def test_similarity():
filename_a = os.path.join("data", "276.pdb")
filename_b = os.path.join("data", "4629.pdb")
activesite_a = io.read_active_site(filename_a)
activesite_b = io.read_active_site(filename_b)
# dist(a,b) == expected
assert round(compute_similarity(activesite_a, activesite_b), 3) == 13.857
# dist(a,a) == 0
assert compute_similarity(activesite_a, activesite_a) == 0
# dist(a,b) == dist(b,a)
assert compute_similarity(activesite_a,
activesite_b) == compute_similarity(
activesite_b, activesite_a)
# sign(dist(a,b)) == +
active_sites = read_active_sites("data")
for i in range(len(active_sites)):
for j in range(len(active_sites)):
if i != j:
assert compute_similarity(active_sites[i], active_sites[j]) > 0
def test_hierarchical_clustering():
random.seed(40)
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
# update this assertion
label = cluster.cluster_hierarchically(active_sites)
assert all(label[1] == [0, 0, 1])
def test_rand():
pdb_ids = [276, 4629, 10701, 10814, 13052, 14181]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
c1 = [["276", "4629"], ["10701", "10814"], ["13052", "14181"]]
c2 = [["10701", "10814"], ["276", "4629"], ["13052", "14181"]]
assert compare_clusters.rand_index(c1, c2, active_sites) == 1
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 39299, 38031]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
sim_matrix = cluster.similarity_matrix(active_sites)
assert cluster.cluster_by_partitioning([], {}) == []
assert cluster.cluster_by_partitioning([active_sites[0]],
{}) == [[active_sites[0]]]
def test_distance_to_self():
#dist(a,a)==0
pdb_ids = [276]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
features = find_features.calc_features(active_sites)
x = scoring.L2(features['276'], features['276'])
assert x == 0.0
def test_hierarchical_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
# update this assertion
# checking the the three sites cluster as expected
assert np.array_equal(
cluster.cluster_hierarchically(active_sites, 2)[0], [0, 0, 1])
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
assert cluster.cluster_by_partitioning(active_sites) == [["276"], ["4629"],
["10701"]]
# check empty active sites doesn't crash
assert cluster.cluster_by_partitioning(None) is None
def test_recip_distance():
#dist(a,b)==dist(b,a)
pdb_ids = [276, 4629]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
features = find_features.calc_features(active_sites)
assert scoring.L2(features['276'],
features['4629']) == scoring.L2(features['4629'],
features['276'])
def test_hierarchical_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
# update this assertion
assert cluster.test_format_hier(
cluster.cluster_hierarchically(active_sites)) == [[[276, 4629],
[10701]],
[[276, 4629, 10701]]]
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701, 10701,10814,13052,14181,15813]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb"%id)
active_sites.append(io.read_active_site(filepath))
cluster.get_order_residues(active_sites)
# update this assertion
assert len(cluster.cluster_by_partitioning(active_sites,2)[0]) == 2
assert len(cluster.cluster_by_partitioning(active_sites,3)[0]) == 3
def test_hierarchical_clustering():
# tractable subset
pdb_ids = [276, 52954, 34088]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
sim_matrix = cluster.similarity_matrix(active_sites)
# update this assertion
assert cluster.cluster_hierarchically([], {}) == []
assert cluster.cluster_hierarchically([active_sites[0]],
{}) == [[active_sites[0]]]
def test_hierarchical_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
features = find_features.calc_features(active_sites)
for res, feature_vect in features.items():
hier.hierarchical("V" + res, feature_vect, metric='Euclidian')
assert hier.hierarchical.Cluster()
def test_hierarchical_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
assignment = cluster.cluster_hierarchically(active_sites)
assert cluster.convert_indices_to_active_sites(assignment,
active_sites) == [["276"],
["4629"],
["10701"]]
pdb_ids = [276, 4629]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
# check empty active sites doesn't crash
assert cluster.cluster_hierarchically(None, K=10) is None
def test_hierarchical_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
# clusters more similar clusters together
clustering = cluster.cluster_hierarchically(active_sites, [2])
assert get_names(flatten(clustering[0])) in [['4629', '276'], ['10701']]
assert get_names(flatten(clustering[1])) in [['4629', '276'], ['10701']]
# len(clustered_list.unique()==k)
active_sites = read_active_sites("data")
assert len(cluster.cluster_hierarchically(active_sites, [2])) == 2
assert len(cluster.cluster_hierarchically(active_sites, [3])) == 3
def test_hierarchical_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
clusters = []
for clust in cluster.cluster_hierarchically(active_sites, 1):
elems = []
for e in clust:
elems.append([int(n.name) for n in e])
clusters.append(elems)
assert clusters == [[[276], [4629], [10701]], [[276], [10701, 4629]],
[[276, 10701, 4629]]]
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
features = find_features.calc_features(active_sites)
data = []
for res, feature_vect in features.items():
data.append(kmeans.data_point(label=res, data=tuple(feature_vect)))
km = kmeans.kmeans(data=data, k=3, threshold=3)
km.cluster()
# update this assertion
assert len(km.centroids.items()) == 3
def test_get_order_residues():
filename_a = os.path.join("data", "46495.pdb")
activesite_a = io.read_active_site(filename_a)
assert np.array_equal((activesite_a.newresidues),[])
cluster.get_order_residues([activesite_a])
assert np.array_equal((activesite_a.newresidues),['ASP', 'LYS', 'SER', 'ARG', 'ASP', 'ASP', 'ASP'])