treesak 1.51.2__py3-none-any.whl

TreeSAK/AssessPB.py

@@ -0,0 +1,130 @@
+import os
+import argparse
+
+
+AssessPB_usage = '''
+====================== AssessPB example commands ======================
+
+# Dependency: bpcomp and tracecomp (from PhyloBayes-MPI)
+
+export OMPI_MCA_btl=^openib
+
+TreeSAK AssessPB -c1 c1dir/c1 -c2 c2dir/c2
+TreeSAK AssessPB -c1 c1dir/c1 -c2 c2dir/c2 -c3 c3dir/c3
+TreeSAK AssessPB -c1 c1dir/c1 -c2 c2dir/c2 -c3 c3dir/c3 -c4 c4dir/c4
+TreeSAK AssessPB -cdir chain_dir
+
+# This is a wrapper for: 
+bpcomp -x 1000 10 c1 c2
+bpcomp -x 1000 10 c1 c2 c3 c4
+tracecomp -x 1000 c1 c2
+tracecomp -x 1000 c1 c2 c3 c4
+
+=======================================================================
+'''
+
+
+def compare2chains(chain_1, chain_2, chain_3, chain_4, burn_in, sample_interval, with_bpcomp, with_tracecomp, op_dir, cmd_txt):
+
+    # bpcomp:    -x <burnin> [<every> <until>]. default burnin = 10 percent of the chain
+    # tracecomp: -x <burnin> [<every> <until>]. default burnin = 20 percent of the chain
+
+    bpcomp_cmd    = 'bpcomp -o %s/bpcomp -x %s %s %s %s'    % (op_dir, burn_in, sample_interval, chain_1, chain_2)
+    tracecomp_cmd = 'tracecomp -o %s/tracecomp -x %s %s %s' % (op_dir, burn_in, chain_1, chain_2)
+
+    if (chain_3 is not None) and (chain_4 is None):
+        bpcomp_cmd    = 'bpcomp -o %s/bpcomp -x %s %s %s %s %s'    % (op_dir, burn_in, sample_interval, chain_1, chain_2, chain_3)
+        tracecomp_cmd = 'tracecomp -o %s/tracecomp -x %s %s %s %s' % (op_dir, burn_in, chain_1, chain_2, chain_3)
+
+    if (chain_3 is not None) and (chain_4 is not None):
+        bpcomp_cmd    = 'bpcomp -o %s/bpcomp -x %s %s %s %s %s %s'    % (op_dir, burn_in, sample_interval, chain_1, chain_2, chain_3, chain_4)
+        tracecomp_cmd = 'tracecomp -o %s/tracecomp -x %s %s %s %s %s' % (op_dir, burn_in, chain_1, chain_2, chain_3, chain_4)
+
+    # write out commands
+    cmd_txt_handle = open(cmd_txt, 'a')
+    cmd_txt_handle.write(bpcomp_cmd + '\n')
+    cmd_txt_handle.write(tracecomp_cmd + '\n')
+    cmd_txt_handle.close()
+
+    # execute commands
+    if with_bpcomp is True:
+        print()
+        print('====================== bpcomp ======================')
+        print()
+        print(bpcomp_cmd)
+        os.system(bpcomp_cmd)
+        print('Guideline')
+        print('1. maxdiff < 0.1: good run.')
+        print('2. maxdiff < 0.3: acceptable: gives a good qualitative picture of the posterior consensus.')
+        print('3. 0.3 < maxdiff < 1: the sample is not yet sufficiently large and have not converged, but on right track.')
+        print('4. if maxdiff = 1 even after 10,000 points: at least one run stuck in a local maximum.')
+        print()
+
+    if with_tracecomp is True:
+        print('==================== tracecomp ====================')
+        print()
+        print(tracecomp_cmd)
+        print()
+        os.system(tracecomp_cmd)
+        print()
+        print('Guideline')
+        print('1. rel diff < 0.1 and minimum effective size > 300: good run.')
+        print('2. rel diff < 0.3 and minimum effective size > 50: acceptable run.')
+        print()
+
+    print('====================================================')
+
+
+def AssessPB(args):
+
+    chain_1         = args['c1']
+    chain_2         = args['c2']
+    chain_3         = args['c3']
+    chain_4         = args['c4']
+    chain_dir       = args['cdir']
+    burn_in         = args['bi']
+    sample_interval = args['si']
+    op_dir          = args['o']
+    force_overwrite = args['f']
+    with_bpcomp     = True
+    with_tracecomp  = True
+
+    cmd_txt         = '%s/cmds.txt' % op_dir
+
+    # create output dir
+    if os.path.isdir(op_dir) is True:
+        if force_overwrite is True:
+            os.system('rm -r %s' % op_dir)
+        else:
+            print('output folder already exist, program exited!')
+            exit()
+    os.system('mkdir %s' % op_dir)
+
+    if (chain_1 is not None) and (chain_2 is not None) and (chain_dir is None):
+        compare2chains(chain_1, chain_2, chain_3, chain_4, burn_in, sample_interval, with_bpcomp, with_tracecomp, op_dir, cmd_txt)
+
+    elif (chain_1 is None) and (chain_2 is None) and (chain_dir is not None):
+        print('Compare multiple chains')
+        print('Function to be added!')
+        print('Program exited!')
+
+    else:
+        print('Please compare either no more than four chains (specified by -c1, -c2, -c3 and -c4) or multiple chains provided within -cdir')
+        print('Program exited!')
+        exit()
+
+
+if __name__ == '__main__':
+
+    AssessPB_parser = argparse.ArgumentParser()
+    AssessPB_parser.add_argument('-c1',     required=False, default=None,           help='chain 1')
+    AssessPB_parser.add_argument('-c2',     required=False, default=None,           help='chain 2')
+    AssessPB_parser.add_argument('-c3',     required=False, default=None,           help='chain 3')
+    AssessPB_parser.add_argument('-c4',     required=False, default=None,           help='chain 4')
+    AssessPB_parser.add_argument('-cdir',   required=False, default=None,           help='chain folder')
+    AssessPB_parser.add_argument('-bi',     required=False, default=1000,           help='burn-in, default: 1000')
+    AssessPB_parser.add_argument('-si',     required=False, default=10,             help='sample interval, default: 10')
+    AssessPB_parser.add_argument('-o',      required=True, default=None,            help='output directory')
+    AssessPB_parser.add_argument('-f',      required=False, action="store_true",    help='force overwrite')
+    args = vars(AssessPB_parser.parse_args())
+    AssessPB(args)

TreeSAK/BMGE.py

@@ -0,0 +1,49 @@
+import os
+import argparse
+
+
+BMGE_usage = '''
+======================= BMGE example commands =======================
+
+# require: java
+
+TreeSAK BMGE -p demo -i input.aln -m BLOSUM30 -esc 0.55
+
+# Settings for calculating split score (Nina Dombrowski): 
+# -t AA -m BLOSUM30 -h 0.55
+
+=====================================================================
+'''
+
+
+def BMGE(args):
+
+    op_prefix               = args['p']
+    msa_in                  = args['i']
+    trim_model              = args['m']
+    entropy_score_cutoff    = args['esc']
+
+    # define file name
+    msa_out_fasta  = '%s.BMGE.fasta'  % op_prefix
+
+    # specify path to BMGE.jar
+    current_file_path   = '/'.join(os.path.realpath(__file__).split('/')[:-1])
+    pwd_bmge_jar        = '%s/BMGE.jar' % current_file_path
+
+    # run BMGE
+    bmge_cmd = 'java -jar %s -i %s -m %s -t AA -h %s -of %s' % (pwd_bmge_jar, msa_in, trim_model, entropy_score_cutoff, msa_out_fasta)
+    print(bmge_cmd)
+    os.system(bmge_cmd)
+
+    print('Done!')
+
+
+if __name__ == '__main__':
+
+    BMGE_parser = argparse.ArgumentParser()
+    BMGE_parser.add_argument('-p',   required=True,                         help='output prefix')
+    BMGE_parser.add_argument('-i',   required=True,                         help='input MSA')
+    BMGE_parser.add_argument('-m',   required=False, default='BLOSUM30',    help='trim model, default: BLOSUM30')
+    BMGE_parser.add_argument('-esc', required=False, default='0.55',        help='entropy score cutoff, default: 0.55')
+    args = vars(BMGE_parser.parse_args())
+    BMGE(args)

TreeSAK/CompareMCMC.py

@@ -0,0 +1,138 @@
+import os
+import argparse
+import arviz as az
+import pandas as pd
+import matplotlib as mpl
+mpl.use('Agg')
+import matplotlib.pyplot as plt
+from matplotlib.pyplot import figure
+
+
+CompareMCMC_usage = '''
+====================================== CompareMCMC example commands ======================================
+
+TreeSAK CompareMCMC -mx IR_mcmc.txt -my AR_mcmc.txt -lx IR -ly AR -o convergence_plot.png -max 40 -fs 12
+
+cd /Users/songweizhi/Desktop
+TreeSAK CompareMCMC -mx /Users/songweizhi/Desktop/Sponge_r220/6_dating/MCMCTree/dating_outputs/topo2p10_clock3_nsample250000_run1_mcmc.txt -my /Users/songweizhi/Desktop/Sponge_r220/6_dating/MCMCTree/dating_outputs/topo2p10_clock3_nsample250000_run2_mcmc.txt -lx IR -ly AR -o convergence_plot.png -max 40 -fs 12
+
+==========================================================================================================
+'''
+
+
+def sep_path_basename_ext(file_in):
+    file_path, file_name = os.path.split(file_in)
+    if file_path == '':
+        file_path = '.'
+    file_basename, file_extension = os.path.splitext(file_name)
+    return file_path, file_basename, file_extension
+
+
+def CompareMCMC(args):
+
+    mcmc_txt_x      = args['mx']
+    mcmc_txt_y      = args['my']
+    label_x         = args['lx']
+    label_y         = args['ly']
+    pwd_figure      = args['o']
+    max_axis_value  = args['max']
+    label_fs        = args['fs']
+
+    x_path, x_basename, x_ext = sep_path_basename_ext(mcmc_txt_x)
+    y_path, y_basename, y_ext = sep_path_basename_ext(mcmc_txt_y)
+
+    if label_x is None:
+        label_x = x_basename
+    if label_y is None:
+        label_y = y_basename
+
+    # read in dataframe
+    df_x = pd.read_table(mcmc_txt_x, index_col=0)
+    df_y = pd.read_table(mcmc_txt_y, index_col=0)
+
+    # get Mean value for each column
+    df_x_col_to_mean_dict = {col_name: mean for col_name, mean in df_x.mean().iteritems()}
+    df_y_col_to_mean_dict = {col_name: mean for col_name, mean in df_y.mean().iteritems()}
+
+    # get CI95 for each column
+    df_x_col_to_ci_dict = {col_name: az.hdi(col.values, hdi_prob=0.95) for col_name, col in df_x.iteritems()}
+    df_y_col_to_ci_dict = {col_name: az.hdi(col.values, hdi_prob=0.95) for col_name, col in df_y.iteritems()}
+
+    num_list_x = []
+    num_list_y = []
+    err_range_x = []
+    err_range_y = []
+    for col_name, col in df_x.iteritems():
+        if col_name not in ['mu', 'sigma2', 'lnL']:
+            num_list_x.append(df_x_col_to_mean_dict[col_name])
+            num_list_y.append(df_y_col_to_mean_dict[col_name])
+            err_range_x.append(df_x_col_to_ci_dict[col_name])
+            err_range_y.append(df_y_col_to_ci_dict[col_name])
+
+    x_err_l = []
+    x_err_r = []
+    y_err_l = []
+    y_err_u = []
+    max_value = 0
+    min_value = 100000000000000
+    n = 0
+    while n < len(num_list_x):
+        x_value = num_list_x[n]
+        y_value = num_list_y[n]
+        x_range = err_range_x[n]
+        y_range = err_range_y[n]
+        x_l_dist = abs(x_value - x_range[0])
+        x_r_dist = abs(x_range[1] - x_value)
+        y_l_dist = abs(y_value - y_range[0])
+        y_u_dist = abs(y_range[1] - y_value)
+        x_err_l.append(x_l_dist)
+        x_err_r.append(x_r_dist)
+        y_err_l.append(y_l_dist)
+        y_err_u.append(y_u_dist)
+
+        current_max = max(x_value, y_value, x_range[0], x_range[1], y_range[0], y_range[1])
+        current_min = min(x_value, y_value, x_range[0], x_range[1], y_range[0], y_range[1])
+
+        if current_max > max_value:
+            max_value = current_max
+        if current_min < min_value:
+            min_value = current_min
+        n += 1
+
+    figure(figsize=(6, 6), dpi=300)
+    plt.plot([min_value, max_value], [min_value, max_value], color='black', linestyle='dashed', linewidth=1, alpha=0.5)
+    plt.scatter(num_list_x, num_list_y, s=0)
+    plt.errorbar(num_list_x, num_list_y, xerr=[x_err_l, x_err_r], yerr=[y_err_l, y_err_u],
+                 ls='none', ecolor='skyblue', elinewidth=1, alpha=0.5)
+
+    if max_axis_value is not None:
+        plt.xlim([0, max_axis_value])
+        plt.ylim([0, max_axis_value])
+
+    # Set the font size of xticks and yticks
+    plt.xticks(fontsize=label_fs)
+    plt.yticks(fontsize=label_fs)
+    plt.xlabel(label_x, fontsize=label_fs)
+    plt.ylabel(label_y, fontsize=label_fs)
+
+    # write out
+    plt.tight_layout()
+    plt.savefig(pwd_figure)
+    plt.close()
+
+    print('Plot exported to %s, done!' % pwd_figure)
+
+
+if __name__ == '__main__':
+
+    # initialize the options parser
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-mx',      required=True,                          help='mcmc.txt for x axis')
+    parser.add_argument('-my',      required=True,                          help='mcmc.txt for y axis')
+    parser.add_argument('-lx',      required=False, default=None,           help='label for x axis')
+    parser.add_argument('-ly',      required=False, default=None,           help='label for y axis')
+    parser.add_argument('-max',     required=False, default=None, type=int, help='maximum axis value')
+    parser.add_argument('-fs',      required=False, default=16, type=int,   help='label font size, default: 16')
+    parser.add_argument('-o',       required=True,                          help='output plot')
+    args = vars(parser.parse_args())
+    CompareMCMC(args)

TreeSAK/ConcateMSA.py

@@ -0,0 +1,111 @@
+import os
+import glob
+import argparse
+from Bio import SeqIO
+from Bio import AlignIO
+
+
+ConcateMSA_usage = '''
+================= ConcateMSA example commands =================
+
+TreeSAK ConcateMSA -i aln -x aln -p concatenated -gene2gnm
+
+# output file include:
+concatenated.fasta
+concatenated.phylip
+concatenated.partition.txt
+
+===============================================================
+'''
+
+
+def ConcateMSA(args):
+
+    msa_dir                 = args['i']
+    msa_ext                 = args['x']
+    op_prefix               = args['p']
+    gene2gnm                = args['gene2gnm']
+
+    concatenated_msa_phy    = '%s.phylip'           % op_prefix
+    concatenated_msa_fasta  = '%s.fasta'            % op_prefix
+    partition_file          = '%s.partition.txt'    % op_prefix
+
+    msa_file_re             = '%s/*.%s'             % (msa_dir, msa_ext)
+    msa_file_list           = [os.path.basename(file_name) for file_name in glob.glob(msa_file_re)]
+    msa_file_list_sorted    = sorted(msa_file_list)
+
+    complete_gnm_set = set()
+    for each_msa_file in msa_file_list:
+        pwd_msa = '%s/%s' % (msa_dir, each_msa_file)
+        for each_seq in SeqIO.parse(pwd_msa, 'fasta'):
+            seq_id = each_seq.id
+            if gene2gnm is True:
+                seq_id = '_'.join(seq_id.split('_')[:-1])
+            complete_gnm_set.add(seq_id)
+
+    complete_gnm_list_sorted = sorted([i for i in complete_gnm_set])
+
+    # initialize concatenated msa dict
+    gnm_to_seq_dict = {i: '' for i in complete_gnm_list_sorted}
+    msa_len_dict = dict()
+    for each_msa_file in msa_file_list_sorted:
+        msa_id = each_msa_file.split('.' + msa_ext)[0]
+
+        # read in msa
+        current_msa_len = 0
+        current_msa_len_set = set()
+        pwd_current_msa = '%s/%s' % (msa_dir, each_msa_file)
+        current_msa_seq_dict = dict()
+        for each_seq in SeqIO.parse(pwd_current_msa, 'fasta'):
+            seq_id = each_seq.id
+            if gene2gnm is True:
+                seq_id = '_'.join(seq_id.split('_')[:-1])
+            complete_gnm_set.add(seq_id)
+            current_msa_seq_dict[seq_id] = str(each_seq.seq)
+            current_msa_len_set.add(len(each_seq.seq))
+            current_msa_len = len(each_seq.seq)
+
+        if len(current_msa_len_set) != 1:
+            print('Sequences with different length were found in %s, program exited!' % each_msa_file)
+            exit()
+
+        msa_len_dict[msa_id] = current_msa_len
+
+        # add sequence to concatenated msa dict
+        for each_gnm in complete_gnm_list_sorted:
+            msa_seq = current_msa_seq_dict.get(each_gnm, current_msa_len*'-')
+            gnm_to_seq_dict[each_gnm] += msa_seq
+
+    # write out concatenated msa
+    concatenated_msa_handle = open(concatenated_msa_fasta, 'w')
+    for each_gnm in complete_gnm_list_sorted:
+        concatenated_msa_handle.write('>%s\n' % each_gnm)
+        concatenated_msa_handle.write('%s\n' % gnm_to_seq_dict[each_gnm])
+    concatenated_msa_handle.close()
+
+    # write out partition file
+    end_pos = 0
+    partition_file_handle = open(partition_file, 'w')
+    for each_m in msa_file_list_sorted:
+        gene_id = each_m.split('.' + msa_ext)[0]
+        current_m_len = msa_len_dict[gene_id]
+        partition_file_handle.write('%s = %s-%s\n' % (each_m, (end_pos + 1), (end_pos + current_m_len)))
+        end_pos += current_m_len
+    partition_file_handle.close()
+
+    # convert msa in fasta to phy
+    AlignIO.convert(concatenated_msa_fasta, 'fasta', concatenated_msa_phy, 'phylip-relaxed')
+
+
+
+if __name__ == '__main__':
+
+    # initialize the options parser
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-i',           required=True,                       help='input MSA folder')
+    parser.add_argument('-x',           required=False, default='aln',       help='input file extension')
+    parser.add_argument('-p',           required=True,                       help='output prefix')
+    parser.add_argument('-gene2gnm',    required=False, action="store_true", help='gene id to gnm id, split sequence id before the last _')
+
+    args = vars(parser.parse_args())
+    ConcateMSA(args)

TreeSAK/ConvertMSA.py

@@ -0,0 +1,135 @@
+import os
+import glob
+import argparse
+from Bio import SeqIO
+from Bio import AlignIO
+
+
+ConvertMSA_usage = '''
+================================= ConvertMSA example commands =================================
+
+# phylip to fasta
+TreeSAK ConvertMSA -i concatenated.phy -fi phylip-relaxed -o concatenated.fasta -fo fasta
+TreeSAK ConvertMSA -i phy_files -fi phylip-relaxed -xi phy -o MSA_in_fasta -fo fasta -xo fa 
+
+# examples of alignment format (https://biopython.org/wiki/AlignIO): 
+fasta, phylip, phylip-relaxed, phylip-sequential, clustal
+
+===============================================================================================
+'''
+
+
+def sep_path_basename_ext(file_in):
+
+    # separate path and file name
+    file_path, file_name = os.path.split(file_in)
+    if file_path == '':
+        file_path = '.'
+
+    # separate file basename and extension
+    file_basename, file_extension = os.path.splitext(file_name)
+
+    return file_path, file_basename, file_extension
+
+
+def ConvertMSA(args):
+
+    aln_in            = args['i']
+    aln_in_ext        = args['xi']
+    aln_in_format     = args['fi']
+    aln_out           = args['o']
+    aln_out_ext       = args['xo']
+    aln_out_format    = args['fo']
+    one_line          = args['oneline']
+    no_gap            = args['nogap']
+    force_overwriting = args['f']
+
+    if ((one_line is True) and (aln_out_format != 'fasta')) or ((no_gap is True) and (aln_out_format != 'fasta')):
+        print('Please provide "-oneline" and/or "-nogap" only if "-fo" is fasta')
+        exit()
+
+    if os.path.isfile(aln_in) is True:
+        if (one_line is False) and (no_gap is False):
+            AlignIO.convert(aln_in, aln_in_format, aln_out, aln_out_format)
+        else:
+            aln_out_tmp = aln_out + '.tmp'
+            AlignIO.convert(aln_in, aln_in_format, aln_out_tmp, aln_out_format)
+            pwd_aln_out_handle = open(aln_out, 'w')
+            for each_seq in SeqIO.parse(aln_out_tmp, 'fasta'):
+                seq_id = each_seq.id
+                seq_sequence = str(each_seq.seq)
+                if no_gap is False:
+                    pwd_aln_out_handle.write('>%s\n' % seq_id)
+                    pwd_aln_out_handle.write('%s\n' % seq_sequence)
+                else:
+                    pwd_aln_out_handle.write('>%s\n' % seq_id)
+                    pwd_aln_out_handle.write('%s\n' % seq_sequence.replace('-', ''))
+            pwd_aln_out_handle.close()
+            os.system('rm %s' % aln_out_tmp)
+
+        print('Done!')
+
+    elif os.path.isdir(aln_in) is True:
+        aln_in_re = '%s/*.%s' % (aln_in, aln_in_ext)
+        aln_in_list = [os.path.basename(file_name) for file_name in glob.glob(aln_in_re)]
+
+        # check input
+        if len(aln_in_list) == 0:
+            print('Input file not detected, program exited!')
+            exit()
+
+        # check output folder
+        if os.path.isdir(aln_out) is True:
+            if force_overwriting is True:
+                os.system('rm -r %s' % aln_out)
+            else:
+                print('Output folder already exist, program exited!')
+                exit()
+        os.system('mkdir %s' % aln_out)
+
+        # convert
+        for each_aln_in in aln_in_list:
+
+            aln_in_path, aln_in_basename, aln_in_ext = sep_path_basename_ext(each_aln_in)
+            pwd_aln_in      = '%s/%s'        % (aln_in, each_aln_in)
+            pwd_aln_out     = '%s/%s.%s'     % (aln_out, aln_in_basename, aln_out_ext)
+            pwd_aln_out_tmp = '%s/%s_tmp.%s' % (aln_out, aln_in_basename, aln_out_ext)
+
+            if (one_line is False) and (no_gap is False):
+                AlignIO.convert(pwd_aln_in, aln_in_format, pwd_aln_out, aln_out_format)
+            else:
+                AlignIO.convert(pwd_aln_in, aln_in_format, pwd_aln_out_tmp, aln_out_format)
+                pwd_aln_out_handle = open(pwd_aln_out, 'w')
+                for each_seq in SeqIO.parse(pwd_aln_out_tmp, 'fasta'):
+                    seq_id = each_seq.id
+                    seq_sequence = str(each_seq.seq)
+                    if no_gap is False:
+                        pwd_aln_out_handle.write('>%s\n' % seq_id)
+                        pwd_aln_out_handle.write('%s\n' % seq_sequence)
+                    else:
+                        sequence_no_gap = seq_sequence.replace('-', '')
+                        if len(sequence_no_gap) > 0:
+                            pwd_aln_out_handle.write('>%s\n' % seq_id)
+                            pwd_aln_out_handle.write('%s\n' % sequence_no_gap)
+                pwd_aln_out_handle.close()
+                os.system('rm %s' % pwd_aln_out_tmp)
+        print('Done!')
+    else:
+        print('Input file not found, program exited!')
+
+
+if __name__ == '__main__':
+
+    # initialize the options parser
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-i',       required=True,                       help='input alignment')
+    parser.add_argument('-xi',      required=False, default='aln',       help='input alignment extension')
+    parser.add_argument('-fi',      required=True,                       help='input alignment format, e.g., fasta, phylip')
+    parser.add_argument('-o',       required=True,                       help='output alignment')
+    parser.add_argument('-xo',      required=False, default='aln',       help='output alignment extension')
+    parser.add_argument('-fo',      required=True,                       help='output alignment format, e.g., fasta, phylip')
+    parser.add_argument('-oneline', required=False, action="store_true", help='put sequence in single line, available if -fo is fasta')
+    parser.add_argument('-nogap',   required=False, action="store_true", help='remove gaps from alignment, available if -fo is fasta')
+    parser.add_argument('-f',       required=False, action="store_true", help='force overwrite existing output folder')
+    args = vars(parser.parse_args())
+    ConvertMSA(args)

TreeSAK/Dir.rb

@@ -0,0 +1,82 @@
+require 'find'
+
+
+################################################################################
+class Dir
+    def self.mkdirs(path)
+        if(!File.directory?(path))
+            if(!mkdirs(File.dirname(path)))
+                return false;
+            end
+            mkdir(path)
+        end
+        return true
+    end
+end
+
+
+################################################################################
+def mkdir_with_force(outdir, is_force=false, is_tolerate=false)
+  if outdir.class != String
+    raise "outdir wrong? Exiting ......"
+  end
+
+  if ! Dir.exists?(outdir)
+    `mkdir -p #{outdir}`
+  else
+    if is_tolerate
+      ;
+    elsif is_force
+      `rm -rf #{outdir}`
+      `mkdir -p #{outdir}`
+    else
+      raise "The outdir #{outdir} has already existed!"
+    end
+  end
+end
+
+
+def read_infiles(indir, suffix='', is_all_subfolder=false)
+  infiles = Array.new
+  if ! is_all_subfolder
+    Dir.foreach(indir) do |b|
+      next if b =~ /^\./
+      if suffix.is_a?(String)
+        if suffix != ''
+          next if b !~ /#{suffix}$/
+        end
+      elsif suffix.is_a?(Array)
+        next unless suffix.any?{|i| b =~ /#{i}$/ }
+      end
+      infiles << File.join(indir, b)
+    end
+  else
+    Find.find(indir) do |path|
+      next if File.directory?(path)
+      next if File.basename(path) =~ /^\./
+      infiles << path if suffix.is_a?(String) ? path =~ /\.#{suffix}$/ : suffix.any?{|i| path =~ /#{i}$/ }
+    end
+  end
+  return(infiles)
+end
+
+
+def getFilesBySuffices(indir, suffices)
+  files = Array.new
+  infiles = read_infiles(indir)
+  infiles.each do |infile|
+    if suffices.include?(File.extname(infile))
+      files << infile
+    end
+  end
+  return(files)
+end
+
+
+def get_file_path(file)
+  path = File.symlink?(file) ? File.readlink(file) : file
+  return(path)
+end
+
+################################################################################
+