def calculate_distance_of_one_leaf_string_input(tree1_str, tree2_str, leaf_label):
'''
See description for calculate_distance_of_one_leaf_between_trees.
'''
calculated_distance = 0
tree_1 = Tree(tree1_str)
tree_2 = Tree(tree2_str)
for node in tree_1.iter_leaf_names():
difference_in_leaf_distance = abs(tree_1.get_distance(leaf_label, node)
- tree_2.get_distance(leaf_label, node))
calculated_distance += difference_in_leaf_distance
return calculated_distance
def format_alignment(fasta, tree, outdir):
treeroot = tree
fastaroot = path.join(fasta, "*/*prank.best.fas")
check_dir(outdir)
for infile in glob(fastaroot):
# print progress
print infile
basename = path.basename(infile).partition('.')[0]
basename = "".join(basename.split("_")[0] + "_" + basename.split("_")[1])
prefix = basename.partition('_')[0][:2]
fastafile = infile
treedir = path.join(treeroot, prefix)
treefile = path.join(treedir, basename + '.nh')
# create the first 2 directories (fasta_out, fasta_AA_out)
fasta_out_dir = path.join(outdir, "fasta")
check_dir(fasta_out_dir)
fasta_AA_out_dir = path.join(outdir, "fasta_AA")
check_dir(fasta_AA_out_dir)
fasta_out_subdir = path.join(fasta_out_dir, prefix)
check_dir(fasta_out_subdir)
fasta_out_file_path = path.join(fasta_out_subdir, "".join(basename + ".fa"))
fasta_AA_out_subdir = path.join(fasta_AA_out_dir, prefix)
check_dir(fasta_AA_out_subdir)
fasta_AA_out_file_path = path.join(fasta_AA_out_subdir, "".join(basename + ".fa"))
fasta_out_file = open(fasta_out_file_path, "w")
fasta_AA_out_file = open(fasta_AA_out_file_path, "w")
for ID in SeqIO.parse(fastafile,"fasta", alphabet=IUPAC.unambiguous_dna):
tree_ids = Tree(newick=treefile)
for tree_id in tree_ids.iter_leaf_names():
if tree_id.find(ID.id) != -1:
#print ID.id
ID.id = tree_id
#ID.name = ""
ID.description = ""
#print ID.id
#print ID
# write the normal fasta out
SeqIO.write(ID, fasta_out_file, "fasta")
# translate cDNA and write AA fasta
aa_seq = []
coding_dna = ID.seq
#print coding_dna
for codon in grouper(coding_dna, 3):
cog = "".join(codon)
if cog == "---":
aa_seq.append("-")
else:
cog_aa = translate(cog)
aa_seq.append(cog_aa)
aa_seq = "".join(aa_seq)
ID = SeqRecord(Seq(aa_seq, IUPAC.protein), id = ID.id, name = ID.name)
ID.description = ""
SeqIO.write(ID, fasta_AA_out_file, "fasta")
fasta_out_file.close()
fasta_AA_out_file.close()
phy_out_dir = path.join(outdir, "phylip")
check_dir(phy_out_dir)
phy_AA_out_dir = path.join(outdir, "phylip_AA")
check_dir(phy_AA_out_dir)
phy_out_subdir = path.join(phy_out_dir, prefix)
check_dir(phy_out_subdir)
phy_out_file_path = path.join(phy_out_subdir, "".join(basename + ".phy"))
phy_AA_out_subdir = path.join(phy_AA_out_dir, prefix)
check_dir(phy_AA_out_subdir)
phy_AA_out_file_path = path.join(phy_AA_out_subdir, "".join(basename + ".phy"))
fasta_alignment = open(fasta_out_file_path, "rU")
fasta_AA_alignment = open(fasta_AA_out_file_path, "rU")
phy_out_file = open(phy_out_file_path, "w")
phy_AA_out_file = open(phy_AA_out_file_path, "w")
alignments = AlignIO.parse(fasta_alignment, "fasta")
AlignIO.write(alignments, phy_out_file, "phylip-relaxed")
fasta_alignment.close()
phy_out_file.close()
alignments_AA = AlignIO.parse(fasta_AA_alignment, "fasta")
AlignIO.write(alignments_AA, phy_AA_out_file, "phylip-relaxed")
fasta_AA_alignment.close()
phy_AA_out_file.close()
def format_trees(treeroot, fastaroot, outroot):
fastafiles = path.join(fastaroot, "*/*.fa")
if not os.path.exists(outroot):
os.makedirs(outroot)
rooted_out_dir = path.join(outroot, "rooted")
check_dir(rooted_out_dir)
unrooted_out_dir = path.join(outroot, "unrooted")
check_dir(unrooted_out_dir)
for infile in glob(fastafiles):
print infile
basename = path.basename(infile).partition('.')[0]
basename = "".join(basename.split("_")[0] + "_" + basename.split("_")[1])
prefix = basename.partition('_')[0][:2]
fastafile = infile
treedir = path.join(treeroot, prefix)
treefile = path.join(treedir, basename + '.nh')
# make the tree object
tree = Tree(newick=treefile)
# loop that deletes nodes that are not in the alignment
for leaf_name in tree.iter_leaf_names():
name_check = []
for ID in SeqIO.parse(fastafile, "fasta"):
if ID.id in leaf_name:
name_check.append(True)
else:
name_check.append(False)
if any(name_check):
continue
else:
leaf = tree.search_nodes(name=leaf_name)[0]
leaf.delete()
#node = leaf.up
#node.remove_child(leaf)
# create the directories for rooted trees
rooted_out_sub_dir = path.join(rooted_out_dir, prefix)
check_dir(rooted_out_sub_dir)
rooted_out_file = path.join(rooted_out_sub_dir, basename + ".nh")
tree.write(outfile=rooted_out_file, format=6)
# create subdirectories for unrooted trees
unrooted_out_sub_dir = path.join(unrooted_out_dir, prefix)
check_dir(unrooted_out_sub_dir)
unrooted_out_file = path.join(unrooted_out_sub_dir, basename + ".nh")
# unroot the tree
tree.unroot()
tree.write(outfile=unrooted_out_file, format=6)
