treesak 1.53.3__py3-none-any.whl

TreeSAK/RootTreeGTDB220.py

@@ -0,0 +1,300 @@
+import random
+import dendropy
+import argparse
+from ete3 import Tree
+
+
+RootTreeGTDB220_usage = '''
+========================================== RootTreeGTDB220 example command ==========================================   
+
+TreeSAK RootTreeGTDB220 -add_root -d ar -tree ar53.tree -tax ar53.summary.tsv -db db_dir -o ar53.rooted.tree
+TreeSAK RootTreeGTDB220 -add_root -d bac -tree bac120.tree -tax bac120.summary.tsv -db db_dir -o bac120.rooted.tree
+
+# Need to download and decompress the following files to your database folder (provide with -db)
+https://data.ace.uq.edu.au/public/gtdb/data/releases/release220/220.0/ar53_r220.tree.tar.gz
+https://data.ace.uq.edu.au/public/gtdb/data/releases/release220/220.0/bac120_r220.tree.tar.gz
+https://data.ace.uq.edu.au/public/gtdb/data/releases/release220/220.0/ar53_metadata_r220.tsv.gz
+https://data.ace.uq.edu.au/public/gtdb/data/releases/release220/220.0/bac120_metadata_r220.tsv.gz
+
+=====================================================================================================================
+'''
+
+
+def get_smallest_outgroup(tree_object):
+
+    min_outgroup_leaf_num = 99999
+    for each_root_child in tree_object.children:
+        leaf_list = each_root_child.get_leaf_names()
+        if len(leaf_list) < min_outgroup_leaf_num:
+            min_outgroup_leaf_num = len(leaf_list)
+
+    out_group_leaf_list = []
+    for each_root_child in tree_object.children:
+        leaf_list = each_root_child.get_leaf_names()
+        if len(leaf_list) == min_outgroup_leaf_num:
+            out_group_leaf_list = leaf_list
+
+    return out_group_leaf_list
+
+
+def sep_taxon_str(taxon_string):
+
+    taxon_string_split = taxon_string.strip().split(';')
+    taxon_p = taxon_string_split[1]
+    taxon_c = taxon_string_split[2]
+    taxon_o = taxon_string_split[3]
+    taxon_f = taxon_string_split[4]
+    taxon_g = taxon_string_split[5]
+
+    return taxon_p, taxon_c, taxon_o, taxon_f, taxon_g
+
+
+def subset_and_rename_tree(tree_file_in, to_keep_leaf_list, rename_dict):
+
+    input_tree = Tree(tree_file_in, quoted_node_names=True, format=1)
+
+    # subset tree
+    subset_tree = input_tree.copy()
+    subset_tree.prune(to_keep_leaf_list, preserve_branch_length=True)
+
+    # rename leaf
+    for each_leaf in subset_tree:
+        leaf_name_new = rename_dict.get(each_leaf.name, each_leaf.name)
+        each_leaf.name = leaf_name_new
+
+    return subset_tree
+
+
+def root_with_outgroup(input_tree, out_group_list, add_root_branch, tree_file_rooted):
+
+    """
+    Reroot the tree using the given outgroup.
+    modified based on: https://github.com/Ecogenomics/GTDBTk/blob/master/gtdbtk/reroot_tree.py
+
+    input_tree:  File containing Newick tree to rerooted.
+    output_tree: Name of file for rerooted tree.
+    outgroup:    Labels of taxa in outgroup.
+    """
+
+    tree = dendropy.Tree.get_from_path(input_tree, schema='newick', rooting='force-rooted', preserve_underscores=True)
+
+    outgroup_in_tree = set()
+    ingroup_leaves = set()
+    for n in tree.leaf_node_iter():
+        if n.taxon.label in out_group_list:
+            outgroup_in_tree.add(n.taxon)
+        else:
+            ingroup_leaves.add(n)
+
+    # Since finding the MRCA is a rooted tree operation, the tree is first rerooted on an ingroup taxa. This
+    # ensures the MRCA of the outgroup can be identified so long as the outgroup is monophyletic. If the
+    # outgroup is polyphyletic trying to root on it is ill-defined. To try and pick a "good" root for
+    # polyphyletic outgroups, random ingroup taxa are selected until two of them give the same size
+    # lineage. This will, likely, be the smallest bipartition possible for the given outgroup though
+    # this is not guaranteed.
+
+    mrca = tree.mrca(taxa=outgroup_in_tree)
+    mrca_leaves = len(mrca.leaf_nodes())
+    while True:
+        rnd_ingroup = random.sample(list(ingroup_leaves), 1)[0]
+        tree.reroot_at_edge(rnd_ingroup.edge, length1=0.5 * rnd_ingroup.edge_length, length2=0.5 * rnd_ingroup.edge_length)
+        mrca = tree.mrca(taxa=outgroup_in_tree)
+        if len(mrca.leaf_nodes()) == mrca_leaves:
+            break
+        mrca_leaves = len(mrca.leaf_nodes())
+
+    if mrca.edge_length is not None:
+        tree.reroot_at_edge(mrca.edge, length1=0.5 * mrca.edge_length, length2=0.5 * mrca.edge_length)
+
+        # tree.write_to_path(tree_file_rooted, schema='newick', suppress_rooting=True, unquoted_underscores=True)
+        tree_out_string = tree.as_string(schema='newick', suppress_rooting=True, unquoted_underscores=True)
+        tree_out_string = tree_out_string.replace("'", "")
+
+        # add the root bar
+        if add_root_branch is True:
+            tree_out_string = '(' + tree_out_string
+            tree_out_string = tree_out_string.replace(');', '):0.02);')
+
+        # write out tree string
+        tree_file_rooted_handle = open(tree_file_rooted, 'w')
+        tree_file_rooted_handle.write(tree_out_string)
+        tree_file_rooted_handle.close()
+
+
+def RootTreeGTDB220(args):
+
+    input_unrooted_tree = args['tree']
+    user_gnm_taxon      = args['tax']
+    db_dir              = args['db']
+    gnm_domain          = args['d']
+    add_root_branch     = args['add_root']
+    rooted_tree         = args['o']
+
+    leaf_list = []
+    for leaf in Tree(input_unrooted_tree, format=1):
+        leaf_name = leaf.name
+        leaf_list.append(leaf_name)
+
+    # define file name
+    gtdb_ref_tree_ar    = '%s/ar53_r220.tree'           % db_dir
+    gtdb_ref_tree_bac   = '%s/bac120_r220.tree'         % db_dir
+    gtdb_gnm_meta_ar    = '%s/ar53_metadata_r220.tsv'   % db_dir
+    gtdb_gnm_meta_bac   = '%s/bac120_metadata_r220.tsv' % db_dir
+
+    if gnm_domain == 'bac':
+        gtdb_ref_tree = gtdb_ref_tree_bac
+        gtdb_gnm_metadata = gtdb_gnm_meta_bac
+    elif gnm_domain == 'ar':
+        gtdb_ref_tree = gtdb_ref_tree_ar
+        gtdb_gnm_metadata = gtdb_gnm_meta_ar
+    else:
+        print('please provide either "ar" or "bac" to -d')
+        exit()
+
+    tree = Tree(gtdb_ref_tree, quoted_node_names=True, format=1)
+    ref_tree_gnm_list = tree.get_leaf_names()
+    ref_tree_gnm_set = {i for i in ref_tree_gnm_list}
+
+    # read in user_gnm_taxon
+    user_gnm_taxon_dict_p = dict()
+    user_gnm_taxon_dict_c = dict()
+    user_gnm_taxon_dict_o = dict()
+    user_gnm_taxon_dict_f = dict()
+    user_gnm_taxon_dict_g = dict()
+    for each_gnm in open(user_gnm_taxon):
+        if not each_gnm.startswith('user_genome\t'):
+            each_gnm_split = each_gnm.strip().split('\t')
+            gnm_id = each_gnm_split[0]
+            gnm_taxon = each_gnm_split[1]
+
+            if gnm_id in leaf_list:
+                count_current_gnm = False
+                if gnm_domain == 'bac':
+                    if 'd__Bacteria' in gnm_taxon:
+                        count_current_gnm = True
+                elif gnm_domain == 'ar':
+                    if 'd__Archaea' in gnm_taxon:
+                        count_current_gnm = True
+
+                if count_current_gnm is True:
+                    gnm_p, gnm_c, gnm_o, gnm_f, gnm_g = sep_taxon_str(gnm_taxon)
+
+                    if gnm_p not in user_gnm_taxon_dict_p:
+                        user_gnm_taxon_dict_p[gnm_p] = set()
+                    if gnm_c not in user_gnm_taxon_dict_c:
+                        user_gnm_taxon_dict_c[gnm_c] = set()
+                    if gnm_o not in user_gnm_taxon_dict_o:
+                        user_gnm_taxon_dict_o[gnm_o] = set()
+                    if gnm_f not in user_gnm_taxon_dict_f:
+                        user_gnm_taxon_dict_f[gnm_f] = set()
+                    if gnm_g not in user_gnm_taxon_dict_g:
+                        user_gnm_taxon_dict_g[gnm_g] = set()
+
+                    user_gnm_taxon_dict_p[gnm_p].add(gnm_id)
+                    user_gnm_taxon_dict_c[gnm_c].add(gnm_id)
+                    user_gnm_taxon_dict_o[gnm_o].add(gnm_id)
+                    user_gnm_taxon_dict_f[gnm_f].add(gnm_id)
+                    user_gnm_taxon_dict_g[gnm_g].add(gnm_id)
+
+    # determine rooting rank, start from phylum
+    rooting_rank = ''
+    rooting_rank_taxon_dict = dict()
+    if len(user_gnm_taxon_dict_p) > 1:
+        rooting_rank = 'p'
+        rooting_rank_taxon_dict = user_gnm_taxon_dict_p
+    elif len(user_gnm_taxon_dict_c) > 1:
+        rooting_rank = 'c'
+        rooting_rank_taxon_dict = user_gnm_taxon_dict_c
+    elif len(user_gnm_taxon_dict_o) > 1:
+        rooting_rank = 'o'
+        rooting_rank_taxon_dict = user_gnm_taxon_dict_o
+    elif len(user_gnm_taxon_dict_f) > 1:
+        rooting_rank = 'f'
+        rooting_rank_taxon_dict = user_gnm_taxon_dict_f
+    elif len(user_gnm_taxon_dict_g) > 1:
+        rooting_rank = 'g'
+        rooting_rank_taxon_dict = user_gnm_taxon_dict_g
+
+    if rooting_rank == '':
+        print('All user genomes are from the same genus, program exited!')
+        exit()
+
+    col_index = {}
+    canditate_gnms_rooting_rank = dict()
+    counted_taxons_rooting_rank = set()
+    for each_ref in open(gtdb_gnm_metadata):
+            each_ref_split = each_ref.strip().split('\t')
+            if each_ref.startswith('accession	ambiguous_bases'):
+                col_index = {key: i for i, key in enumerate(each_ref_split)}
+            else:
+                ref_accession = each_ref_split[0]
+                gtdb_taxonomy = each_ref_split[col_index['gtdb_taxonomy']]
+                if ref_accession in ref_tree_gnm_set:
+                    gnm_p, gnm_c, gnm_o, gnm_f, gnm_g = sep_taxon_str(gtdb_taxonomy)
+
+                    gnm_rooting_rank = ''
+                    if rooting_rank == 'p':
+                        gnm_rooting_rank = gnm_p
+                    elif rooting_rank == 'c':
+                        gnm_rooting_rank = gnm_c
+                    elif rooting_rank == 'o':
+                        gnm_rooting_rank = gnm_o
+                    elif rooting_rank == 'f':
+                        gnm_rooting_rank = gnm_f
+                    elif rooting_rank == 'g':
+                        gnm_rooting_rank = gnm_g
+
+                    # rooting_rank
+                    if gnm_rooting_rank in rooting_rank_taxon_dict:
+                        if gnm_rooting_rank not in counted_taxons_rooting_rank:
+                            counted_taxons_rooting_rank.add(gnm_rooting_rank)
+                            canditate_gnms_rooting_rank[ref_accession] = gnm_rooting_rank
+
+    ref_tree_rooting_rank = subset_and_rename_tree(gtdb_ref_tree, canditate_gnms_rooting_rank, canditate_gnms_rooting_rank)
+
+    # get the smallest out group taxon set
+    smallest_outgroup_taxon_list = get_smallest_outgroup(ref_tree_rooting_rank)
+
+    user_gnm_taxon_dict_rooting_rank = dict()
+    if rooting_rank == 'p':
+        user_gnm_taxon_dict_rooting_rank = user_gnm_taxon_dict_p
+    elif rooting_rank == 'c':
+        user_gnm_taxon_dict_rooting_rank = user_gnm_taxon_dict_c
+    elif rooting_rank == 'o':
+        user_gnm_taxon_dict_rooting_rank = user_gnm_taxon_dict_o
+    elif rooting_rank == 'f':
+        user_gnm_taxon_dict_rooting_rank = user_gnm_taxon_dict_f
+    elif rooting_rank == 'g':
+        user_gnm_taxon_dict_rooting_rank = user_gnm_taxon_dict_g
+
+    # get the smallest out group genome set
+    out_group_gnm_set_1 = set()
+    out_group_gnm_set_2 = set()
+    for each_rooting_rank_taxon in user_gnm_taxon_dict_rooting_rank:
+        gnm_member_set = user_gnm_taxon_dict_rooting_rank[each_rooting_rank_taxon]
+        if each_rooting_rank_taxon in smallest_outgroup_taxon_list:
+            out_group_gnm_set_1.update(gnm_member_set)
+        else:
+            out_group_gnm_set_2.update(gnm_member_set)
+
+    # select the smaller one as outgroup
+    if len(out_group_gnm_set_1) < len(out_group_gnm_set_2):
+        out_group_gnm_set = out_group_gnm_set_1
+    else:
+        out_group_gnm_set = out_group_gnm_set_2
+
+    # root user tree with identified out group genomes
+    root_with_outgroup(input_unrooted_tree, out_group_gnm_set, add_root_branch, rooted_tree)
+
+
+if __name__ == '__main__':
+
+    RootTreeGTDB220_parser = argparse.ArgumentParser(usage=RootTreeGTDB220_usage)
+    RootTreeGTDB220_parser.add_argument('-tree',        required=True,                         help='input unrooted tree')
+    RootTreeGTDB220_parser.add_argument('-tax',         required=False, default='fna',         help='leaf taxon')
+    RootTreeGTDB220_parser.add_argument('-db',          required=True,                         help='GTDB database files')
+    RootTreeGTDB220_parser.add_argument('-d',           required=False, default=None,          help='domain, either ar or bac')
+    RootTreeGTDB220_parser.add_argument('-add_root',    required=False, action='store_true',   help='add the root branch')
+    RootTreeGTDB220_parser.add_argument('-o',           required=True,                         help='output folder')
+    args = vars(RootTreeGTDB220_parser.parse_args())
+    RootTreeGTDB220(args)

TreeSAK/SequentialDating.py

@@ -0,0 +1,16 @@
+
+SequentialDating_usage = '''
+======================== SequentialDating example commands ========================
+
+TreeSAK SequentialDating -h
+
+===================================================================================
+'''
+
+
+def SequentialDating():
+
+    pass
+
+
+SequentialDating()

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)
+