treesak 1.53.3__py3-none-any.whl

TreeSAK/ALE.py

@@ -0,0 +1,63 @@
+
+ALE_usage = '''
+================================================= ALE example commands =================================================
+
+# ALE modules
+TreeSAK ALE1         -> Step 1: get gene tree
+TreeSAK ALE2         -> Step 2: run ALE
+TreeSAK ALE3         -> Step 3: parse ALE outputs (ancestral genome reconstruction, transfer propensity/verticality and gain/loss)
+TreeSAK ALE4         -> Filter ALE identified HGTs
+TreeSAK ALE5         -> Get RTC file based on ALE detected HGTs
+TreeSAK SingleAleHGT -> Perform HGT analysis using ALE for single protein family
+TreeSAK ALE6         -> faa ancestral genomes
+TreeSAK ALE7         -> get function P/A in ancestral genomes
+
+# Example commands
+TreeSAK ALE1 -i OrthologousGroups.txt -s combined_d__Archaea_o_rs.faa -p oma -m 50 -t 12 -jst 3 -f -o ALE1_op_dir
+TreeSAK ALE2 -i ALE1_op_dir -s genome_tree_rooted_noEU.treefile -t 10 -f -o ALE2_op_dir -runALE -docker gregmich/alesuite_new
+TreeSAK ALE3 -i ALE2_op_dir -o ALE3_op_dir_c0.75 -f -c 0.75
+TreeSAK ALE4 -i1 ALE1_op_dir -i2 ALE2_op_dir -c genome_taxon.txt -color phylum_color.txt -o ALE4_op_dir_0.3 -fc 0.3 -f -api your_own_itol_api
+TreeSAK ALE4 -i1 ALE1_op_dir -i2 ALE2_op_dir -c genome_taxon.txt -color phylum_color.txt -o ALE4_op_dir_0.5 -fc 0.5 -f -api your_own_itol_api
+TreeSAK ALE4 -i1 ALE1_op_dir -i2 ALE2_op_dir -c genome_taxon.txt -color phylum_color.txt -o ALE4_op_dir_0.8 -fc 0.8 -f -api your_own_itol_api
+TreeSAK ALE7 -6 ALE6_op_dir -fun ko.txt -node internal_node.txt -o Fun_PA.txt
+TreeSAK ALE7 -6 ALE6_op_dir -fun K01995,K01995 -node 359,466,470 -o Fun_PA.txt
+TreeSAK ALE7 -6 ALE6_op_dir -fun arCOG07811,K01995 -node 359,466,470 -o Fun_PA.txt
+TreeSAK SingleAleHGT -i OMA00001.aln -s genome.treefile -fc 0.3 -c genome_taxon.txt -color phylum_color.txt -api S1kZZuDHc0d5M7J5vLnUNQ -t 9 -f -o OMA00001_ALE_HGT_wd
+
+Note:
+Genome names should NOT contain "_".
+
+========================================================================================================================
+'''
+
+'''
+cd /Users/songweizhi/Desktop/run_ALE_wd
+TreeSAK ALE2 -i ALE1_op_dir -s genome_tree_rooted_noEU.treefile -t 10 -f -o ALE2_op_dir -runALE -docker gregmich/alesuite_new
+TreeSAK ALE3 -i ALE2_op_dir -c 0.8 -f -o ALE3_op_dir
+TreeSAK ALE4 -i1 ALE1_op_dir -i2 ALE2_op_dir -c genome_taxon.txt -color phylum_color.txt -o ALE4_op_dir_0.3 -fc 0.3 -f -api S1kZZuDHc0d5M7J5vLnUNQ
+TreeSAK ALE4 -i1 ALE1_op_dir -i2 ALE2_op_dir -c genome_taxon.txt -color phylum_color.txt -o ALE4_op_dir_0.5 -fc 0.5 -f -api S1kZZuDHc0d5M7J5vLnUNQ
+TreeSAK ALE4 -i1 ALE1_op_dir -i2 ALE2_op_dir -c genome_taxon.txt -color phylum_color.txt -o ALE4_op_dir_0.8 -fc 0.8 -f -api S1kZZuDHc0d5M7J5vLnUNQ
+
+python3 /Users/songweizhi/PycharmProjects/TreeSAK/TreeSAK/ALE4.py -i1 ALE1_op_dir -i2 ALE2_op_dir -c genome_taxon.txt -color phylum_color.txt -o ALE4_op_dir_0.3 -fc 0.3 -f -api S1kZZuDHc0d5M7J5vLnUNQ
+python3 /Users/songweizhi/PycharmProjects/TreeSAK/TreeSAK/ALE4.py -i1 ALE1_op_dir -i2 ALE2_op_dir -c genome_taxon.txt -color phylum_color.txt -o ALE4_op_dir_0.5 -fc 0.5 -f -api S1kZZuDHc0d5M7J5vLnUNQ
+python3 /Users/songweizhi/PycharmProjects/TreeSAK/TreeSAK/ALE4.py -i1 ALE1_op_dir -i2 ALE2_op_dir -c genome_taxon.txt -color phylum_color.txt -o ALE4_op_dir_0.8 -fc 0.8 -f -api S1kZZuDHc0d5M7J5vLnUNQ
+python3 /Users/songweizhi/PycharmProjects/TreeSAK/TreeSAK/ALE3.py -i ALE2_op_dir -c 0.8 -f -o ALE3_op_dir
+'''
+
+'''
+cd /Users/songweizhi/Documents/Research/Sponge_Hologenome/6_ALE_wd
+python3 /Users/songweizhi/PycharmProjects/TreeSAK/TreeSAK/ALE1.py -i OMA_op_filtered/OrthologousGroups.txt -s OMA_op_filtered/OrthologousGroups.fasta -p oma -m 3 -t 10 -jt 2 -f -o ALE1_op_dir
+TreeSAK ALE2 -i ALE1_op_dir -s genome_tree_rooted_noEU.treefile -t 10 -f -o ALE2_op_dir -runALE -docker gregmich/alesuite_new
+
+cd /Users/songweizhi/Documents/Research/Sponge_Hologenome/8_ALE_wd_all_OGs
+TreeSAK ALE2 -i ALE1_op_dir_ufboot -s concatenated_rooted.treefile -t 10 -f -o ALE2_op_dir -runALE -docker gregmich/alesuite_new
+
+cd /home-user/wzsong/tmp
+TreeSAK ALE2 -i ALE1_op_dir_ufboot -s concatenated_rooted.treefile -t 32 -f -o ALE2_op_dir -runALE -docker gregmich/alesuite_new
+
+cd /Users/songweizhi/Documents/Research/Sponge_Hologenome/8_ALE_wd_all_OGs
+TreeSAK ALE3 -i ALE2_op_dir -o ALE3_op_dir_c0.75 -f -c 0.75
+
+cd /Users/songweizhi/Documents/Research/Sponge_Hologenome/8_ALE_wd_all_OGs
+/usr/local/bin/python3.7 /Users/songweizhi/PycharmProjects/TreeSAK/TreeSAK/ALE3.py -i ALE2_op_dir -o ALE3_op_dir_c0.75 -f -c 0.75 -a ALE1_arcog_description.txt
+'''

TreeSAK/ALE1.py

@@ -0,0 +1,268 @@
+import os
+import glob
+import argparse
+from Bio import SeqIO
+from ete3 import Tree
+from distutils.spawn import find_executable
+
+
+ALE1_usage = '''
+====================================== ALE1 example commands ======================================
+
+TreeSAK ALE1 -i OrthologousGroups.txt -s combined.faa -p oma -m 50 -jst 3 -f -o ALE1_op_dir -bmge
+TreeSAK ALE1 -ms s03_marker_seq -msx fa -p marker_set_1 -m 50 -jst 3 -f -o ALE1_op_dir -bmge
+
+===================================================================================================
+'''
+
+
+def check_dependencies(program_list):
+
+    not_detected_programs = []
+    for needed_program in program_list:
+        if find_executable(needed_program) is None:
+            not_detected_programs.append(needed_program)
+
+    if not_detected_programs != []:
+        print('%s not found, program exited!' % ','.join(not_detected_programs))
+        exit()
+
+
+def sep_path_basename_ext(file_in):
+
+    f_path, file_name = os.path.split(file_in)
+    if f_path == '':
+        f_path = '.'
+
+    f_base, f_ext = os.path.splitext(file_name)
+
+    return f_path, f_base, f_ext
+
+
+def subset_tree(tree_file_in, leaves_to_keep_list, tree_file_out):
+
+    input_tree = Tree(tree_file_in)
+    subset_tree = input_tree.copy()
+    subset_tree.prune(leaves_to_keep_list, preserve_branch_length=True)
+    if tree_file_out is None:
+        return subset_tree.write()
+    else:
+        subset_tree.write(outfile=tree_file_out)
+
+
+def get_ortho_to_gene_dict(ortho_groups_txt, og_program):
+
+    ortho_to_gene_dict = dict()
+    for each_og in open(ortho_groups_txt):
+        if not each_og.startswith('#'):
+            og_id = ''
+            gene_list = []
+            if og_program == 'orthofinder':
+                each_og_split = each_og.strip().split(' ')
+                og_id = each_og_split[0][:-1]
+                gene_list = each_og_split[1:]
+            elif og_program == 'oma':
+                each_og_split = each_og.strip().split('\t')
+                og_id = each_og_split[0]
+                group_member_list = each_og_split[1:]
+                for each_protein in group_member_list:
+                    protein_id = each_protein.split(' ')[0].split(':')[1]
+                    gene_list.append(protein_id)
+            ortho_to_gene_dict[og_id] = gene_list
+
+    return ortho_to_gene_dict
+
+
+def ALE1(args):
+
+    orthogroups_op_txt          = args['i']
+    combined_faa                = args['s']
+    og_program                  = args['p']
+    marker_seq_dir              = args['ms']
+    marker_seq_ext              = args['msx']
+    min_og_genome_num           = args['m']
+    js_num_threads              = args['jst']
+    force_create_op_dir         = args['f']
+    op_dir                      = args['o']
+    trim_with_bmge              = args['bmge']
+    bmge_trim_model             = args['bmge_m']
+    bmge_entropy_score_cutoff   = args['bmge_esc']
+    designate_ogs               = []
+    to_ignore_ogs_list          = []
+
+    # check dependencies
+    check_dependencies(['java', 'blastp', 'mafft-einsi'])
+
+    # specify path to BMGE.jar
+    current_file_path = '/'.join(os.path.realpath(__file__).split('/')[:-1])
+    pwd_bmge_jar      = '%s/BMGE.jar' % current_file_path
+
+    # define output file name
+    get_gene_tree_cmds_txt = '%s_cmds.txt' % op_dir
+
+    # determine the version of iqtree available on the system
+    if find_executable('iqtree2'):
+        iqtree_exe = 'iqtree2'
+    elif find_executable('iqtree'):
+        iqtree_exe = 'iqtree'
+    else:
+        print('iqtree not detected, program exited!')
+        exit()
+
+    # create op_dir
+    if os.path.isdir(op_dir) is True:
+        if force_create_op_dir is True:
+            os.system('rm -r %s' % op_dir)
+        else:
+            print('Output folder detected, program exited!')
+            exit()
+    os.system('mkdir %s' % op_dir)
+
+    if (orthogroups_op_txt is not None) and (combined_faa is not None) and (marker_seq_dir is None):
+
+        # get ortho_to_gene_dict
+        ortho_to_gene_dict = get_ortho_to_gene_dict(orthogroups_op_txt, og_program)
+
+        # get qualified orthogroups
+        qualified_og_set = set()
+        for each_ortho in ortho_to_gene_dict:
+            ortho_gene_set = ortho_to_gene_dict[each_ortho]
+            ortho_gnm_set = set()
+            for each_gene in ortho_gene_set:
+                gene_gnm = '_'.join(each_gene.split('_')[:-1])
+                ortho_gnm_set.add(gene_gnm)
+            if len(ortho_gnm_set) >= min_og_genome_num:
+                qualified_og_set.add(each_ortho)
+        print('The total number of identified orthogroups is %s.' % len(ortho_to_gene_dict))
+        print('The number of orthogroups spanning >= %s genomes is %s.' % (min_og_genome_num, len(qualified_og_set)))
+
+        # process qualified OG
+        og_to_process = sorted([i for i in qualified_og_set])
+        if len(designate_ogs) > 0:
+            print('The number of designated OGs to process: %s' % len(designate_ogs))
+            og_to_process = designate_ogs
+
+        og_to_process_no_ignored = set()
+        for each_og in og_to_process:
+            if each_og not in to_ignore_ogs_list:
+                og_to_process_no_ignored.add(each_og)
+
+        # read sequence into dict
+        gene_seq_dict = dict()
+        for each_seq in SeqIO.parse(combined_faa, 'fasta'):
+            seq_id = each_seq.id
+            gene_seq_dict[seq_id] = str(each_seq.seq)
+
+        # extract gene sequences and prepare commands for building gene tree
+        print('Preparing commands and sequence files for building gene trees')
+        get_gene_tree_cmds_txt_handle = open(get_gene_tree_cmds_txt, 'w')
+        for qualified_og in sorted(og_to_process_no_ignored):
+            qualified_og_gene_set = ortho_to_gene_dict[qualified_og]
+            qualified_og_gene_faa = '%s/%s.faa' % (op_dir, qualified_og)
+
+            og_aln          = '%s.aln'          % qualified_og
+            og_aln_trimmed  = '%s_trimmed.aln'  % qualified_og
+
+            # write out commands
+            mafft_cmd       = 'mafft-einsi --thread %s --quiet %s.faa > %s'         % (js_num_threads, qualified_og, og_aln)
+            trim_cmd        = 'java -jar %s -i %s -m %s -t AA -h %s -of %s'         % (pwd_bmge_jar, og_aln, bmge_trim_model, bmge_entropy_score_cutoff, og_aln_trimmed)
+            iqtree_cmd      = '%s -m LG+G+I -bb 1000 --wbtl -nt %s -s %s -pre %s'   % (iqtree_exe, js_num_threads, og_aln, qualified_og)
+            if trim_with_bmge is True:
+                iqtree_cmd  = '%s -m LG+G+I -bb 1000 --wbtl -nt %s -s %s -pre %s'   % (iqtree_exe, js_num_threads, og_aln_trimmed, qualified_og)
+
+            if trim_with_bmge is True:
+                get_gene_tree_cmds_txt_handle.write('%s; %s; %s\n' % (mafft_cmd, trim_cmd, iqtree_cmd))
+            else:
+                get_gene_tree_cmds_txt_handle.write('%s; %s\n' % (mafft_cmd, iqtree_cmd))
+
+            # write out sequences
+            qualified_og_gene_faa_handle = open(qualified_og_gene_faa, 'w')
+            for each_gene in qualified_og_gene_set:
+                qualified_og_gene_faa_handle.write('>%s\n' % each_gene)
+                qualified_og_gene_faa_handle.write('%s\n' % gene_seq_dict[each_gene])
+            qualified_og_gene_faa_handle.close()
+        get_gene_tree_cmds_txt_handle.close()
+
+    elif (orthogroups_op_txt is None) and (combined_faa is None) and (marker_seq_dir is not None):
+
+        marker_seq_re = '%s/*.%s' % (marker_seq_dir, marker_seq_ext)
+        marker_seq_list = glob.glob(marker_seq_re)
+
+        marker_to_gene_dict = dict()
+        for each_file in marker_seq_list:
+            _, f_base, _ = sep_path_basename_ext(each_file)
+            marker_to_gene_dict[f_base] = set()
+            for each_seq in SeqIO.parse(each_file, 'fasta'):
+                marker_to_gene_dict[f_base].add(each_seq.id)
+
+        # get qualified orthogroups
+        qualified_og_set = set()
+        for each_ortho in marker_to_gene_dict:
+            ortho_gene_set = marker_to_gene_dict[each_ortho]
+            ortho_gnm_set = set()
+            for each_gene in ortho_gene_set:
+                gene_gnm = '_'.join(each_gene.split('_')[:-1])
+                ortho_gnm_set.add(gene_gnm)
+            if len(ortho_gnm_set) >= min_og_genome_num:
+                qualified_og_set.add(each_ortho)
+        print('The total number of identified orthogroups is %s.'       % len(marker_to_gene_dict))
+        print('The number of orthogroups spanning >= %s genomes is %s.' % (min_og_genome_num, len(qualified_og_set)))
+
+        # process qualified OG
+        og_to_process = sorted([i for i in qualified_og_set])
+        if len(designate_ogs) > 0:
+            print('The number of designated OGs to process: %s' % len(designate_ogs))
+            og_to_process = designate_ogs
+
+        og_to_process_no_ignored = set()
+        for each_og in og_to_process:
+            if each_og not in to_ignore_ogs_list:
+                og_to_process_no_ignored.add(each_og)
+
+        # extract gene sequences and prepare commands for building gene tree
+        print('Preparing commands for building gene trees')
+        get_gene_tree_cmds_txt_handle = open(get_gene_tree_cmds_txt, 'w')
+        for qualified_og in sorted(og_to_process_no_ignored):
+
+            # copy sequence file into output directory
+            os.system('cp %s/%s.%s %s/' % (marker_seq_dir, qualified_og, marker_seq_ext, op_dir))
+
+            qualified_og_aln          = '%s.aln'          % qualified_og
+            qualified_og_aln_trimmed  = '%s_trimmed.aln'  % qualified_og
+
+            # write out commands
+            mafft_cmd  = 'mafft-einsi --thread %s --quiet %s.%s > %s'               % (js_num_threads, qualified_og, marker_seq_ext, qualified_og_aln)
+            trim_cmd   = 'java -jar %s -i %s -m %s -t AA -h %s -of %s'              % (pwd_bmge_jar, qualified_og_aln, bmge_trim_model, bmge_entropy_score_cutoff, qualified_og_aln_trimmed)
+            iqtree_cmd = '%s -m LG+G+I -bb 1000 --wbtl -nt %s -s %s -pre %s'        % (iqtree_exe, js_num_threads, qualified_og_aln, qualified_og)
+            if trim_with_bmge is True:
+                iqtree_cmd = '%s -m LG+G+I -bb 1000 --wbtl -nt %s -s %s -pre %s'    % (iqtree_exe, js_num_threads, qualified_og_aln_trimmed, qualified_og)
+
+            if trim_with_bmge is False:
+                get_gene_tree_cmds_txt_handle.write('%s; %s\n' % (mafft_cmd, iqtree_cmd))
+            else:
+                get_gene_tree_cmds_txt_handle.write('%s; %s; %s\n' % (mafft_cmd, trim_cmd, iqtree_cmd))
+
+        get_gene_tree_cmds_txt_handle.close()
+
+    print('Sequece files exported to %s.'                       % op_dir)
+    print('Commands for inferring gene tree exported to %s.'    % get_gene_tree_cmds_txt)
+    print('Done!')
+
+
+if __name__ == '__main__':
+
+    ALE1_parser = argparse.ArgumentParser()
+    ALE1_parser.add_argument('-i',          required=False, default=None,          help='orthologous groups, either from orthofinder or oma')
+    ALE1_parser.add_argument('-s',          required=False, default=None,          help='sequence file, e.g., combined.faa')
+    ALE1_parser.add_argument('-ms',         required=False, default=None,          help='input is a folder holds the sequence of each marker')
+    ALE1_parser.add_argument('-msx',        required=False, default='fa',          help='file extension of marker sequence file, default: fa')
+    ALE1_parser.add_argument('-p',          required=True,                         help='orthologous identification program, orthofinder or oma')
+    ALE1_parser.add_argument('-m',          required=False, type=int, default=50,  help='min_og_genome_num, default: 50')
+    ALE1_parser.add_argument('-bmge',       required=False, action="store_true",   help='trim MSA with BMGE, default no trimming')
+    ALE1_parser.add_argument('-bmge_m',     required=False, default='BLOSUM30',    help='BMGE trim model, default: BLOSUM30')
+    ALE1_parser.add_argument('-bmge_esc',   required=False, default='0.55',        help='BMGE entropy score cutoff, default: 0.55')
+    ALE1_parser.add_argument('-o',          required=True,                         help='output dir, i.e., OMA working directory')
+    ALE1_parser.add_argument('-jst',        required=False, type=int, default=3,   help='number of threads specified in job script, default: 3')
+    ALE1_parser.add_argument('-f',          required=False, action="store_true",   help='force overwrite')
+    args = vars(ALE1_parser.parse_args())
+    ALE1(args)

TreeSAK/ALE2.py

@@ -0,0 +1,168 @@
+import os
+import glob
+import argparse
+from ete3 import Tree
+import multiprocessing as mp
+
+
+ALE2_usage = '''
+============================================ ALE2 example commands ===========================================
+
+TreeSAK ALE2 -1 ALE1_op_dir -s genome.treefile -t 10 -f -runALE -docker gregmich/alesuite_new -o ALE2_op_dir
+
+Note: 
+Genome names should NOT contain "_", the program will tackle this automatically.
+
+# You can try to add this while building the docker images
+--platform linux/arm64/v8
+
+# Only the ufboot files in ALE1_op_dir will be needed in this step.
+
+===============================================================================================================
+'''
+
+
+def sep_path_basename_ext(file_in):
+
+    # separate path and file name
+    f_path, file_name = os.path.split(file_in)
+    if f_path == '':
+        f_path = '.'
+
+    # separate file basename and extension
+    f_base, f_ext = os.path.splitext(file_name)
+
+    return f_path, f_base, f_ext
+
+
+def subset_tree(tree_file_in, leaves_to_keep_list, tree_file_out):
+
+    input_tree = Tree(tree_file_in)
+    subset_tree = input_tree.copy()
+    subset_tree.prune(leaves_to_keep_list, preserve_branch_length=True)
+    if tree_file_out is None:
+        return subset_tree.write()
+    else:
+        subset_tree.write(outfile=tree_file_out)
+
+
+def prepare_ale_ip_worker(arg_list):
+
+    ufboot_in   = arg_list[0]
+    ufboot_out  = arg_list[1]
+
+    ufboot_out_handle = open(ufboot_out, 'w')
+    for each_gene_tree in open(ufboot_in):
+        gene_tree_str = each_gene_tree.strip()
+        gene_tree_in = Tree(gene_tree_str, format=1)
+        for leaf in gene_tree_in:
+            leaf_name_split = leaf.name.split('_')
+            gnm_id = '_'.join(leaf_name_split[:-1])
+            gene_index = leaf_name_split[-1]
+            gnm_id_renamed = gnm_id.replace('_', '')
+            gene_id_renamed = '%s_%s' % (gnm_id_renamed, gene_index)
+            leaf.name = gene_id_renamed
+        gene_tree_str_renamed = gene_tree_in.write()
+        ufboot_out_handle.write(gene_tree_str_renamed + '\n')
+    ufboot_out_handle.close()
+
+
+def ALE2(args):
+
+    ale1_op_dir             = args['1']
+    genome_tree_file_rooted = args['s']
+    force_create_ale_wd     = args['f']
+    num_threads             = args['t']
+    ale2_op_dir             = args['o']
+    run_ale                 = args['runALE']
+    docker_image            = args['docker']
+    run_ale_cmds_txt        = '%s_cmds.txt'     % ale2_op_dir
+
+    ufboot_file_re   = '%s/*.ufboot' % ale1_op_dir
+    ufboot_file_list = glob.glob(ufboot_file_re)
+    og_to_process_list = []
+    for each_ufboot in ufboot_file_list:
+        _, ufboot_base, _ = sep_path_basename_ext(each_ufboot)
+        og_to_process_list.append(ufboot_base)
+
+    # define file name
+    gnm_tree_no_underscore       = 'genome_tree.newick'
+    gnm_tree_leaf_rename_txt     = 'genome_tree_leaf_rename.txt'
+    gnm_tree_no_underscore_in_wd = '%s/%s' % (ale2_op_dir, gnm_tree_no_underscore)
+
+    # create ale2_op_dir
+    if force_create_ale_wd is True:
+        if os.path.isdir(ale2_op_dir) is True:
+            os.system('rm -r %s' % ale2_op_dir)
+    os.system('mkdir %s' % ale2_op_dir)
+
+    # prepare genome tree for running ALE
+    gnm_tree_leaf_rename_txt_handle = open(gnm_tree_leaf_rename_txt, 'w')
+    gnm_tree_in = Tree(genome_tree_file_rooted, format=1)
+    rename_dict = dict()
+    for leaf in gnm_tree_in:
+        leaf_name = leaf.name
+        leaf_name_new = leaf_name.replace('_', '')
+        gnm_tree_leaf_rename_txt_handle.write('%s\t%s\n' % (leaf_name_new, leaf.name))
+        leaf.name = leaf_name_new
+        rename_dict[leaf_name] = leaf_name_new
+    gnm_tree_leaf_rename_txt_handle.close()
+
+    gnm_tree_in.write(outfile=gnm_tree_no_underscore_in_wd)
+
+    # prepare gene tree for running ALE
+    run_ale_cmds_txt_handle = open(run_ale_cmds_txt, 'w')
+    prepare_ale_ip_worker_arg_lol = []
+    ale_cmd_list = []
+    for qualified_og in og_to_process_list:
+        pwd_gene_tree_ufboot = '%s/%s.ufboot' % (ale1_op_dir, qualified_og)
+        if os.path.isfile(pwd_gene_tree_ufboot) is False:
+            print('%s not found, please build gene tree first!' % pwd_gene_tree_ufboot)
+        else:
+            pwd_gene_tree_ufboot_in     = '%s/%s.ufboot'                                            % (ale1_op_dir, qualified_og)
+            pwd_gene_tree_ufboot_out    = '%s/%s.ufboot'                                            % (ale2_op_dir, qualified_og)
+
+            # get commands for ALEobserve and ALEml_undated
+            obtain_ale_file_cmd         = 'ALEobserve %s.ufboot > %s.ALEobserve.log'                % (qualified_og, qualified_og)
+            reconciliation_cmd          = 'ALEml_undated %s %s.ufboot.ale > %s.ALEml_undated.log'   % (gnm_tree_no_underscore, qualified_og, qualified_og)
+            if docker_image is not None:
+                obtain_ale_file_cmd     = 'docker run -v $PWD:$PWD -w $PWD %s %s'                   % (docker_image, obtain_ale_file_cmd)
+                reconciliation_cmd      = 'docker run -v $PWD:$PWD -w $PWD %s %s'                   % (docker_image, reconciliation_cmd)
+
+            current_arg_list = [pwd_gene_tree_ufboot_in, pwd_gene_tree_ufboot_out]
+            run_ale_cmds_txt_handle.write('%s; %s\n' % (obtain_ale_file_cmd, reconciliation_cmd))
+            ale_cmd_list.append('%s; %s\n' % (obtain_ale_file_cmd, reconciliation_cmd))
+            prepare_ale_ip_worker_arg_lol.append(current_arg_list)
+    run_ale_cmds_txt_handle.close()
+
+    # prepare input files and job script for running ALE with multiprocessing
+    print('Preparing files for running ALE with %s cores for %s OGs' % (num_threads, len(prepare_ale_ip_worker_arg_lol)))
+    pool = mp.Pool(processes=num_threads)
+    pool.map(prepare_ale_ip_worker, prepare_ale_ip_worker_arg_lol)
+    pool.close()
+    pool.join()
+
+    # run ALE
+    if run_ale is True:
+        print('running ALE with %s cores for %s OGs' % (num_threads, len(prepare_ale_ip_worker_arg_lol)))
+        os.chdir(ale2_op_dir)
+        pool = mp.Pool(processes=num_threads)
+        pool.map(os.system, ale_cmd_list)
+        pool.close()
+        pool.join()
+
+    print('Done!')
+
+
+if __name__ == '__main__':
+
+    ALE2_parser = argparse.ArgumentParser()
+    ALE2_parser.add_argument('-1',      required=True,                         help='ALE1 output directory')
+    ALE2_parser.add_argument('-s',      required=True,                         help='rooted species tree')
+    ALE2_parser.add_argument('-o',      required=True,                         help='output dir, i.e., OMA working directory')
+    ALE2_parser.add_argument('-runALE', required=False, action="store_true",   help='run ALE')
+    ALE2_parser.add_argument('-docker', required=False, default=None,          help='Docker image, if ALE was installed with Docker, e.g., gregmich/alesuite_new')
+    ALE2_parser.add_argument('-f',      required=False, action="store_true",   help='force overwrite')
+    ALE2_parser.add_argument('-t',      required=False, type=int, default=6,   help='number of threads, default: 6')
+    args = vars(ALE2_parser.parse_args())
+    ALE2(args)

TreeSAK/ALE2RTC.py

@@ -0,0 +1,30 @@
+import os
+import argparse
+
+
+ALE2RTC_usage = '''
+================================ ALE2RTC example commands ================================
+
+TreeSAK ALE2RTC -h
+
+==========================================================================================
+'''
+
+
+def ALE2RTC():
+
+    pass
+
+    # file_in     = args['i']
+    # op_dir      = args['o']
+
+
+# if __name__ == '__main__':
+#
+#     ALE2RTC_parser = argparse.ArgumentParser()
+#     ALE2RTC_parser.add_argument('-i',     required=True,                   help='the file "out" generated by MCMCTree')
+#     ALE2RTC_parser.add_argument('-o',     required=True,                   help='output directory, which will be the input to the pRTC module (-rrtc)')
+#     args = vars(ALE2RTC_parser.parse_args())
+#     ALE2RTC(args)
+
+ALE2RTC()