genomes.txt

d_grimshawi
d_virilis
d_mojavensis
d_willistoni
d_persimilis
d_pseudoobscura
d_ananassae
d_erecta
d_yakuba
d_melanogaster
d_sechellia
d_simulans

output.txt

    /-d_grimshawi
   /-|
  |  |   /-d_virilis
  |   \-|
--|      \-d_mojavensis
  |
  |   /-d_willistoni
  |  |
   \-|      /-d_persimilis
     |   /-|
     |  |   \-d_pseudoobscura
      \-|
        |   /-d_ananassae
        |  |
         \-|      /-d_erecta
           |   /-|
           |  |   \-d_yakuba
            \-|
              |   /-d_melanogaster
               \-|
                 |   /-d_sechellia
                  \-|
                     \-d_simulans
['1', '1', '1', '1', '1', '1', '1', '1', '1', '1', '1', '1'] 4095
['1', '1', '1', '0', '0', '0', '0', '0', '0', '0', '0', '0'] 3584
['0', '1', '1', '0', '0', '0', '0', '0', '0', '0', '0', '0'] 1536
['0', '0', '0', '1', '1', '1', '1', '1', '1', '1', '1', '1'] 511
['0', '0', '0', '0', '1', '1', '1', '1', '1', '1', '1', '1'] 255
['0', '0', '0', '0', '1', '1', '0', '0', '0', '0', '0', '0'] 192
['0', '0', '0', '0', '0', '0', '1', '1', '1', '1', '1', '1'] 63
['0', '0', '0', '0', '0', '0', '0', '1', '1', '1', '1', '1'] 31
['0', '0', '0', '0', '0', '0', '0', '1', '1', '0', '0', '0'] 24
['0', '0', '0', '0', '0', '0', '0', '0', '0', '1', '1', '1'] 7
['0', '0', '0', '0', '0', '0', '0', '0', '0', '0', '1', '1'] 3

permute_clades.py

import argparse
from ete3 import Tree

def get_genome_ids(path):
    genome_id, genomes = 0, {}
    with open(path) as fh:
        for line in fh:
            genomes[line.strip()] = genome_id
            genome_id += 1

    return genomes


def get_clade_ints(path, genomes):
    t = Tree(path)
    clades = []
    print(t)
    for node in t.traverse('preorder'):
        if not node.is_leaf():
            clade = set(n.name for n in node.traverse('preorder') if len(n.name) > 0)
            clades += [clade]

    clade_ints = set()
    for clade in clades:
        binary_int = ['0'] * len(genomes)
        for genome in clade:
            binary_int[genomes[genome]] = '1'

        base_10_int = int(''.join(binary_int), 2)
        print(binary_int, base_10_int)
        clade_ints.add(base_10_int)

    return clade_ints


if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Builds a CdBG using kcollections')
    parser.add_argument('newick_file', type=str, help='Path to the newick file.')
    parser.add_argument('genomes', type=str,
                        help='Path to a file that lists the order of the genomes (one per line).')

    args = parser.parse_args()

    print(args.genomes)
    genomes = get_genome_ids(args.genomes)
    get_clade_ints(args.newick_file, genomes)