treesak 1.53.3__py3-none-any.whl

TreeSAK/AssessPB.py

@@ -0,0 +1,113 @@
+import os
+import argparse
+
+
+AssessPB_usage = '''
+====================== AssessPB example commands ======================
+
+# Dependency: bpcomp and tracecomp (from PhyloBayes-MPI)
+export OMPI_MCA_btl=^openib
+TreeSAK AssessPB -c all_chains.txt
+
+# This is a wrapper for (take 4 chains as an example): 
+bpcomp -x 1000 10 c1 c2 c3 c4
+tracecomp -x 1000 c1 c2 c3 c4
+
+# format of the file provided to -c: directory_path/output_prefix
+GTDB_SCG_best50p0_pb_chain1/GTDB_SCG_best50p0_pb_chain1 
+GTDB_SCG_best50p0_pb_chain2/GTDB_SCG_best50p0_pb_chain2 
+GTDB_SCG_best50p0_pb_chain3/GTDB_SCG_best50p0_pb_chain3 
+GTDB_SCG_best50p0_pb_chain4/GTDB_SCG_best50p0_pb_chain4
+
+=======================================================================
+'''
+
+
+def compare2chains(chain_1, chain_2, chain_3, chain_4, burn_in, sample_interval, 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
+    print('\n================================ bpcomp ================================')
+    os.system(bpcomp_cmd)
+    print('\nGuideline')
+    print('maxdiff < 0.1:     good')
+    print('maxdiff < 0.3:     acceptable, gives a good qualitative picture of the posterior consensus.')
+    print('0.3 < maxdiff < 1: the sample is not yet sufficiently large and have not converged, but on right track.')
+    print('If maxdiff = 1 even after 10,000 points: at least one run stuck in a local maximum.')
+    print('\n============================== tracecomp ==============================\n')
+    os.system(tracecomp_cmd)
+    print('\nGuideline')
+    print('good:       rel diff < 0.1 and minimum effective size > 300')
+    print('acceptable: rel diff < 0.3 and minimum effective size > 50')
+    print('\n========================================================================\n')
+
+
+def AssessPB(args):
+
+    chain_file      = args['c']
+    burn_in         = args['bi']
+    sample_interval = args['si']
+    op_dir          = args['o']
+    force_overwrite = args['f']
+
+    cmd_txt         = '%s/cmds.txt' % op_dir
+
+    # check is chain_file exist
+    if os.path.isfile(chain_file) is False:
+        print('%s not found, program exited!' % chain_file)
+        exit()
+
+    # check if chains were provided in the file
+    chain_list = []
+    for each_chain in open(chain_file):
+        chain_list.append(each_chain.strip())
+    if len(chain_list) < 2:
+        print('Provided %s chains, need at least two chains, program exited!' % len(chain_list))
+        exit()
+
+    # 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 len(chain_list) == 2:
+        compare2chains(chain_list[0], chain_list[1], burn_in, sample_interval, op_dir, cmd_txt)
+    elif len(chain_list) == 3:
+        compare2chains(chain_list[0], chain_list[1], chain_list[2], burn_in, sample_interval, op_dir, cmd_txt)
+    elif len(chain_list) == 4:
+        compare2chains(chain_list[0], chain_list[1], chain_list[2], chain_list[3], burn_in, sample_interval, op_dir, cmd_txt)
+
+
+if __name__ == '__main__':
+
+    AssessPB_parser = argparse.ArgumentParser()
+    AssessPB_parser.add_argument('-c',      required=False, default=None,           help='a txt file contain all the chains')
+    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/C60SR4.nex

@@ -0,0 +1,127 @@
+#nexus
+
+begin models;
+
+frequency C60NT1= 0.6671684132 0.0296031604 0.263873245 0.0393551815;
+
+frequency C60NT2= 0.1276338907 0.0209812196 0.7927062299 0.0586786597;
+
+frequency C60NT3= 0.0163962994 0.0051413956 0.0030074531 0.975454852;
+
+frequency C60NT4= 0.43894983 0.1822394649 0.0174009227 0.3614097825;
+
+frequency C60NT5= 0.0979385646 0.2096596198 0.0222763602 0.6701254554;
+
+frequency C60NT6= 0.245811863 0.1332129821 0.5371646791 0.083810476;
+
+frequency C60NT7= 0.0226930145 0.3959457214 0.0091927563 0.5721685078;
+
+frequency C60NT8= 0.5015838424 0.4308125086 0.0079650295 0.0596386196;
+
+frequency C60NT9= 0.2221963854 0.3881879363 0.1020538807 0.2875617976;
+
+frequency C60NT10= 0.2637737779 0.1509966633 0.2145338888 0.3706956701;
+
+frequency C60NT11= 0.192147964 0.0110024977 0.7823009601 0.0145485781;
+
+frequency C60NT12= 0.1484234234 0.0338349152 0.4455828719 0.3721587895;
+
+frequency C60NT13= 0.7701156248 0.0361294714 0.0511613978 0.142593506;
+
+frequency C60NT14= 0.4210820539 0.0363523971 0.0088100421 0.5337555069;
+
+frequency C60NT15= 0.4443921233 0.0693293801 0.4521540079 0.0341244887;
+
+frequency C60NT16= 0.3775042704 0.0269821801 0.580257087 0.0152564625;
+
+frequency C60NT17= 0.4767453479 0.034379142 0.1231147917 0.3657607185;
+
+frequency C60NT18= 0.0268679326 0.0169276748 0.0098917288 0.9463126639;
+
+frequency C60NT19= 0.3018006878 0.0294470475 0.6420354145 0.0267168502;
+
+frequency C60NT20= 0.3419571734 0.0262071154 0.6184824034 0.0133533078;
+
+frequency C60NT21= 0.0096247416 0.9088039403 0.0103815544 0.0711897638;
+
+frequency C60NT22= 0.1999965426 0.0297517307 0.2954127651 0.4748389616;
+
+frequency C60NT23= 0.1127907248 0.5495098576 0.0691492727 0.268550145;
+
+frequency C60NT24= 0.0776920852 0.0329607437 0.0190469923 0.8703001788;
+
+frequency C60NT25= 0.8938602529 0.0175688123 0.0516233175 0.0369476173;
+
+frequency C60NT26= 0.27898143 0.2724136798 0.2567784573 0.1918264331;
+
+frequency C60NT27= 0.498929145 0.0363065742 0.3503605267 0.1144037542;
+
+frequency C60NT28= 0.2681948281 0.06920056 0.5207582638 0.1418463481;
+
+frequency C60NT29= 0.2045159736 0.0339698809 0.0436529982 0.7178611476;
+
+frequency C60NT30= 0.2691226215 0.0356845278 0.162767839 0.5324250117;
+
+frequency C60NT31= 0.7694198604 0.0996406504 0.090926784 0.040012705;
+
+frequency C60NT32= 0.015577726 0.0724312301 0.0067063212 0.9052847226;
+
+frequency C60NT33= 0.0832030401 0.1132575475 0.2862435644 0.5172958479;
+
+frequency C60NT34= 0.0509990348 0.0082496135 0.0061309345 0.9346204172;
+
+frequency C60NT35= 0.7537265064 0.0213859704 0.1711138164 0.0537737068;
+
+frequency C60NT36= 0.909000965 0.0289286367 0.0266394188 0.0354309794;
+
+frequency C60NT37= 0.9546241163 0.008441069 0.0316827792 0.0052520355;
+
+frequency C60NT38= 0.5192884454 0.0572862542 0.3797587173 0.0436665831;
+
+frequency C60NT39= 0.1341646585 0.5925517098 0.1874442682 0.0858393636;
+
+frequency C60NT40= 0.0448326475 0.0307205308 0.0250541698 0.8993926521;
+
+frequency C60NT41= 0.5664706531 0.0393032078 0.3812930448 0.0129330943;
+
+frequency C60NT42= 0.8370819783 0.0190256158 0.1290970633 0.0147953427;
+
+frequency C60NT43= 0.1120464953 0.0574737723 0.799428803 0.0310509292;
+
+frequency C60NT44= 0.5567531248 0.030047458 0.113077382 0.3001220351;
+
+frequency C60NT45= 0.7530681463 0.0296715581 0.1919452504 0.0253150453;
+
+frequency C60NT46= 0.0813111668 0.4663342365 0.3315560742 0.1207985224;
+
+frequency C60NT47= 0.3493942031 0.0181602391 0.5911205418 0.0413250161;
+
+frequency C60NT48= 0.7273938304 0.0224960247 0.2440348688 0.0060752763;
+
+frequency C60NT49= 0.144800238 0.0781260939 0.6995327663 0.0775409016;
+
+frequency C60NT50= 0.5558261942 0.0217135959 0.355400139 0.0670600707;
+
+frequency C60NT51= 0.0142277933 0.577157862 0.0046886186 0.4039257261;
+
+frequency C60NT52= 0.566952106 0.1662596481 0.0829557817 0.1838324641;
+
+frequency C60NT53= 0.3710307018 0.2568582793 0.3304267825 0.0416842365;
+
+frequency C60NT54= 0.4673591892 0.0443703034 0.0644933219 0.4237771855;
+
+frequency C60NT55= 0.2935718655 0.0371033744 0.5025606284 0.1667641317;
+
+frequency C60NT56= 0.1445054403 0.0175105032 0.8019947085 0.035989348;
+
+frequency C60NT57= 0.5953413269 0.0543418469 0.3379976485 0.0123191777;
+
+frequency C60NT58= 0.5011346064 0.0186312309 0.4456054968 0.034628666;
+
+frequency C60NT59= 0.8862685333 0.0262544484 0.0131639188 0.0743130995;
+
+frequency C60NT60= 0.0386456469 0.0058035261 0.0121187396 0.9434320874;
+
+model C60SR4=GTR+G+FMIX{C60NT1,C60NT2,C60NT3,C60NT4,C60NT5,C60NT6,C60NT7,C60NT8,C60NT9,C60NT10,C60NT11,C60NT12,C60NT13,C60NT14,C60NT15,C60NT16,C60NT17,C60NT18,C60NT19,C60NT20,C60NT21,C60NT22,C60NT23,C60NT24,C60NT25,C60NT26,C60NT27,C60NT28,C60NT29,C60NT30,C60NT31,C60NT32,C60NT33,C60NT34,C60NT35,C60NT36,C60NT37,C60NT38,C60NT39,C60NT40,C60NT41,C60NT42,C60NT43,C60NT44,C60NT45,C60NT46,C60NT47,C60NT48,C60NT49,C60NT50,C60NT51,C60NT52,C60NT53,C60NT54,C60NT55,C60NT56,C60NT57,C60NT58,C60NT59,C60NT60}+F;
+
+end;

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)