def parsimony(self, score=False):
"""
Return ancestral state inferred by maximum parsimony method for each site
@param score: bool, return state + score or only return state without score, default: False
@return: tuple, in the form of (state, score) or list, contains states (ancestral state for each site)
"""
state = self.top2bottom()
scores = []
states = []
for s in state:
stating = {}
scoring = []
for ss in s:
cost = ss.pop('cost')
stating[cost] = ss
scoring.append(cost)
min_score = min(scoring)
scores.append(min_score)
states.append(stating[min_score])
if self.save:
nodes = self.nodes(ids=True)
ancestral_state = {}
for n in nodes:
ns = []
for c in states:
ns.append(c[n])
ancestral_state[n] = ''.join(ns)
relationship = ['\t'.join([str(k), str(v[0]), str(v[1]), str(v[2])]) for k, v in self.tree.items()]
state_base_name = os.path.basename(self.mp)
nodes_base_name = os.path.basename(self.mp)
state_filename = state_base_name.replace('.fasta', '') + '_AncestralStates_MP.fasta'
nodes_relationship = nodes_base_name.replace('.fasta', '') + '_NodesRelationship_MP.txt'
state_filename = os.path.join(self.outdir, state_filename)
nodes_relationship = os.path.join(self.outdir, nodes_relationship)
fasta.write(ancestral_state, state_filename)
with open(nodes_relationship, 'wb') as f:
f.write('#ID\tParent\tName\tOffsprings\n')
f.write('\n'.join(relationship))
if score:
return (states, scores)
else:
return states
type=int, help='Maximum read length')
parser.add_argument('--coverage', type=float, action='store', default=11,
help='Desired coverage of given RefSeq')
parser.add_argument('--error', type=float, action='store', default=0,
help='Error rate, in %')
parser.add_argument('--rev', type=float, action='store', default=0,
help='Reverse strip rate, in %')
args = parser.parse_args()
if args.RefSeq == '-':
f = sys.stdin
else:
f = open(args.RefSeq, 'rb')
if args.output == '-':
g = sys.stdout
else:
g = open(args.output, 'wb')
seqs = [s for _, s in parse(f)]
for i, fragment in enumerate(split_reads(seqs, args.min_size,
args.max_size, args.coverage,
args.error, args.rev)):
write(fragment, 'fragment_%d' % i, g)
if args.RefSeq != '-':
f.close()
if args.output != '-':
g.close()
Generator: Generates random genomes for experiments
Author: Paulo Viadanna
"""
from fasta import write
from random import choice
import argparse
import sys
def generate_sequence(size, alphabet='ACGT'):
return "".join([choice(alphabet) for _ in xrange(size)])
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Generate random sequence')
parser.add_argument('Size',
type=int,
nargs='?',
default=1000,
help='Size of generated sequence')
parser.add_argument('Alphabet',
type=str,
nargs='?',
default='ACGT',
help='Alphabet used to generate sequence')
args = parser.parse_args()
g = sys.stdout
write(generate_sequence(args.Size, args.Alphabet),
'random_genome_size_%d' % args.Size, g)
#!/usr/bin/python
"""
Generator: Generates random genomes for experiments
Author: Paulo Viadanna
"""
from fasta import write
from random import choice
import argparse
import sys
def generate_sequence(size, alphabet='ACGT'):
return "".join([choice(alphabet) for _ in xrange(size)])
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Generate random sequence')
parser.add_argument('Size', type=int, nargs='?', default=1000,
help='Size of generated sequence')
parser.add_argument('Alphabet', type=str, nargs='?', default='ACGT',
help='Alphabet used to generate sequence')
args = parser.parse_args()
g = sys.stdout
write(generate_sequence(args.Size, args.Alphabet),
'random_genome_size_%d' % args.Size, g)
