def load():
valid_chromosomes = set(genome.get_chromosome_lengths())
data = {}
entries = read_bed(filename)
data["chr"] = np.array(
[chromosome_mangler(to_string(e.refseq)) for e in entries],
dtype=np.object)
data["start"] = np.array([e.position for e in entries], dtype=np.int32)
data["stop"] = np.array([e.position + e.length for e in entries],
dtype=np.int32)
data["score"] = np.array([e.score for e in entries], dtype=np.float)
data["strand"] = np.array([e.strand for e in entries], dtype=np.int8)
data["name"] = np.array([to_string(e.name) for e in entries],
dtype=np.object)
data = pd.DataFrame(data)
if filter_invalid_chromosomes: # pragma: no cover
keep = [x in valid_chromosomes for x in data["chr"]]
data = data[keep]
res = data
if len(res) == 0:
raise ValueError("Emtpty Bed file - %s" % filename)
if (np.isnan(res["score"])).all():
res = res.drop(["score"], axis=1)
if (len(res["name"]) > 1) and (len(res["name"].unique()) == 1):
res = res.drop(["name"], axis=1)
return res
def load():
from mbf_fileformats.gff import gffToDict
entries = gffToDict(filename, comment_char=comment_char)
data = {
"chr": [],
"start": [],
"stop": [],
"score": [],
"strand": [],
"name": [],
}
name_found = False
for entry in entries:
if filter_function and not filter_function(entry):
continue
if chromosome_mangler:
chr = chromosome_mangler(entry["seqname"])
else:
chr = entry["seqname"]
data["chr"].append(to_string(chr))
start = entry["start"]
if fix_negative_coordinates and start < 0:
start = 0
data["start"].append(start)
data["stop"].append(entry["end"])
data["score"].append(entry["score"])
data["strand"].append(entry["strand"])
name = entry["attributes"].get("Name", [""])[0]
data["name"].append(name)
if name:
name_found = True
if not name_found:
del data["name"]
return pd.DataFrame(data)
def do_liftover(self, listOfChromosomeIntervals, chain_file):
"""perform a lift over. Error messages are silently swallowed!"""
tmp_input = tempfile.NamedTemporaryFile(mode="wb")
tmp_output = tempfile.NamedTemporaryFile(mode="wb")
tmp_error = tempfile.NamedTemporaryFile(mode="wb")
max_len = 0
listOfChromosomeIntervals = [
list(row) for row in listOfChromosomeIntervals
]
for row in listOfChromosomeIntervals:
tmp_input.write(b" ".join(to_bytes(str(x)) for x in row))
tmp_input.write(b"\n")
max_len = max(len(row), max_len)
tmp_input.write(b"\n")
tmp_input.flush() # it's magic ;)
cmd = [
self.algo.path / "liftOver",
tmp_input.name,
chain_file,
tmp_output.name,
tmp_error.name,
]
p = subprocess.Popen(cmd,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
dummy_stdout, stderr = p.communicate()
if p.returncode != 0: # pragma: no cover
raise ValueError("do_liftover failed. Returncode: %s, stderr: %s" %
(p.returncode, stderr))
tmp_output_in = open(tmp_output.name, "rb")
res = []
for row in tmp_output_in:
row = row.strip().split(b"\t")
row[0] = to_string(row[0])
row[1] = int(row[1])
row[2] = int(row[2])
res.append(tuple(row))
tmp_error_in = open(tmp_error.name, "rb")
tmp_error_in.read()
tmp_input.close()
tmp_output.close()
tmp_error.close()
return res
def test_to_string():
a = "für".encode("utf-8")
b = "für"
assert to_string(b) is b
assert to_string(a) == b
def load():
df = wiggle_to_intervals(filename, comment_char=comment_char)
df["chr"] = [to_string(x) for x in df["chr"]]
df["start"] -= enlarge_5prime
df["stop"] += enlarge_3prime
return df