_clusters_Type_sorted = reorder_dict_by_keys(pangenome_clusters_Type, sorted_First_keys)
 
@@ -296,7 +253,7 @@ def cluster(options):
     else:
         pangenome_clusters_Type = single_clustering_counting(pangenome_clusters_First, reps)
         sorted_First_keys = sort_keys_by_values(pangenome_clusters_First, pangenome_clusters_First_sequences)
-        pangenome_clusters_First_sorted = reorder_dict_by_keys(pangenome_clusters_First, sorted_First_keys)
+        #pangenome_clusters_First_sorted = reorder_dict_by_keys(pangenome_clusters_First, sorted_First_keys)
         pangenome_clusters_First_sequences_sorted = reorder_dict_by_keys(pangenome_clusters_First_sequences,
                                                                          sorted_First_keys)
         pangenome_clusters_Type_sorted = reorder_dict_by_keys(pangenome_clusters_Type, sorted_First_keys)
@@ -375,17 +332,16 @@ def cluster(options):
     if options.gene_presence_absence_out != False:
         if options.reclustered != None:
             # Pass both First and Second clustering data
-            gene_presence_absence_output(options, genome_dict, pangenome_clusters_First_sorted,
+            gene_presence_absence_output(options, genome_dict,
                                          pangenome_clusters_First_sequences_sorted,
                                          combined_pangenome_clusters_First_Second_clustered,
                                          combined_pangenome_clusters_Second_sequences_sorted)
         else:
             # Only First clustering data available
-            gene_presence_absence_output(options, genome_dict, pangenome_clusters_First_sorted,
-                                         pangenome_clusters_First_sequences_sorted)
+            gene_presence_absence_output(options, genome_dict, pangenome_clusters_First_sequences_sorted)
 
 
-    ###Need to fix this below. If full/partial the ifs need to be different. If full we first need to output the gfs then align. if -wruite-groups not presented then it needs
+    ###Need to fix this below. If full/partial the ifs need to be different. If full we first need to output the gfs then align. if -write-groups not presented then it needs
     # to be done for alignment full anyway...
 
     genome_list = list(genome_dict.keys())
@@ -400,17 +356,24 @@ def cluster(options):
                 outfile.write('>group_'+str(cluster)+'\n')
                 wrapped_aa_seq = wrap_sequence(sequences[ids[0]], 60)
                 outfile.write(wrapped_aa_seq+'\n')
-        if options.write_groups != None:
+        if options.write_groups != False:
             print("Outputting gene group FASTA files")
             #output_dir = os.path.dirname(os.path.abspath(options.output_dir))
             output_dir = os.path.join(options.output_dir, 'Gene_Groups_Output')
             write_groups_func(options,output_dir, key_order, cores, sequences,
                          pangenome_clusters_First_sequences_sorted, combined_pangenome_clusters_Second_sequences)
 
-            if options.align_core != None:
+            if options.align_core != False:
                 print("Processing gene group alignment")
                 process_gene_groups(options, output_dir, None, None, genome_list, 'core_gene_alignment.aln')
 
+        if options.write_individual_groups == True:
+            output_dir = os.path.join(options.output_dir, 'Gene_Groups_Output')
+            write_individual_groups(options, output_dir, key_order, cores, sequences,
+                                        pangenome_clusters_First_sequences_sorted,
+                                        combined_pangenome_clusters_Second_sequences)
+
+
     elif options.run_mode == 'Partial':
         sequences = read_fasta(options.fasta)
         if options.reclustered == None:
@@ -432,16 +395,21 @@ def cluster(options):
                 outfile.write('>group_'+str(cluster)+'\n')
                 wrapped_aa_seq = wrap_sequence(sequences[ids[0]], 60)
                 outfile.write(wrapped_aa_seq+'\n')
-        if options.write_groups != None:
+        if options.write_groups != False:
             print("Outputting gene group FASTA files")
             output_dir = os.path.join(options.output_dir, 'Gene_Groups_Output')
             write_groups_func(options,output_dir, key_order, cores, sequences,
                          pangenome_clusters_First_sequences_sorted, combined_pangenome_clusters_Second_sequences)
 
-            if options.align_core != None:
+            if options.align_core != False:
                 print("Processing gene group alignment")
                 process_gene_groups(options, output_dir, None, None, genome_list, 'core_gene_alignment.aln')
 
+        if options.write_individual_groups == True:
+            output_dir = os.path.join(options.output_dir, 'Gene_Groups_Output')
+            write_individual_groups(options, output_dir, key_order, cores, sequences,
+                                        pangenome_clusters_First_sequences_sorted,
+                                        combined_pangenome_clusters_Second_sequences)
 
 
         #
@@ -461,4 +429,3 @@ def cluster(options):
     #
     #
     #
-

PyamilySeq/Seq_Combiner.py

@@ -1,6 +1,3 @@
-import argparse
-
-
 try:
     from .constants import *
     from .utils import *
@@ -8,10 +5,94 @@ except (ModuleNotFoundError, ImportError, NameError, TypeError) as error:
     from constants import *
     from utils import *
 
+import threading
+import time
+import os
+from typing import Optional
+import re
+
+def count_matching_files(input_dir: str, name_split: Optional[str], extensions):
+    """
+    Count input files in input_dir that match the provided extensions and, if name_split supplied,
+    contain the name_split substring in the filename. This is used to compute total work units (files).
+    """
+    if not input_dir or not os.path.isdir(input_dir):
+        return 0
+    total = 0
+    for fname in os.listdir(input_dir):
+        low = fname.lower()
+        if any(low.endswith(ext) for ext in extensions):
+            if name_split:
+                if name_split in fname:
+                    total += 1
+            else:
+                total += 1
+    return total
+
+def count_files_present_in_combined(combined_file: str, name_split: Optional[str]) -> int:
+    """
+    Heuristic: count number of distinct input files (genomes) already present in the combined output.
+    Primary approach: parse headers and take the second '|' field (header.split('|')[1]) as genome/file id.
+    If that parsing fails, look for tokens containing name_split inside the header.
+    """
+    if not combined_file or not os.path.exists(combined_file):
+        return 0
+    seen = set()
+    try:
+        with open(combined_file, 'r') as fh:
+            for line in fh:
+                if not line.startswith('>'):
+                    continue
+                header = line[1:].strip()
+                # 1) Prefer headers like ">id|genome|rest" -> take genome (second field)
+                if '|' in header:
+                    parts = header.split('|')
+                    if len(parts) > 1 and parts[1]:
+                        seen.add(parts[1])
+                        continue
+                # 2) If name_split provided, look for a filename-like token that includes it
+                if name_split:
+                    match = re.search(r'([^\s/\\]*' + re.escape(name_split) + r'[^\s/\\]*)', header)
+                    if match:
+                        token = os.path.basename(match.group(1))
+                        seen.add(token)
+                        continue
+                # 3) If nothing matched, skip this header (avoids per-sequence overcounting)
+    except Exception:
+        return 0
+    return len(seen)
+
+# Helpers for progress reporting
 
+def progress_reporter(stop_event, logger, total_files, combined_file, name_split=None, interval=10):
+    """
+    Periodically log progress. Preference: count headers in combined_file.
+    Falls back to simple heartbeat if combined_file isn't yet created.
+    """
+    start = time.time()
+    while not stop_event.is_set():
+        # Use number of distinct input files represented in the combined output for "processed"
+        processed = count_files_present_in_combined(combined_file, name_split) if combined_file else 0
+        # Cap processed to total_files (prevents >100%)
+        if total_files > 0 and processed > total_files:
+            processed = total_files
+        pct = (processed / total_files * 100) if total_files > 0 else 0.0
+        elapsed = time.time() - start
+        logger.info("Progress: %d/%d processed (%.1f%%). Elapsed: %.0fs", processed, total_files, pct, elapsed)
+        # Wait with early exit support
+        stop_event.wait(interval)
+    # Final log when exiting
+    processed = count_files_present_in_combined(combined_file, name_split) if combined_file else 0
+    if total_files > 0 and processed > total_files:
+        processed = total_files
+    pct = (processed / total_files * 100) if total_files > 0 else 0.0
+    elapsed = time.time() - start
+    logger.info("Final progress: %d/%d processed (%.1f%%). Total elapsed: %.0fs", processed, total_files, pct, elapsed)
 
 def main():
-    parser = argparse.ArgumentParser(description='PyamilySeq ' + PyamilySeq_Version + ': Seq-Combiner - A tool to extract sequences from GFF/FASTA files and prepare them for PyamilySeq.')
+    # Early console-only logger so parser.description is logged before help/usage.
+    early_logger = configure_logger("PyamilySeq.Seq_Combiner", enable_file=False, log_dir=None, verbose=False)
+    parser = LoggingArgumentParser(logger_name="PyamilySeq.Seq_Combiner", description='Running Seq-Combiner - A tool to extract sequences from GFF/FASTA files and prepare them for PyamilySeq.')
     ### Required Arguments
     required = parser.add_argument_group('Required Arguments')
     required.add_argument('-input_dir', action='store', dest='input_dir',
@@ -47,37 +128,66 @@ def main():
     misc.add_argument("-v", "--version", action="version",
                       version=f"PyamilySeq: Seq-Combiner version {PyamilySeq_Version} - Exiting",
                       help="Print out version number and exit")
+    parser.add_argument("--log", action="store_true", dest="log", help="Create a timestamped logfile for this run.")
+    parser.add_argument("--log-dir", dest="log_dir", default=None, help="Directory for logfile (default: output_dir).")
 
     options = parser.parse_args()
 
+    # Setup logger for Seq-Combiner
+    output_path = os.path.abspath(options.output_dir)
+    if not os.path.exists(output_path):
+        os.makedirs(output_path)
+    log_dir = options.log_dir if getattr(options, "log_dir", None) else output_path
+    logger = configure_logger("PyamilySeq.Seq_Combiner", enable_file=getattr(options, "log", False), log_dir=log_dir, verbose=False)
+
+    # --- Progress reporting setup ------------------------------------------------
+    combined_out_file = os.path.join(output_path, options.output_file)
+    # Determine name_split and extensions per mode and count matching input files as total work units
+    if options.input_type == 'fasta':
+        name_split = options.name_split_fasta
+        exts = ('.fasta', '.fa', '.fna')
+    else:  # 'separate' or 'combined'
+        name_split = options.name_split_gff
+        exts = ('.gff', '.gff3', '.gff.gz', '.gff3.gz')
+
+    total_work = count_matching_files(options.input_dir, name_split, exts)
+    logger.info("Found %d input files (matching pattern) to process in %s", total_work, options.input_dir)
+
+    stop_event = threading.Event()
+    reporter_thread = threading.Thread(target=progress_reporter, args=(stop_event, logger, total_work, combined_out_file, name_split, 10), daemon=True)
+    reporter_thread.start()
+    # ---------------------------------------------------------------------------
 
     if options.input_type == 'separate' and options.name_split_gff is None:
+        logger.error("Please provide a substring to split the filename and extract the genome name.")
         print("Please provide a substring to split the filename and extract the genome name.")
         exit(1)
     if options.input_type == 'combined' and options.name_split_gff is None:
+        logger.error("Please provide a substring to split the filename and extract the genome name.")
         print("Please provide a substring to split the filename and extract the genome name.")
         exit(1)
     if options.input_type == 'fasta' and options.name_split_fasta is None:
+        logger.error("Please provide a substring to split the filename and extract the genome name.")
         print("Please provide a substring to split the filename and extract the genome name.")
         exit(1)
 
-    output_path = os.path.abspath(options.output_dir)
-    if not os.path.exists(output_path):
-        os.makedirs(output_path)
-
-    #output_file = options.output_file + '.fasta'
-    if os.path.exists(os.path.join(output_path, options.output_file)):
-        print(f"Output file {options.output_file} already exists in the output directory. Please delete or rename the file and try again.")
-        exit(1)
-
-    combined_out_file = os.path.join(output_path, options.output_file )
-
     if options.input_type == 'separate':
+        logger.info("Processing 'separate' input_type from %s", options.input_dir)
         read_separate_files(options.input_dir, options.name_split_gff, options.name_split_fasta, options.gene_ident, combined_out_file, options.translate, True)
     elif options.input_type == 'combined':
+        logger.info("Processing 'combined' input_type from %s", options.input_dir)
         read_combined_files(options.input_dir, options.name_split_gff, options.gene_ident, combined_out_file, options.translate, True)
     elif options.input_type == 'fasta':
+        logger.info("Processing 'fasta' input_type from %s", options.input_dir)
         read_fasta_files(options.input_dir, options.name_split_fasta, combined_out_file, options.translate, True)
+    logger.info("Seq-Combiner completed.")
+
+    # Stop reporter and wait for final log
+    stop_event.set()
+    reporter_thread.join(timeout=5)
+    # Final summary: count number of input files represented (heuristic)
+    final_files = count_files_present_in_combined(combined_out_file, name_split)
+    logger.info("Completed combining. Final combined file: %s (input files represented: %d)", combined_out_file, final_files)
 
 if __name__ == "__main__":
     main()

PyamilySeq/Seq_Extractor.py

@@ -1,5 +1,12 @@
-import argparse
+
 import copy
+import os
+
+# Use centralised logger factory
+try:
+    from .constants import configure_logger, LoggingArgumentParser
+except Exception:
+    from constants import configure_logger, LoggingArgumentParser
 
 def find_gene_ids_in_csv(csv_file, group_name):
     """Find gene IDs associated with the specified group name in the CSV file, starting from column 14."""
@@ -39,7 +46,10 @@ def extract_sequences(fasta_file, gene_ids):
     return sequences
 
 def main():
-    parser = argparse.ArgumentParser(description="Extract sequences for specified group name from CSV file and corresponding FASTA file.")
+    # Early console-only logger so parser.description appears in logger output before argparse prints the menu.
+    early_logger = configure_logger("PyamilySeq.Seq_Extractor", enable_file=False, log_dir=None, verbose=False)
+    parser = LoggingArgumentParser(logger_name="PyamilySeq.Seq_Extractor", description="Running Seq-Extractor - A tool to extract sequences for specified group name from CSV file and corresponding FASTA file.")
+
     parser.add_argument("-csv", action='store', dest='csv_file',
                         help="CSV file containing group data", required=True)
     parser.add_argument("-group", action='store', dest='group_name',
@@ -48,22 +58,34 @@ def main():
                         help="Input FASTA file containing sequences", required=True)
     parser.add_argument("-out", action='store', dest='output_file',
                         help="Output FASTA file with extracted sequences", required=True)
+    parser.add_argument("--log", action="store_true", dest="log", help="Create a timestamped logfile for this run.")
+    parser.add_argument("--log-dir", dest="log_dir", default=None, help="Directory for logfile (default: dir of output_file).")
 
     options = parser.parse_args()
 
+    # Setup logger
+    out_dir = os.path.abspath(os.path.dirname(options.output_file)) if options.output_file else os.getcwd()
+    log_dir = options.log_dir if getattr(options, "log_dir", None) else out_dir
+    logger = configure_logger("PyamilySeq.Seq_Extractor", enable_file=getattr(options, "log", False), log_dir=log_dir, verbose=False)
+
+    logger.info("Searching for gene IDs in CSV %s for group %s", options.csv_file, options.group_name)
+
     # Find gene IDs in CSV
     gene_ids = find_gene_ids_in_csv(options.csv_file, options.group_name)
     if not gene_ids:
+        logger.warning("No gene IDs found for group name '%s' in the CSV.", options.group_name)
         print(f"No gene IDs found for group name '{options.group_name}' in the CSV.")
         return
 
     # Extract sequences from the FASTA file
+    logger.info("Extracting sequences from FASTA: %s", options.fasta_file)
     sequences = extract_sequences(options.fasta_file, gene_ids)
 
     # Write matched sequences to the output FASTA file
     with open(options.output_file, 'w') as output:
         for gene_id, sequence_lines in sequences.items():
             output.write("\n".join(sequence_lines) + "\n")
+    logger.info("Wrote %d sequences to %s", len(sequences), options.output_file)
 
 if __name__ == "__main__":
     main()