nargs='?',
default=None,
type=str,
help="the output summary file\n"
"[stdout if not present]")
return vars(p.parse_args())
if __name__ == "__main__":
args = read_params(sys.argv)
cscores = collections.defaultdict(set)
fwmarkers = {}
maps = collections.defaultdict(set)
tree = ppa.PpaTree(args['taxonomy'])
clades2terms = ppa.clades2terms(tree.tree)
clades2taxa = dict([(clade.full_name,
set([-int(taxon.name[4:]) for taxon in taxa]))
for clade, taxa in clades2terms.items()])
for l in open(args['cscores']):
gene_seed, clade, n, n_tot, coreness = l.strip().split('\t')
gene_seed, clade, n, n_tot, coreness = int(gene_seed), clade, int(
n), int(n_tot), float(coreness)
cscores[gene_seed].add((clade, n, n_tot, coreness))
for i, l in enumerate(open(args['fwmarkers'])):
taxa_id, gene_seed, clade, n, n_tot, coreness, n_ext_seeds, n_ext_taxa, uniqueness, ext_taxa = l.strip(
).split('\t')
default=None,
type=str,
help="the input tree")
p.add_argument('out_file',
nargs='?',
default=None,
type=str,
help="the output file (b2zipped if ending with '.bz2')\n"
"[stdout if not present]")
p.add_argument(
'-n',
action='store_true',
help="Distances normalized with respect to the total branch length")
return vars(p.parse_args())
if __name__ == "__main__":
args = read_params(sys.argv)
ppatree = ppa.PpaTree(args['intree'])
dists = ppa.dist_matrix(ppatree.tree)
tbl = ppatree.tree.total_branch_length() if args['n'] else 1.0
#tbl = ppatree.tree.total_branch_length()-1.0 if args['n'] else 1.0
with utils.openw(args['out_file']) as out:
for k1, v1 in dists.items():
for k2, v2 in v1.items():
if k1 < k2:
out.write("\t".join([k1, k2, str(v2 / tbl)]) + "\n")
def read_params( args ):
p = ap.ArgumentParser(
description='Select top markers')
p.add_argument( 'infile', nargs='?', default=None, type=str,
help= "the input marker file [stdin if not present]")
p.add_argument('outfile', nargs='?', default=None, type=str,
help= "the output core file [stdout if not present]")
p.add_argument('-n', metavar="Maximum number of markers to be selected"
"for each clade",
default=100, type=int )
p.add_argument('--th', metavar="Threshold on markerness",
default=None, type=str )
return vars( p.parse_args() )
if __name__ == "__main__":
args = read_params( sys.argv )
tree = ppa.PpaTree( None )
markers = tree.select_markers( args['infile'], markerness_th = args['th'], max_markers = args['n'] )
with open( args['outfile'], "w" ) as outf:
for clade in markers:
for m in clade:
outf.write( "\n".join( m ) + "\n" )
p = ap.ArgumentParser(description='Profile ChocoPhlAn genes\n')
p.add_argument( '--markers', required = True, default=None, type=str )
p.add_argument( '--euk_taxonomy', required = True, default=None, type=str )
#p.add_argument( '--mic_taxonomy', required = True, default=None, type=str )
p.add_argument('out', nargs='?', default=None, type=str,
help= "the output summary file\n"
"[stdout if not present]")
return vars( p.parse_args() )
if __name__ == "__main__":
args = read_params( sys.argv )
cen2data = {}
etree = ppa.PpaTree( args['euk_taxonomy'] )
#vtree = ppa.PpaTree( args['vir_taxonomy'] )
#mtree = ppa.PpaTree( args['mic_taxonomy'] )
#vall = set([a.name for a in vtree.tree.get_terminals()])
#mall = set([int(a.name[3:]) for a in mtree.tree.get_terminals()])
eall = set([a.name for a in etree.tree.get_terminals()])
lin = (l.split('\t') for l in open(args['markers']))
for d1,cen,taxa,tax,d2,d3,coreness,d4,d5,d6,d7,tin,tout,d8,tsin,tsout in lin:
tsin,tsout = set(["t__"+a for a in tsin.strip().split(":") if a]),set(["t__"+b for b in tsout.strip().split(":") if b])
#tsin,tsout = set([int(a) for a in tsin.strip().split(":") if a]),set([int(b) for b in tsout.strip().split(":") if b])
cen2data[int(cen)] = {'taxa':int(taxa),'tax':tax,'coreness':float(coreness),'tsin':tsin,'tsout':tsout}
tax2cen = collections.defaultdict( set )
for k,v in cen2data.items():
p.add_argument('--mic_taxonomy', required=True, default=None, type=str)
p.add_argument('out',
nargs='?',
default=None,
type=str,
help="the output summary file\n"
"[stdout if not present]")
return vars(p.parse_args())
if __name__ == "__main__":
args = read_params(sys.argv)
cen2data = {}
vtree = ppa.PpaTree(args['vir_taxonomy'])
mtree = ppa.PpaTree(args['mic_taxonomy'])
vall = set([a.name for a in vtree.tree.get_terminals()])
#mall = set([int(a.name[3:]) for a in mtree.tree.get_terminals()])
mall = set([a.name for a in mtree.tree.get_terminals()])
lin = (l.split('\t') for l in open(args['markers']))
for d1, cen, taxa, tax, d2, d3, coreness, d4, d5, d6, d7, tin, tout, d8, tsin, tsout in lin:
tsin, tsout = set(
["t__" + a for a in tsin.strip().split(":")
if a]), set(["t__" + b for b in tsout.strip().split(":") if b])
#tsin,tsout = set([int(a) for a in tsin.strip().split(":") if a]),set([int(b) for b in tsout.strip().split(":") if b])
cen2data[int(cen)] = {
'taxa': int(taxa),
'tax': tax,
'coreness': float(coreness),