def main(args):
with fileutil.open_or_stdin(args.i) as fin:
total_sum = np.sum(np.loadtxt(fin))
with fileutil.open_or_stdout(args.o, 'w') as fout:
print >> fout, total_sum
def main(args):
with fileutil.open_or_stdin(args.i) as fin:
M = np.loadtxt(fin, delimiter='\t')
v = np.sum(M, axis=0) + np.sum(M, axis=1)
with fileutil.open_or_stdout(args.o, 'w') as fout:
np.savetxt(fout, v, fmt='%g', delimiter='\t')
def main(args):
# read the description of the genetic code
with open(args.code) as fin_gcode:
arr = list(csv.reader(fin_gcode, delimiter='\t'))
indices, aminos, codons = zip(*arr)
if [int(x) for x in indices] != range(len(indices)):
raise ValueError
# read the input
with fileutil.open_or_stdin(args.i) as fin:
paragraphs = list(gen_paragraphs(fin))
human_header = paragraphs[1][0]
human_lines = paragraphs[1][1:]
chimp_header = paragraphs[2][0]
chimp_lines = paragraphs[2][1:]
if human_header != 'Human_Horai':
raise ValueError
if chimp_header != 'Chimp_Horai':
raise ValueError
human_dna = ''.join(human_lines)
human_codons = [human_dna[i:i+3] for i in range(0, len(human_dna), 3)]
chimp_dna = ''.join(chimp_lines)
chimp_codons = [chimp_dna[i:i+3] for i in range(0, len(chimp_dna), 3)]
codon_alignment_columns = zip(*(human_codons, chimp_codons))
patterns = design.get_pattern_array(codons, codon_alignment_columns)
ncodons = len(codons)
counts = np.zeros((ncodons, ncodons), dtype=int)
for i, j in patterns:
counts[i, j] += 1
# write the (ncodons, ncodons) array of counts of human to chimp changes
with fileutil.open_or_stdout(args.counts_out, 'w') as fout:
np.savetxt(fout, counts, fmt='%g', delimiter='\t')
for i, line in enumerate(paragraphs[0]):
name = line.split()[0]
name_to_index[name] = i
# check that the selected taxa are in the file
missing_taxa = set(selected_taxa) - set(name_to_index)
if missing_taxa:
raise Exception('could not find taxa: ' + ' '.join(missing_taxa))
# write selected lines from each paragraph
for p in paragraphs:
for name in selected_taxa:
i = name_to_index[name]
print >> fout, p[i]
print >> fout
if __name__ == '__main__':
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument('-i', default='-',
help='input interleaved phylip file (default stdin)')
parser.add_argument('-o', default='-',
help='output interleaved phylip file (default stdout)')
parser.add_argument('taxa', nargs='+',
help='taxa to include in the output')
args = parser.parse_args()
with fileutil.open_or_stdin(args.i) as fin:
with fileutil.open_or_stdout(args.o, 'w') as fout:
main(args.taxa, fin, fout)
counts[istate, jstate] += weight
# write the count array
np.savetxt(fout, counts, fmt='%g', delimiter='\t')
if __name__ == '__main__':
# define the command line usage
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument('--taxa', required=True,
help='a tabular file that defines the taxon ordering')
parser.add_argument('--patterns', required=True,
help='each row of this integer array is a pattern'),
parser.add_argument('--pattern-weights',
help='a list of pattern weights (by default all weights are 1)')
parser.add_argument('--initial-taxon-name', required=True,
help='name of the initial taxon')
parser.add_argument('--final-taxon-name', required=True,
help='name of the final taxon')
parser.add_argument('--nstates', type=moretypes.pos_int,
help='size of the Markov state space')
parser.add_argument('--counts-out', default='-',
help='write the count matrix here (default is stdout)')
args = parser.parse_args()
with fileutil.open_or_stdout(args.counts_out, 'w') as fout:
main(args, fout)
