def test_pdd_rounding_down(self):
points = [[0, 0, 2], [0, 0, 2.4]]
x, y = ftuv.pair_distance_distribution(points, 0.3)
nptest.assert_array_equal(x, np.array([0, 0.3]))
nptest.assert_array_equal(y, np.array([0, 1]))
x, y = ftuv.pair_distance_distribution(points, 0.06)
nptest.assert_array_equal(
x, np.array([0, 0.06, 0.12, 0.18, 0.24, 0.3, 0.36]))
nptest.assert_array_equal(y, np.array([0, 0, 0, 0, 0, 0, 1]))
def test_pdd_rounding_down(self):
points = [[0, 0, 2], [0, 0, 2.4]]
x, y = ftuv.pair_distance_distribution(points, 0.3)
nptest.assert_array_equal(x, np.array([0, 0.3]))
nptest.assert_array_equal(y, np.array([0, 1]))
x, y = ftuv.pair_distance_distribution(points, 0.06)
nptest.assert_array_equal(x, np.array(
[0, 0.06, 0.12, 0.18, 0.24, 0.3, 0.36]))
nptest.assert_array_equal(y, np.array(
[0, 0, 0, 0, 0, 0, 1]))
def test_pdd_smaller_step(self):
points = [[0, 0, 4], [0, 0, -4], [3, 0, 0]]
x, y = ftuv.pair_distance_distribution(points, 0.5)
nptest.assert_array_equal(x, np.array(
[0, 0.5, 1, 1.5, 2, 2.5, 3, 3.5, 4, 4.5, 5, 5.5, 6, 6.5, 7, 7.5, 8]))
nptest.assert_array_equal(y, np.array(
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 1]))
def get_allatom_pdd(filename, stepsize):
chains = ftup.get_all_chains(filename)[0]
atoms = []
for chain in chains:
for res in chain:
for atom in res:
atoms.append(atom.coord)
x, y = ftuv.pair_distance_distribution(atoms, stepsize)
df = pd.DataFrame({"step": x, "count": y})
return df
def test_pdd_smaller_step(self):
points = [[0, 0, 4], [0, 0, -4], [3, 0, 0]]
x, y = ftuv.pair_distance_distribution(points, 0.5)
nptest.assert_array_equal(
x,
np.array([
0, 0.5, 1, 1.5, 2, 2.5, 3, 3.5, 4, 4.5, 5, 5.5, 6, 6.5, 7, 7.5,
8
]))
nptest.assert_array_equal(
y, np.array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 1]))
def load(self, pattern):
num_loaded = 0
num_selected = 0
if not isinstance(pattern, list):
pattern = [pattern]
fns = []
for pat in pattern:
fns.extend(glob(pat))
if len(fns) > 1000:
lev = logging.WARNING
else:
lev = logging.INFO
log.log(lev, "Loading %s files", len(fns))
with _LoggingContext(logging.getLogger(), logging.CRITICAL):
for fn in fns:
num_selected += 1
if fn not in self.cgs:
cgs = forgi.load_rna(fn)
if len(cgs) != 1:
raise ValueError(
"Expected 1 RNA component in file {}, found {}:{}".
format(fn, len(cgs)), [cg.name for cg in cgs])
cg, = cgs
cg.infos["filename"] = fn
self.cgs[fn] = cg
num_loaded += 1
if fn not in self.pdds:
points = []
try:
pd_pdd = pd.read_csv(fn + ".pdd.csv")
except:
for i in range(1, cg.seq_length + 1):
points.append(
cg.get_virtual_residue(
i, allow_single_stranded=True))
x, y = ftuv.pair_distance_distribution(
points, stepsize=self.stepsize)
df = pd.DataFrame({"step": x, "count": y})
df.to_csv(fn + ".pdd.csv")
else:
x = pd_pdd["step"]
y = pd_pdd["count"]
self.pdds[fn] = (x, y)
scores = self.get_scores(pattern)
if scores:
minsc = scores[0]
maxsc = scores[-1]
else:
minsc = None
maxsc = None
return num_selected, num_loaded, minsc, maxsc
def test_pdd(self):
points = [[0, 0, 4], [0, 0, -4], [3, 0, 0]]
x, y = ftuv.pair_distance_distribution(points)
nptest.assert_array_equal(x, np.array([0, 1, 2, 3, 4, 5, 6, 7, 8]))
nptest.assert_array_equal(y, np.array([0, 0, 0, 0, 0, 2, 0, 0, 1]))
def test_pdd(self):
points = [[0, 0, 4], [0, 0, -4], [3, 0, 0]]
x, y = ftuv.pair_distance_distribution(points)
nptest.assert_array_equal(x, np.array([0, 1, 2, 3, 4, 5, 6, 7, 8]))
nptest.assert_array_equal(y, np.array([0, 0, 0, 0, 0, 2, 0, 0, 1]))