def create_gene_tree(bed_file_path):
# dictionary mapping chromosome names to interval trees
models = dict()
#dmRNA = getmRNAlengths(gff3_file_path)
tree = GenomeIntervalTree()
# parse the annotations file (GFF3) and build the interval trees
with open(bed_file_path, 'r') as annotations_file:
reader = csv.reader(annotations_file, delimiter='\t')
for row in reader:
if len(row) == 9 and not row[0].startswith('##'):
seqid = row[0]
start = int(row[1])
end = int(row[2])
strand = row[3]
m_id = row[4]
g_id = row[5]
cov = float(row[6])
idty = float(row[7])
matches = int(row[8])
#tree = None
if tree[seqid].overlaps(start, end):
continue
else:
models[m_id] = 1
models[g_id] = 1
tree[seqid].addi(start,
end,
data=({
"ID": m_id,
"Parent": g_id
}))
return models
def test_pickling():
git = GenomeIntervalTree()
git['a'][1:2] = ['some', 'data']
git['a'][1.5:2.5] = ['more', 'data']
git['b'][10:12] = ['even', 'more', 'data']
s = pickle.dumps(git)
new_git = pickle.loads(s)
assert len(git) == len(new_git)
assert len(git['a']) == len(new_git['a'])
