def fasta_to_tree(DIR,
fasta,
num_cores,
seqtype,
num_seq_cutoff=NUM_SEQ_CUTOFF):
"""
given a fasta file
align, trim alignment and build a tree
choose appropriate tools depending on size of the fasta file
"""
if DIR[-1] != "/": DIR += "/"
seqcount, maxlen = get_fasta_size(DIR + fasta)
assert seqcount >= 4, "Less than four sequences in " + DIR + fasta
print fasta, seqcount, "sequences"
if seqcount >= NUM_SEQ_CUTOFF: # large cluster
print "running pasta"
alignment = pasta(DIR, fasta, num_cores, seqtype)
cleaned = pxclsq(DIR, alignment, 0.01, seqtype)
if len(read_fasta_file(DIR + cleaned)) >= 4:
tree = fasttree(DIR, cleaned, seqtype)
else:
print "Less than 4 taxa in", cleaned
else: # small cluster
alignment = mafft(DIR, fasta, num_cores, seqtype)
cleaned = pxclsq(DIR, alignment, 0.1, seqtype)
if len(read_fasta_file(DIR + cleaned)) >= 4:
tree = raxml(DIR, cleaned, num_cores, seqtype)
else:
print "Less than 4 taxa in", cleaned
def fasta_to_bs_tree(DIR, fasta, num_cores, seqtype):
"""
given a fasta file for the final homolog
align, trim alignment and build a tree with bootstrap support
"""
if DIR[-1] != "/": DIR += "/"
seqcount, maxlen = get_fasta_size(DIR + fasta)
assert seqcount >= 4, "Less than four sequences in " + DIR + fasta
print fasta, seqcount, "sequences"
alignment = mafft(DIR, fasta, num_cores, seqtype)
cleaned = phyutility(DIR, alignment, 0.2, seqtype)
if len(read_fasta_file(DIR + cleaned)) >= 4:
tree = raxml_bs(DIR, cleaned, num_cores, seqtype)
else:
print "Less than 4 taxa in", cleaned
def fasta_to_tree(DIR,
fasta,
num_cores,
seqtype,
num_seq_cutoff=NUM_SEQ_CUTOFF):
"""
given a fasta file
align, trim alignment and build a tree
choose appropriate tools depending on size of the fasta file
"""
if DIR[-1] != "/": DIR += "/"
seqcount, maxlen = get_fasta_size(DIR + fasta)
assert seqcount >= 3, "Less than three sequences in " + DIR + fasta
print fasta, seqcount, "sequences"
if seqcount >= NUM_SEQ_CUTOFF: # large cluster
alignment = pasta(DIR, fasta, num_cores, seqtype)
# cleaned = phyutility(DIR,alignment,0.01,seqtype)
cleaned = trimal(
DIR, alignment, 0.5,
0.001) # use trimal-added by Tao, now need to def trimal
if len(read_fasta_file(DIR + cleaned)) >= 3:
tree = fasttree(DIR, cleaned, seqtype)
else:
print "Less than 3 taxa in", cleaned
else: # small cluster
alignment = mafft(DIR, fasta, num_cores, seqtype)
# cleaned = phyutility(DIR,alignment,0.1,seqtype) "phyutility can only trim gaps-added by tao"
cleaned = trimal(
DIR, alignment, 0.5,
0.001) # use trimal-added by Tao, now need to def trimal
seqcount, maxlen = get_fasta_size(DIR + cleaned)
print cleaned, seqcount, "sequences"
if len(read_fasta_file(DIR + cleaned)) >= 3:
tree = fasttree(DIR, cleaned, seqtype)
#tree = raxml(DIR,cleaned,num_cores,seqtype)
#if len(read_fasta_file(DIR+cleaned)) == 3: # added by Tao
#tree = fasttree(DIR,cleaned,seqtype) # use added by Tao
else:
print "Less than 3 taxa in", cleaned