'28': 'HR2',
'30': 'G11012',
'24': 'Pm1'
}
# for i in range(len(nos)):
# dt[nos[i]] = dataorder[i]
def get_species_name(node_name_string):
# Species code is the first part of leaf name (separated by an # underscore character)
spcode = node_name_string
# We could even translate the code to complete names
code2name = dt
return code2name[spcode]
t.set_species_naming_function(get_species_name)
for node in t.iter_search_nodes():
if node.name == "43":
node.dist = 5e-05
#t.show(tree_style=ts)
# t.render("/Volumes/MP_HD/CI_GENOME_SEQ/CI_gene_coverage (generate stat for sig diff cov)/gene_copy_no_tree/CI_gain_loss_tree.pdf",tree_style=ts,w=3200,h=4800,dpi=200)
t.render(
"/Volumes/MP_HD/CI_GENOME_SEQ/CI_orthomcl_data/gain_loss_tree_frm_orthogroups/CI_denovo_gene_gain_loss_tree.pdf",
tree_style=ts,
w=3200,
h=4800,
dpi=200)
#!/usr/bin/python
from __future__ import absolute_import
import sys
from ete2 import PhyloTree
if __name__ == "__main__":
t = sys.argv[1]
s = sys.argv[2]
out = sys.argv[3]
pt = PhyloTree(t)
# pt.link_to_alignment(alignment=s)
pt.render(out)
ts = TreeStyle()
# ts.mode = "c"
for i in open(in_id,"r").readlines():
i=i.strip('\n')
print i
outf = "/".join(in_id.split('/')[:-1])+"/top_hits_pm1_madss/"+i+"_blastp_hits_"+in_eval+".fasta"
no_hits = blast_gene(i,in_eval,indb,outf)
print no_hits
align_args = "/usr/local/bin/megacc -a "+ align_mao +" -o "+align_dir+" -s -d " + outf
subprocess.Popen(align_args, shell=True).wait()
sl(2)
align_lis = glob.glob(align_dir + "/*.meg")
alignpath = ''
for j in align_lis:
if i in j:
tree_args = "/usr/local/bin/megacc -a "+ tree_mao +" -o "+tree_dir+" -d " + j
subprocess.Popen(tree_args, shell=True).wait()
tree_ls = glob.glob(tree_dir + "/*.nwk")
for j in tree_ls:
if i in j and "consensus" not in j:
t = PhyloTree(j, format=1)
#t.show()
# t = Phylo.read(j,"newick")
# #t.ladderize()
# #Phylo.draw(t)
# Phylo.write(t,j.replace(".nwk",".xml"),"phyloxml")
# Phylo.draw_graphviz(t,prog="neato")
t.render(tree_dir+"/"+i+"_blastp_hits_"+in_eval+".pdf",tree_style=ts,dpi=200)
### Align if verbose: print "aligning..." aln_file_name = os.path.splitext(temp_file_name)[0] + ".afa" align_muscle(temp_file_name, aln_file_name, gapopen=-1000.0) ### Build tree if verbose: print "building tree..." tree, aln = build_tree_FT(aln_file_name) ### Show in pretty format pretty_tree = PhyloTree(str(tree), alignment=aln_file_name, alg_format="fasta") pretty_tree.ladderize() ts = TreeStyle() pretty_tree.render(outfile, tree_style=ts) ### Clean up your mess os.remove(temp_file_name) os.remove(aln_file_name) ### TODO # highlight adapter rows # root on adapter? # tweak alignment parameters so it's better # understand muscle alignment score. how can we rationally change parameters to improve? # consider NJ. pairwise distances. how would you overlay alignment? # would need pairwise alignment and distance for N^2 ~ 10,000 sequences # what we have is simple and achieves the desired outcome
