also generating a partitions file in nexus format now, thanks to note from @Stian-2rz (#108)

Author: Mike Lee

bin/GToTree

@@ -5,7 +5,7 @@ GREEN='\033[0;32m'
 RED='\033[0;31m'
 YELLOW='\033[0;33m'
 NC='\033[0m'
-VERSION="v1.8.14"
+VERSION="v1.8.15"
 
 if [ "$1" == "--version" ] || [ "$1" == "-v" ]; then
     printf "GToTree ${VERSION}\n"
@@ -2643,11 +2643,11 @@ duration=$SECONDS
 printf "           It is currently $curr_time; the process started at $start_time.\n" | tee >( sed 's/\x1b\[[0-9;]*m//g' >> ${gtotree_log} )
 printf "               Current process runtime: $(($duration / 60 / 60)) hours and $((($duration / 60) % 60)) minutes.\n\n" | tee >( sed 's/\x1b\[[0-9;]*m//g' >> ${gtotree_log} )
 
-# this concatenates the alignments and generates the partitions file for mixed model alignments
+# this concatenates the alignments and generates the partitions file for mixed-model treeing
 if [ $nucleotide != 'false' ]; then
-    gtt-cat-alignments -t $tmp_dir -o $output_dir --nucleotides
+    gtt-cat-alignments -t $tmp_dir -o ${output_dir} --nucleotides
 else
-    gtt-cat-alignments -t $tmp_dir -o $output_dir
+    gtt-cat-alignments -t $tmp_dir -o ${output_dir}
 fi
 
 # storing genomes that made it through workflow to report at end
@@ -3693,8 +3693,8 @@ if [ $additional_pfam_targets == 'true' ]; then
 fi
 
 printf "    Partitions file (for downstream use with mixed-model treeing) written to:\n" | tee >( sed 's/\x1b\[[0-9;]*m//g' >> ${gtotree_log} )
-printf "        ${GREEN}${output_dir}/run_files/Partitions.txt${NC}\n\n" | tee >( sed 's/\x1b\[[0-9;]*m//g' >> ${gtotree_log} )
-mv ${output_dir}/Partitions.txt ${output_dir}/run_files/Partitions.txt
+printf "        ${GREEN}${output_dir}/run_files/Partitions.txt${NC}\n" | tee >( sed 's/\x1b\[[0-9;]*m//g' >> ${gtotree_log} )
+printf "        ${GREEN}${output_dir}/run_files/Partitions.nex${NC}\n\n" | tee >( sed 's/\x1b\[[0-9;]*m//g' >> ${gtotree_log} )
 
 # reporting any problem files/accessions and mentioning run_files/ directory
 printf " _______________________________________________________________________________\n\n" | tee >( sed 's/\x1b\[[0-9;]*m//g' >> ${gtotree_log} )

bin/gtt-cat-alignments

@@ -5,12 +5,12 @@ from glob import glob
 import argparse
 import os.path
 
-parser = argparse.ArgumentParser(description='This script is a helper script to concatenate fasta-formatted multiple sequence alignment files, and generate partitions file.')
+parser = argparse.ArgumentParser(description='This script is a helper to concatenate fasta-formatted multiple sequence alignment files and generate the partitions files.')
 
 required = parser.add_argument_group('required arguments')
 
 required.add_argument("-t", "--tmp-dir", help="The working tmp_dir for the current GToTree run", action="store", dest="tmp_dir", required=True)
-required.add_argument("-o", "--output-dir", help="The output_dir for the current GToTree run", action="store", dest="output_dir", required=True)
+required.add_argument("-o", "--output-dir", help="The wanted output dir", action="store", dest="output_dir", required=True)
 parser.add_argument("--nucleotides", help="Provide this flag if user specified nucleotide mode", action="store_true")
 
 
@@ -83,13 +83,36 @@ alignment_lengths_list = [len(x) for x in list(dict_of_genomes.values())[0]]
 curr_start = 1
 curr_stop = 0
 
-with open(output_dir + "Partitions.txt", "w") as out:
+partitions_txt_file = output_dir + "/run_files/Partitions.txt"
+partitions_nex_file = output_dir + "/run_files/Partitions.nex"
+
+with open(partitions_txt_file, "w") as out:
     for i in range(0,len(gene_list)):
         curr_stop = curr_start + alignment_lengths_list[i] - 1
 
         if not args.nucleotides:
             out.write("AA, " + str(gene_list[i]) + " = " + str(curr_start) + "-" + str(curr_stop) + "\n")
-            curr_start = curr_stop + 6    
+            curr_start = curr_stop + 6
         else:
             out.write("DNA, " + str(gene_list[i]) + " = " + str(curr_start) + "-" + str(curr_stop) + "\n")
             curr_start = curr_stop + 7
+
+# writing out a nex formatted partitions file
+    # thanks to @Stian-2rz on github: https://github.com/AstrobioMike/GToTree/issues/108
+
+with open(partitions_txt_file) as f:
+    lines = [line.strip() for line in f if line.strip()]
+
+with open(partitions_nex_file, "w") as f:
+    f.write("#NEXUS\n")
+    f.write("begin sets;\n")
+    for line in lines:
+        parts = line.split(',')
+        if len(parts) != 2:
+            continue
+        _, rest = parts
+        name, coords = rest.split('=')
+        name = name.strip().replace(" ", "_")
+        coords = coords.strip()
+        f.write(f"  charset {name} = {coords};\n")
+    f.write("end;\n")

bin/gtt-gen-SCG-HMMs

@@ -8,7 +8,7 @@ For examples, please visit the GToTree wiki here: https://github.com/AstrobioMik
 For details on the process, please see: https://github.com/AstrobioMike/GToTree/wiki/SCG-sets
 """
 
-VERSION="v1.8.14"
+VERSION="v1.8.15"
 import os
 import re
 import sys

bin/gtt-pfam-search

@@ -5,7 +5,7 @@ GREEN='\033[0;32m'
 RED='\033[0;31m'
 YELLOW='\033[0;33m'
 NC='\033[0m'
-VERSION="v1.8.14"
+VERSION="v1.8.15"
 
 printf "\n\n                                  GToTree ${VERSION}\n"
 printf "                         (github.com/AstrobioMike/GToTree)\n\n"