import Conf;
import SeqGen;
from Conf import *;
from SeqGen import *;
import generateYaml;
from generateYaml import *;
#conf = Conf("../conf/SeqGen.yaml");
generateYaml("/tmp");
conf = Conf("/tmp/seq.yml");
seqGen = SeqGen(conf);
seqGen.GenerateRandomSequences("negative");
seqGen.GenerateRandomSequences("positive");
motif = seqGen.GenerateMotif()
seqGen.embedMotifInSequence();
print "Positive Set: "
for seq in seqGen.GetPositiveSet():
print seq;
print "Negative Set: "
for seq in seqGen.GetNegativeSet():
print seq;
import SeqGen
from Conf import *
from SeqGen import *
import generateYaml
from generateYaml import *
from SeqGenUtils import *
import sys
directory = sys.argv[1]
CreateConfFiles(directory)
for confFile in findFiles(directory, '*.yml'):
conf = Conf(confFile)
seqGen = SeqGen(conf)
filename = os.path.splitext(os.path.basename(confFile))[0]
posFastaFile = directory + "/" + filename + "_pos.fa"
seqGen.SetPosFileName(posFastaFile)
negFastaFile = directory + "/" + filename + "_neg.fa"
seqGen.SetNegFileName(negFastaFile)
seqGen.GenerateRandomSequences("negative", 0)
seqGen.GenerateRandomSequences("positive", 1)
#seqGen.embedMotifInSequence();
# print "Positive Set: "
# for seq in seqGen.GetPositiveSet():
# print seq;
import SeqGen;
from Conf import *;
from SeqGen import *;
import generateYaml;
from generateYaml import *;
from SeqGenUtils import *;
import sys;
directory = sys.argv[1]
CreateConfFiles(directory);
for confFile in findFiles(directory, '*.yml'):
conf = Conf(confFile);
seqGen = SeqGen(conf);
filename = os.path.splitext(os.path.basename(confFile))[0]
negFastaFile = directory + "/" + filename + "_neg.fa";
seqGen.SetNegFileName(negFastaFile)
seqGen.GenerateRandomSequences("negative", 0);
#seqGen.embedMotifInSequence();
# print "Positive Set: "
# for seq in seqGen.GetPositiveSet():
# print seq;
# print "Negative Set: "
def main(tree_filename, output_filename, single_cols_size, paired_cols_size):
"""
tree_filename --- input newick-format tree filename
output_filename --- output stockholm filename
single|paried cols size --- number of unpaired or paired positions
"""
# msa_filename = 'data/test2.sto'
# lo = .001
# hi = 1.5
# new_tree_filename = 'data/test3.seqgen.tree'
# gen_tree(ntaxa, abl, tree_filename)
tree = dendropy.Tree.get_from_path(tree_filename, 'newick')
# print >> sys.stderr, "rescaling branches to be in [{0},{1})".format(lo, hi)
# Tree.randomly_rescale_branches(tree, lo, hi)
# with open(new_tree_filename, 'w') as f:
# f.write(tree.as_newick_string() + '\n')
# msa = MSA.MSA(msa_filename)
# paired_cols = msa.BP.items()
# paired_cols.sort()
# paired_cols_size = len(paired_cols)
# single_cols_size = msa.aln_len - paired_cols_size * 2
print >> sys.stderr, "{0} single cols, {1} paired cols".format(single_cols_size, paired_cols_size)
tree.print_plot()
oid_preorder = [n.oid for n in tree.preorder_node_iter()]
r = tree.preorder_node_iter()
r.next() # ignore root
order = [(n.edge_length, oid_preorder.index(n.parent_node.oid)) for n in r]
print >> sys.stderr, "order is", order
single_model = SingleModel(SINGLE_MODEL_FULLPATH)
paired_model = PairedModel(PAIRED_MODEL_FULLPATH, single_model)
seqs_s = SeqGen.main(single_model.gtr.R, single_model.Frequency, order, single_cols_size, False)
seqs_p = SeqGen.main(paired_model.gtr.R, paired_model.Frequency, order, paired_cols_size, True)
# now print the generate seqs as stockholm file
with open(output_filename, 'w') as f:
l1 = single_cols_size/2
l2 = single_cols_size - l1
seqrecs = []
# DEBUG BEGIN
# print("self\tparent\tbranch\tsequence")
# for n in tree.preorder_node_iter():
# i = oid_preorder.index(n.oid)
# odd_p = "".join(seqs_p[i][k*2] for k in xrange(paired_cols_size))
# eve_p = "".join(seqs_p[i][k*2+1] for k in xrange(paired_cols_size-1,-1,-1))
# s = seqs_s[i][:l1]
# for k in xrange(paired_cols_size): s += seqs_p[i][k*2]
# for k in xrange(paired_cols_size-1, -1, -1): s += seqs_p[i][k*2+1]
# s += seqs_s[i][l1:]
# print("{0}\t{1}\t{2}\t{3}".format(i, oid_preorder.index(n.parent_node.oid) if n.parent_node is not None else -1, n.edge_length, s))
# if n.is_leaf(): seqrecs.append(SeqRecord(Seq(s), id=n.taxon.label))
# DEBUG END
# COMMENT BELOW WHILE DEBUGGING
for n in tree.leaf_nodes():
i = oid_preorder.index(n.oid)#
#odd_p = "".join(seqs_p[i][k*2] for k in xrange(paired_cols_size))
#eve_p = "".join(seqs_p[i][k*2+1] for k in xrange(paired_cols_size-1,-1,-1))
s = seqs_s[i][:l1]
for k in xrange(paired_cols_size): s += seqs_p[i][k*2]
for k in xrange(paired_cols_size-1, -1, -1): s += seqs_p[i][k*2+1]
s += seqs_s[i][l1:]
seqrecs.append(SeqRecord(Seq(s), id=n.taxon.label))
ss_cons = '.'*l1 + '('*paired_cols_size + ')'*paired_cols_size + '.'*l2
rf = 'x' * (single_cols_size + 2*paired_cols_size)
MSA.write_stockholm(f, seqrecs, ss_cons, rf)
