#make output table, one line per hog,
rs = {
'hog': hog,
'target_sel': 0,
'target_non': 0,
'other_sel': 0,
'other_non': 0,
'target_sel_nom': 0,
'other_sel_nom': 0,
'nom_branches': "",
'cor_branches': ""
}
for line in res_list:
taxa = line[0]
if t.search_nodes(name=taxa):
pval = float(line[6])
pvalholm = float(line[7])
is_testclass = node_in_class(taxa, t, testclade)
if pval < 0.05:
if pvalholm < 0.05:
if is_testclass:
rs['target_sel'] = rs['target_sel'] + 1
else:
rs['other_sel'] = rs['other_sel'] + 1
rs['cor_branches'] = rs['cor_branches'] + taxa + ":"
if is_testclass:
rs['target_sel_nom'] = rs['target_sel_nom'] + 1
else:
rs['other_sel_nom'] = rs['other_sel_nom'] + 1
rs['nom_branches'] = rs['nom_branches'] + taxa + ":"
tree.prune(taxa_in_alignment, preserve_branch_length=True)
test_taxa = []
with open(test_taxa_file, 'r') as test_taxa_list:
for taxon in test_taxa_list:
taxon = taxon.rstrip()
test_taxa.append(taxon)
nodes_to_mark = set() # set since we want it to be all unique ids
# Mark the test taxa
for taxon in test_taxa:
taxon_node = tree & taxon # ete3 notation for finding a node within a tree
taxon_id = taxon_node.node_id # mark_tree only takes node_ids, not labels
nodes_to_mark.add(taxon_id)
# Find internal nodes below the test taxa and mark them
for i in range(len(test_taxa), 1, -1):
taxa_groups = [x for x in combinations(test_taxa, i)]
for group in taxa_groups:
common_node = tree.get_common_ancestor(*group)
taxon_id = common_node.node_id
nodes_to_mark.add(taxon_id)
#TODO change the names of the nodes
for mark_id in nodes_to_mark:
test_node = tree.search_nodes(node_id=mark_id)[0]
test_node.name += '{test}'
tree.write(outfile=out_tree_name, format=1)
with open(treefile, 'r') as treefile:
treestring=treefile.read().replace('\n', '')
treestring=re.sub(r"{\w+}", "", treestring)
t=EvolTree(treestring, format=1)
#now read results into list
with open(resultsfile, 'r') as f:
reader=csv.reader(f)
res_list=list(reader)
#make output table, one line per hog,
rs={'hog' : hog, 'selected_nom' : 0, 'selected_holm' : 0, 'total_tests' : 0, 'nom_branches' : "", 'holm_branches' : "", 'tree' : treestring}
for line in res_list:
taxa=line[0]
if t.search_nodes(name=taxa):
pval=float(line[6])
pvalholm=float(line[7])
node_id=trans_node(taxa, t)
rs['total_tests'] = rs['total_tests'] + 1
if pval < 0.05:
if pvalholm < 0.05:
rs['selected_holm'] = rs['selected_holm'] + 1
rs['holm_branches'] = rs['holm_branches'] + node_id + ":"
rs['selected_nom'] = rs['selected_nom'] + 1
rs['nom_branches'] = rs['nom_branches'] + node_id + ":"
print(rs['hog'], rs['selected_holm'], rs['selected_nom'], rs['total_tests'], rs['holm_branches'][:-1], rs['nom_branches'][:-1], rs['tree'], sep="\t")