treesak 1.51.2__py3-none-any.whl

TreeSAK/SingleAleHGT.py

@@ -0,0 +1,157 @@
+import os
+import argparse
+
+
+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
+
+
+SingleAleHGT_usage = '''
+============================================ SingleAleHGT example commands ============================================
+
+TreeSAK SingleAleHGT -i concatenated.fasta -s genome.treefile -fc 0.3 -c genome_taxon.txt -color phylum_color.txt -api S1kZZuDHc0d5M7J5vLnUNQ -t 9 -f -o demo_SingleAleHGT_wd
+
+=======================================================================================================================
+'''
+
+def SingleAleHGT(args):
+
+    faa_in                      = args['faa']
+    msa_in                      = args['msa']
+    op_dir                      = args['o']
+    genome_tree_file_rooted     = args['s']
+    API_key                     = args['api']
+    hgt_freq_cutoff             = args['fc']
+    ar_phylum_color_code_txt    = args['color']
+    genome_taxon_txt            = args['c']
+    force_overwrite             = args['f']
+    trim_msa                    = args['trim']
+    docker_image                = args['docker']
+    num_threads                 = args['t']
+
+    ######################################## check input files #######################################
+
+    # if docker_image is True, check if docker is activated
+    if (faa_in is not None) and (msa_in is None):
+        f_path, f_base, f_ext = sep_path_basename_ext(faa_in)
+    elif (faa_in is None) and (msa_in is not None):
+        f_path, f_base, f_ext = sep_path_basename_ext(msa_in)
+    else:
+        print('Please specify either -faa or -msa, program exited!')
+        exit()
+
+    ######################################## define file name ########################################
+
+    ale1_op_dir = '%s/ALE1_op_dir'      % op_dir
+    ale2_op_dir = '%s/ALE2_op_dir'      % op_dir
+    ale4_op_dir = '%s/ALE4_op_dir'      % op_dir
+    log_txt     = '%s/log.txt'          % op_dir
+    msa_file    = '%s/%s.aln'           % (ale1_op_dir, f_base)
+    msa_trimmed = '%s/%s_trimmed.aln'   % (ale1_op_dir, f_base)
+    tree_prefix = '%s/%s'               % (ale1_op_dir, f_base)
+
+    ###################################### create output folder ######################################
+
+    if os.path.isdir(op_dir) is True:
+        if force_overwrite is True:
+            os.system('rm -r %s' % op_dir)
+        else:
+            print('%s exist, program exited!' % op_dir)
+            exit()
+    os.mkdir(op_dir)
+    os.mkdir(ale1_op_dir)
+
+    ##################################################################################################
+
+    # run mafft-einsi
+    if (faa_in is not None) and (msa_in is None):
+        mafft_cmd = 'mafft-einsi --thread %s --quiet %s > %s' % (num_threads, faa_in, msa_file)
+
+        with open(log_txt, 'a') as log_txt_handle:
+            log_txt_handle.write(mafft_cmd + '\n')
+        os.system(mafft_cmd)
+        msa_file_for_next_step = msa_file
+    else:
+        msa_file_for_next_step = msa_in
+
+    # run trimal
+    if trim_msa is True:
+        trimal_cmd = 'trimal -in %s -out %s -automated1' % (msa_file_for_next_step, msa_trimmed)
+        with open(log_txt, 'a') as log_txt_handle:
+            log_txt_handle.write(trimal_cmd + '\n')
+        os.system(trimal_cmd)
+        iqtree2_cmd = 'iqtree2 -m LG+G+I -bb 1000 --wbtl -nt %s -s %s -pre %s' % (num_threads, msa_trimmed, tree_prefix)
+        with open(log_txt, 'a') as log_txt_handle:
+            log_txt_handle.write(iqtree2_cmd + '\n')
+        os.system(iqtree2_cmd)
+    else:
+        iqtree2_cmd = 'iqtree2 -m LG+G+I -bb 1000 --wbtl -nt %s -s %s -pre %s' % (num_threads, msa_file_for_next_step, tree_prefix)
+        with open(log_txt, 'a') as log_txt_handle:
+            log_txt_handle.write(iqtree2_cmd + '\n')
+        os.system(iqtree2_cmd)
+
+    # run ALE2
+    ale2_cmd = 'TreeSAK ALE2 -i %s -s %s -t %s -f -runALE -docker %s -o %s' % (ale1_op_dir, genome_tree_file_rooted, num_threads, docker_image, ale2_op_dir)
+    with open(log_txt, 'a') as log_txt_handle:
+        log_txt_handle.write(ale2_cmd + '\n')
+    os.system(ale2_cmd)
+
+    # run ALE4
+    ale4_cmd = 'TreeSAK ALE4 -i1 %s -i2 %s -c %s -color %s -o %s -fc %s -f -api %s' % (ale1_op_dir, ale2_op_dir, genome_taxon_txt, ar_phylum_color_code_txt, ale4_op_dir, hgt_freq_cutoff, API_key)
+    with open(log_txt, 'a') as log_txt_handle:
+        log_txt_handle.write(ale4_cmd + '\n')
+    os.system(ale4_cmd)
+
+
+if __name__ == '__main__':
+
+    SingleAleHGT_parser = argparse.ArgumentParser()
+    SingleAleHGT_parser.add_argument('-faa',    required=False, default=None,               help='input aa file, e.g., OMA0001.faa')
+    SingleAleHGT_parser.add_argument('-msa',    required=False, default=None,               help='input MSA file, e.g., OMA0001.aln')
+    SingleAleHGT_parser.add_argument('-o',      required=True,                              help='output dir, e.g., SingleAleHGT_wd')
+    SingleAleHGT_parser.add_argument('-s',      required=True,                              help='rooted species tree')
+    SingleAleHGT_parser.add_argument('-c',      required=True,                              help='genome_taxon, GTDB format')
+    SingleAleHGT_parser.add_argument('-color',  required=True,                              help='phylum color code')
+    SingleAleHGT_parser.add_argument('-fc',     required=False, type=float, default=0.5,    help='hgt_freq_cutoff, default: 0.5')
+    SingleAleHGT_parser.add_argument('-mld',    required=False, type=int, default=5,        help='donor_node_min_leaf_num, default: 5')
+    SingleAleHGT_parser.add_argument('-mlr',    required=False, type=int, default=5,        help='recipient_node_min_leaf_num, default: 5')
+    SingleAleHGT_parser.add_argument('-trim',   required=False, action="store_true",        help='trim MSA')
+    SingleAleHGT_parser.add_argument('-docker', required=False, default=None,               help='Docker image, if ALE was installed with Docker, e.g., gregmich/alesuite_new')
+    SingleAleHGT_parser.add_argument('-itol',   required=False, default='batch_access_tmp', help='iTOL project_name, default: batch_access_tmp')
+    SingleAleHGT_parser.add_argument('-api',    required=True,                              help='iTOL API key')
+    SingleAleHGT_parser.add_argument('-t',      required=False, type=int, default=6,        help='number of threads, default: 6')
+    SingleAleHGT_parser.add_argument('-f',      required=False, action="store_true",        help='force overwrite')
+    args = vars(SingleAleHGT_parser.parse_args())
+    SingleAleHGT(args)
+
+
+'''
+
+cd /Users/songweizhi/Desktop/DateArTree/01_HGT_ALE_with_OMA/ALE1_op_dir_OMA05484_OMA07484_trimmed
+trimal -in ../ALE1_op_dir_OMA05484_OMA07484/concatenated.fasta -out concatenated.fasta -automated1
+iqtree2 -m LG+G+I -bb 1000 --wbtl -nt 10 -s concatenated.fasta -pre OMA05484_OMA07484
+cd /Users/songweizhi/Desktop/DateArTree/01_HGT_ALE_with_OMA
+TreeSAK ALE2 -i ALE1_op_dir_OMA05484_OMA07484_trimmed -s genome_tree.newick -t 10 -f -runALE -docker gregmich/alesuite_new -o ALE2_op_dir_OMA05484_OMA07484_trimmed
+TreeSAK ALE4 -i1 ALE1_op_dir_OMA05484_OMA07484_trimmed -i2 ALE2_op_dir_OMA05484_OMA07484_trimmed -c genome_taxon.txt -color phylum_color.txt -o ALE4_op_dir_OMA05484_OMA07484_trimmed_0.01 -fc 0.01 -f -api S1kZZuDHc0d5M7J5vLnUNQ
+
+cd /Users/songweizhi/Desktop/DateArTree/01_HGT_ALE_with_OMA
+/usr/local/bin/python3.7 /Users/songweizhi/PycharmProjects/TreeSAK/TreeSAK/SingleAleHGT.py -msa ALE1_op_dir_OMA05484_OMA07484_trimmed/concatenated.fasta -s genome_tree_rooted_noEU.treefile -fc 0.3 -c genome_taxon.txt -color phylum_color.txt -api S1kZZuDHc0d5M7J5vLnUNQ -t 9 -f -o demo_SingleAleHGT_wd -trim
+
+cd /Users/songweizhi/Desktop/DateArTree/01_HGT_ALE_with_OMA/demo_SingleAleHGT_wd
+TreeSAK ALE2 -i ALE1_op_dir -s ../genome_tree.newick -t 10 -f -runALE -docker gregmich/alesuite_new -o ALE2_op_dir
+TreeSAK ALE4 -i1 ALE1_op_dir_OMA05484_OMA07484_trimmed -i2 ALE2_op_dir_OMA05484_OMA07484_trimmed -c genome_taxon.txt -color phylum_color.txt -o ALE4_op_dir_OMA05484_OMA07484_trimmed_0.01 -fc 0.01 -f -api S1kZZuDHc0d5M7J5vLnUNQ
+
+/usr/local/bin/python3.7 /Users/songweizhi/PycharmProjects/TreeSAK/TreeSAK/SingleAleHGT.py -o demo_SingleAleHGT_wd -msa ALE1_op_dir/OMA15312.aln -s genome_tree_rooted_noEU.treefile -fc 0.3 -c genome_taxon.txt -color phylum_color.txt -api S1kZZuDHc0d5M7J5vLnUNQ -t 10 -f -trim -docker gregmich/alesuite_new
+/usr/local/bin/python3.7 /Users/songweizhi/PycharmProjects/TreeSAK/TreeSAK/SingleAleHGT.py -o OMA01402_ALE_HGT_wd -msa ALE1_op_dir/OMA01402.aln -s genome_tree_rooted_noEU.treefile -fc 0.3 -c genome_taxon.txt -color phylum_color.txt -api S1kZZuDHc0d5M7J5vLnUNQ -t 10 -f -trim -docker gregmich/alesuite_new
+/usr/local/bin/python3.7 /Users/songweizhi/PycharmProjects/TreeSAK/TreeSAK/SingleAleHGT.py -o OMA01402_ALE_HGT_wd_no_trim -msa ALE1_op_dir/OMA01402.aln -s genome_tree_rooted_noEU.treefile -fc 0.3 -c genome_taxon.txt -color phylum_color.txt -api S1kZZuDHc0d5M7J5vLnUNQ -t 10 -f -docker gregmich/alesuite_new
+
+'''

TreeSAK/SingleLinePhy.py

@@ -0,0 +1,50 @@
+import os
+import argparse
+from Bio import AlignIO
+
+
+SingleLinePhy_usage = '''
+======== SingleLinePhy example commands ========
+
+TreeSAK SingleLinePhy -i in.phy -o out.phy
+
+================================================
+'''
+
+
+def SingleLinePhy(args):
+
+    phy_in  = args['i']
+    phy_out = args['o']
+
+    # check input file
+    if os.path.isfile(phy_in) is False:
+        print('input file not found, program exited!')
+        exit()
+
+    alignment = AlignIO.read(phy_in, 'phylip-relaxed')
+
+    max_seq_id_len = 0
+    for each_seq in alignment:
+        seq_id_len = len(each_seq.id)
+        if seq_id_len > max_seq_id_len:
+            max_seq_id_len = seq_id_len
+
+    with open(phy_out, 'w') as msa_out_handle:
+        msa_out_handle.write('%s %s\n' % (len(alignment), alignment.get_alignment_length()))
+        for each_seq in alignment:
+            seq_id = each_seq.id
+            seq_id_with_space = '%s%s' % (seq_id, ' ' * (max_seq_id_len + 2 - len(seq_id)))
+            msa_out_handle.write('%s%s\n' % (seq_id_with_space, str(each_seq.seq)))
+
+    print('Done!')
+
+
+if __name__ == '__main__':
+
+    # initialize the options parser
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-i',   required=True,                          help='input file')
+    parser.add_argument('-o',   required=True,                          help='output file')
+    args = vars(parser.parse_args())
+    SingleLinePhy(args)

TreeSAK/SliceMSA.py

@@ -0,0 +1,142 @@
+import os
+import argparse
+from Bio import AlignIO
+
+
+SliceMSA_usage = '''
+========================= SliceMSA example commands =========================
+
+TreeSAK SliceMSA -i 16S_aln.fasta -s 200-300 -o 16S_aln_200-300.fasta
+TreeSAK SliceMSA -i 16S_aln.phylip -fi phylip-relaxed -s sections.txt -o SliceMSA_op -fo phylip-relaxed
+
+# example
+200-300     select columns 200-300
+-100        select columns 1-300
+500-        select columns from 500 to the end
+
+# Example of sections.txt (one section per line):
+200-300
+-100
+500-
+
+# Examples of alignment format (https://biopython.org/wiki/AlignIO): 
+fasta, phylip, phylip-relaxed, phylip-sequential, clustal
+
+=============================================================================
+'''
+
+
+def msa2fasta(msa_object, fasta_out):
+
+    with open(fasta_out, 'w') as fasta_out_handle:
+        for each_seq in msa_object:
+            fasta_out_handle.write('>%s\n' % each_seq.id)
+            fasta_out_handle.write('%s\n' % str(each_seq.seq))
+
+
+def msa2phylip(msa_object, phylip_out):
+
+    max_seq_id_len = 0
+    for each_seq in msa_object:
+        seq_id_len = len(each_seq.id)
+        if seq_id_len > max_seq_id_len:
+            max_seq_id_len = seq_id_len
+
+    with open(phylip_out, 'w') as phylip_out_handle:
+        phylip_out_handle.write('%s %s\n' % (len(msa_object), msa_object.get_alignment_length()))
+        for each_seq in msa_object:
+            seq_id = each_seq.id
+            seq_id_with_space = '%s%s' % (seq_id, ' ' * (max_seq_id_len + 2 - len(seq_id)))
+            phylip_out_handle.write('%s%s\n' % (seq_id_with_space, str(each_seq.seq)))
+
+
+def SliceMSA(args):
+
+    msa_in_file         = args['i']
+    aln_in_format       = args['fi']
+    col_to_select_txt   = args['s']
+    op_dir              = args['o']
+    aln_out_format      = args['fo']
+    force_overwriting   = args['force']
+
+    aln_out_ext = 'fasta'
+    if aln_out_format == 'phylip-relaxed':
+        aln_out_ext = 'phylip'
+
+    if os.path.isfile(msa_in_file) is False:
+        print('Input MSA not found, program exited!')
+        exit()
+
+    # read in msa
+    msa_in = AlignIO.read(msa_in_file, aln_in_format)
+
+    # parse provided sections
+    section_to_select_list = []
+    if os.path.isfile(col_to_select_txt) is False:
+        col_to_select_txt_split = col_to_select_txt.strip().split('-')
+        if col_to_select_txt == '-':
+            section_to_select_list.append(['1', str(msa_in.get_alignment_length())])
+        elif col_to_select_txt.startswith('-'):
+            section_to_select_list.append(['1', col_to_select_txt_split[1]])
+        elif col_to_select_txt.endswith('-'):
+            section_to_select_list.append([col_to_select_txt_split[0], str(msa_in.get_alignment_length())])
+        else:
+            section_to_select_list.append(col_to_select_txt_split)
+    else:
+        for each_section in open(col_to_select_txt):
+            each_section = each_section.strip()
+            each_section_split = each_section.strip().split('-')
+            if each_section == '-':
+                section_to_select_list.append(['1', str(msa_in.get_alignment_length())])
+            elif each_section.startswith('-'):
+                section_to_select_list.append(['1', each_section_split[1]])
+            elif each_section.endswith('-'):
+                section_to_select_list.append([each_section_split[0], str(msa_in.get_alignment_length())])
+            else:
+                section_to_select_list.append(each_section_split)
+
+    # check output folder
+    if len(section_to_select_list) > 1:
+        if os.path.isdir(op_dir) is True:
+            if force_overwriting is True:
+                os.system('rm -r %s' % op_dir)
+            else:
+                print('Output folder already exist, program exited!')
+                exit()
+        os.system('mkdir %s' % op_dir)
+
+    # write out sections
+    if len(section_to_select_list) == 1:
+        current_section = msa_in[:, (int(section_to_select_list[0][0]) - 1):(int(section_to_select_list[0][1]))]
+        if aln_out_ext == 'fasta':
+            msa2fasta(current_section, op_dir)
+        if aln_out_ext == 'phylip':
+            msa2phylip(current_section, op_dir)
+    else:
+        for each_section in section_to_select_list:
+
+            pwd_op_file     = '%s/%s.%s' % (op_dir, '-'.join(each_section), aln_out_ext)
+            current_section = msa_in[:, (int(each_section[0])-1):(int(each_section[1]))]
+
+            # write out
+            if aln_out_ext == 'fasta':
+                msa2fasta(current_section, pwd_op_file)
+            if aln_out_ext == 'phylip':
+                msa2phylip(current_section, pwd_op_file)
+
+    print('MSA subset(s) exported to %s, Done!' % op_dir)
+
+
+if __name__ == '__main__':
+
+    # arguments for rename_seq_parser
+    SliceMSA_parser = argparse.ArgumentParser()
+    SliceMSA_parser.add_argument('-i',      required=True,                         help='input MSA in fasta format')
+    SliceMSA_parser.add_argument('-fi',     required=False, default='fasta',       help='format (NOT file extension) of input MSA, default: fasta')
+    SliceMSA_parser.add_argument('-s',      required=True,                         help='columns to export, e.g. 200-300, -100, 50-')
+    SliceMSA_parser.add_argument('-o',      required=True,                         help='output file or folder')
+    SliceMSA_parser.add_argument('-fo',     required=False, default='fasta',       help='format of output MSA, select from fasta and phylip-relaxed, default: fasta')
+    SliceMSA_parser.add_argument('-force',  required=False, action="store_true",   help='force overwrite existing output folder')
+    args = vars(SliceMSA_parser.parse_args())
+    SliceMSA(args)
+

TreeSAK/SplitScore.py

@@ -0,0 +1,19 @@
+
+SplitScore_usage = '''
+============================================= SplitScore example commands =============================================
+
+# SplitScore modules
+TreeSAK SplitScore1     ->  Step 1: Infer gene tree
+TreeSAK SplitScore1OMA  ->  Step 1: Infer gene tree (based on OMA outputs)
+TreeSAK SplitScore2     ->  Step 2: Calculate split score
+
+# SplitScore1
+TreeSAK SplitScore1 -i OrthologousGroups.txt -s OrthologousGroupsFasta -o step1_op_dir -t 6 -f
+TreeSAK SplitScore1 -i OrthologousGroups.txt -s OrthologousGroupsFasta -o step1_op_dir -t 6 -f -u interested_gnm.txt
+
+# SplitScore2
+# Please ensure that all the commands produced in step one have been executed before proceeding to step two.
+TreeSAK SplitScore2 -i step1_op_dir -g gnm_cluster.tsv -k gnm_taxon.txt -f -t 10 -o step_2_op_dir
+
+=======================================================================================================================
+'''

TreeSAK/SplitScore1.py

@@ -0,0 +1,178 @@
+from __future__ import print_function
+import os
+import glob
+import argparse
+from Bio import SeqIO
+
+
+SplitScore1_usage = '''
+======================== SplitScore1 example commands ========================
+
+TreeSAK SplitScore1 -i marker_seq -x fa -o SplitScore1_op_dir -jst 9 -f
+
+# Format of gene id
+APA_bin56_00001
+APA_bin56_00002
+APA_bin56_00003
+
+==============================================================================
+'''
+
+
+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 SplitScore1(args):
+
+    oma_op_fasta        = args['i']
+    fasta_file_ext      = args['x']
+    interested_gnm_txt  = args['u']
+    iqtree_model        = args['m']
+    cov_cutoff          = args['c']
+    force_overwrite     = args['f']
+    num_of_js_threads   = args['jst']
+    op_dir              = args['o']
+
+    ################################################################################
+
+    interested_gnm_set = set()
+    if interested_gnm_txt is not None:
+        if os.path.isfile(interested_gnm_txt):
+            for each_gnm in open(interested_gnm_txt):
+                interested_gnm_set.add(each_gnm.strip())
+        else:
+            print('%s not found, program exited' % interested_gnm_txt)
+            exit()
+
+    ################################################################################
+
+    fa_file_re   = '%s/*.%s' % (oma_op_fasta, fasta_file_ext)
+    fa_file_list = glob.glob(fa_file_re)
+    if len(fa_file_list) == 0:
+        print('No file found in %s, program exited!' % oma_op_fasta)
+        exit()
+
+    og_to_gene_dict = dict()
+    for each_fa in fa_file_list:
+        _, f_base, _ = sep_path_basename_ext(each_fa)
+        seq_id_set = set()
+        for each_seq in SeqIO.parse(each_fa, 'fasta'):
+            seq_id_set.add(each_seq.id)
+        og_to_gene_dict[f_base] = seq_id_set
+
+    ################################################################################
+
+    gnm_to_process = set()
+    for each_og in og_to_gene_dict:
+        gene_set = og_to_gene_dict[each_og]
+        gnm_set = set()
+        for each_gene in gene_set:
+            gnm_id = '_'.join(each_gene.split('_')[:-1])
+            gnm_set.add(gnm_id)
+            if interested_gnm_txt is None:
+                gnm_to_process.add(gnm_id)
+            else:
+                if gnm_id in interested_gnm_set:
+                    gnm_to_process.add(gnm_id)
+
+        if len(gene_set) != len(gnm_set):
+            print('Program exited!')
+            exit()
+
+    ################################################################################
+
+    # define file name
+    qualified_og_dir    = '%s/qualified_OGs'        % op_dir
+    cmd_1_mafft_txt     = '%s/cmd_1_mafft.txt'      % op_dir
+    cmd_2_trimal_txt    = '%s/cmd_2_trimal.txt'     % op_dir
+    cmd_3_iqtree_txt    = '%s/cmd_3_iqtree.txt'     % op_dir
+    ignored_marker_txt  = '%s/ignored_markers.txt'  % op_dir
+
+    # create output folder
+    if os.path.isdir(op_dir) is True:
+        if force_overwrite is True:
+            os.system('rm -r %s' % op_dir)
+        else:
+            print('%s exist, program exited!' % op_dir)
+            exit()
+    os.mkdir(op_dir)
+    os.mkdir(qualified_og_dir)
+
+    ################################################################################
+
+    cmd_1_mafft_txt_handle = open(cmd_1_mafft_txt, 'w')
+    cmd_2_trimal_txt_handle = open(cmd_2_trimal_txt, 'w')
+    cmd_3_iqtree_txt_handle = open(cmd_3_iqtree_txt, 'w')
+    ignored_og_dict = dict()
+    for each_og in sorted(list(og_to_gene_dict.keys())):
+        seq_file_in          = '%s/%s.%s'       % (oma_op_fasta, each_og, fasta_file_ext)
+        file_out_seq         = '%s/%s.%s'       % (qualified_og_dir, each_og, fasta_file_ext)
+        file_out_aln         = '%s.aln'         % each_og
+        file_out_aln_trimmed = '%s_trimmed.aln' % each_og
+
+        seq_file_out_handle = open(file_out_seq, 'w')
+        current_gnm_set = set()
+        for each_seq in SeqIO.parse(seq_file_in, 'fasta'):
+            seq_id = each_seq.id
+            gnm_id = '_'.join(seq_id.split('_')[:-1])
+            if gnm_id in gnm_to_process:
+                current_gnm_set.add(gnm_id)
+                seq_file_out_handle.write('>%s\n' % each_seq.id)
+                seq_file_out_handle.write('%s\n'  % each_seq.seq)
+        seq_file_out_handle.close()
+
+        cov_value = len(current_gnm_set)*100/len(gnm_to_process)
+        cov_value = float("{0:.2f}".format(cov_value))
+
+        if cov_value < cov_cutoff:
+            report_str = 'Ignored %s, contains proteins from %s (%s%s) genomes, < %s%s.' % (each_og, len(current_gnm_set), cov_value, '%', cov_cutoff, '%')
+            ignored_og_dict[each_og] = report_str
+            os.system('rm %s' % file_out_seq)
+        else:
+            # align, trim and iqtree
+            mafft_cmd     = 'mafft-einsi --thread %s --quiet %s.%s > %s'                                % (num_of_js_threads, each_og, fasta_file_ext, file_out_aln)
+            trimal_cmd    = 'trimal -in %s -out %s -automated1'                                         % (file_out_aln, file_out_aln_trimmed)
+            iqtree_cmd    = 'iqtree2 -s %s --seqtype AA -m %s -B 1000 --wbtl --bnni --prefix %s -T %s --quiet' % (file_out_aln_trimmed, iqtree_model, each_og, num_of_js_threads)
+            # Undinarchaeota illuminate DPANN phylogeny and the impact of gene transfer on archaeal evolution, settings: -m LG+G -bb 1000 -wbtl -bnni
+            cmd_1_mafft_txt_handle.write(mafft_cmd + '\n')
+            cmd_2_trimal_txt_handle.write(trimal_cmd + '\n')
+            cmd_3_iqtree_txt_handle.write(iqtree_cmd + '\n')
+    cmd_1_mafft_txt_handle.close()
+    cmd_2_trimal_txt_handle.close()
+    cmd_3_iqtree_txt_handle.close()
+
+    # report ignored markers
+    if len(ignored_og_dict) > 0:
+        print('The following %s markers were ignored due to low genome coverage, see details in %s:' % (len(ignored_og_dict), ignored_marker_txt))
+        print('\n'.join(sorted(list(ignored_og_dict.keys()))))
+        ignored_marker_txt_handle = open(ignored_marker_txt, 'w')
+        for each_ignored_marker in sorted(list(ignored_og_dict.keys())):
+            ignored_marker_txt_handle.write(ignored_og_dict[each_ignored_marker] + '\n')
+        ignored_marker_txt_handle.close()
+
+    # report
+    print('You will need to execute the commands exported to the following three files before moving to SplitScore2')
+    print(cmd_1_mafft_txt)
+    print(cmd_2_trimal_txt)
+    print(cmd_3_iqtree_txt)
+    print('Done!')
+
+
+if __name__ == '__main__':
+
+    SplitScore1_parser = argparse.ArgumentParser()
+    SplitScore1_parser.add_argument('-i',   required=True,                          help='orthologous gene sequence')
+    SplitScore1_parser.add_argument('-x',   required=True,                          help='fasta file extension')
+    SplitScore1_parser.add_argument('-o',   required=True,                          help='output directory')
+    SplitScore1_parser.add_argument('-u',   required=False, default=None,           help='interested genomes, no file extension')
+    SplitScore1_parser.add_argument('-m',   required=False, default='LG+G+I',       help='iqtree_model, default: LG+G+I')
+    SplitScore1_parser.add_argument('-c',   required=False, type=int, default=85,   help='coverage cutoff, default: 85')
+    SplitScore1_parser.add_argument('-f',   required=False, action="store_true",    help='force overwrite')
+    SplitScore1_parser.add_argument('-jst', required=False, type=int, default=1,    help='num of threads for iqtree2, default: 1')
+    args = vars(SplitScore1_parser.parse_args())
+    SplitScore1(args)