def test_sparse_densify():
"""FP densify"""
sparse_fp = [0, 33, 49, 53, 107, 156, 161, 203, 215, 230, 251, 269, 299,
323, 331, 376, 389, 410, 427, 430, 450, 484, 538, 592, 593,
636, 646, 658, 698, 699, 702, 741, 753, 807, 850, 861, 882,
915, 915, 915, 969, 969, 1023]
# count vectors
dense = sparse_to_dense(sparse_fp, size=1024, count_bits=True)
csr = sparse_to_csr_matrix(sparse_fp, size=1024, count_bits=True)
assert_array_equal(dense.reshape(1, -1), csr.toarray())
resparsed = dense_to_sparse(dense)
resparsed_csr = csr_matrix_to_sparse(csr)
assert_array_equal(sparse_fp, resparsed)
assert_array_equal(sparse_fp, resparsed_csr)
# bool vectors
dense = sparse_to_dense(sparse_fp, size=1024, count_bits=False)
csr = sparse_to_csr_matrix(sparse_fp, size=1024, count_bits=False)
assert_array_equal(dense.reshape(1, -1), csr.toarray())
resparsed = dense_to_sparse(dense)
resparsed_csr = csr_matrix_to_sparse(csr)
assert_array_equal(np.unique(sparse_fp), resparsed)
assert_array_equal(np.unique(sparse_fp), resparsed_csr)
# test stacking
np.random.seed(0)
sparse_fps = np.random.randint(0, 1024, size=(20, 100))
dense = np.vstack(sparse_to_dense(fp, size=1024) for fp in sparse_fps)
csr = sparse_vstack(sparse_to_csr_matrix(fp, size=1024) for fp in sparse_fps)
assert_array_equal(dense, csr.toarray())
# test exceptions
with pytest.raises(ValueError):
csr_matrix_to_sparse(np.array([1, 2, 3]))
def test_sparse_densify():
"""FP densify"""
sparse_fp = [
0, 33, 49, 53, 107, 156, 161, 203, 215, 230, 251, 269, 299, 323, 331,
376, 389, 410, 427, 430, 450, 484, 538, 592, 593, 636, 646, 658, 698,
699, 702, 741, 753, 807, 850, 861, 882, 915, 915, 915, 969, 969, 1023
]
# count vectors
dense = sparse_to_dense(sparse_fp, size=1024, count_bits=True)
csr = sparse_to_csr_matrix(sparse_fp, size=1024, count_bits=True)
assert_array_equal(dense.reshape(1, -1), csr.toarray())
resparsed = dense_to_sparse(dense)
resparsed_csr = csr_matrix_to_sparse(csr)
assert_array_equal(sparse_fp, resparsed)
assert_array_equal(sparse_fp, resparsed_csr)
# bool vectors
dense = sparse_to_dense(sparse_fp, size=1024, count_bits=False)
csr = sparse_to_csr_matrix(sparse_fp, size=1024, count_bits=False)
assert_array_equal(dense.reshape(1, -1), csr.toarray())
resparsed = dense_to_sparse(dense)
resparsed_csr = csr_matrix_to_sparse(csr)
assert_array_equal(np.unique(sparse_fp), resparsed)
assert_array_equal(np.unique(sparse_fp), resparsed_csr)
# test stacking
np.random.seed(0)
sparse_fps = np.random.randint(0, 1024, size=(20, 100))
dense = np.vstack([sparse_to_dense(fp, size=1024) for fp in sparse_fps])
csr = sparse_vstack(
sparse_to_csr_matrix(fp, size=1024) for fp in sparse_fps)
assert_array_equal(dense, csr.toarray())
# test exceptions
with pytest.raises(ValueError):
csr_matrix_to_sparse(np.array([1, 2, 3]))
def _gen_pdbbind_desc(self,
pdbbind_dir,
pdbbind_versions=(2007, 2012, 2013, 2014, 2015, 2016),
desc_path=None,
include_general_set=False,
use_proteins=False,
**kwargs):
pdbbind_versions = sorted(pdbbind_versions)
opt = kwargs.get('opt', {})
# generate metadata
df = None
for pdbbind_version in pdbbind_versions:
p = pdbbind('%s/v%i/' % (pdbbind_dir, pdbbind_version),
version=pdbbind_version,
opt=opt)
# Core set
for set_name in p.pdbind_sets:
if set_name == 'general_PL':
dataset_key = '%i_general' % pdbbind_version
else:
dataset_key = '%i_%s' % (pdbbind_version, set_name)
tmp_df = pd.DataFrame({
'pdbid': list(p.sets[set_name].keys()),
dataset_key: list(p.sets[set_name].values())
})
if df is not None:
df = pd.merge(tmp_df, df, how='outer', on='pdbid')
else:
df = tmp_df
df.sort_values('pdbid', inplace=True)
tmp_act = df['%i_general' % pdbbind_versions[-1]].values
df = df.set_index('pdbid').notnull()
df['act'] = tmp_act
# take non-empty and core + refined set
df = df[df['act'].notnull() &
(df.filter(regex='.*_[refined,core]').any(axis=1) |
include_general_set)]
# build descriptos
pdbbind_db = pdbbind('%s/v%i/' % (pdbbind_dir, pdbbind_versions[-1]),
version=pdbbind_versions[-1])
if not desc_path:
desc_path = path_join(dirname(__file__) + 'descs.csv')
if self.n_jobs is None:
n_jobs = -1
else:
n_jobs = self.n_jobs
blacklist = []
if use_proteins:
# list of protein files that segfault OB 2.4.1
blacklist = pdbbind_db.protein_blacklist[oddt.toolkit.backend]
# check if PDBID exists or is blacklisted
desc_idx = [pid for pid in df.index.values
if (pid not in blacklist and
getattr(pdbbind_db[pid], 'protein'
if use_proteins
else 'pocket') is not None)]
result = Parallel(n_jobs=n_jobs, verbose=1)(
delayed(method_caller)(
self.descriptor_generator,
'build',
[pdbbind_db[pid].ligand],
protein=getattr(pdbbind_db[pid], 'protein' if use_proteins
else 'pocket'))
for pid in desc_idx)
# sparse descs may have different shapes, dense are stored np.array
sparse = (hasattr(self.descriptor_generator, 'sparse') and
self.descriptor_generator.sparse)
if not sparse:
result = np.vstack(result)
# create dataframe with descriptors with pdbids as index
df_desc = pd.DataFrame(result, index=desc_idx)
df_desc.index.rename('pdbid', inplace=True)
# for sparse features leave one column and cast explicitly to list
if sparse:
if len(df_desc.columns) > 1:
raise Exception('There are more than one column in the '
'sparse descriptor table.')
df_desc.columns = ['sparse']
df_desc['sparse'] = df_desc['sparse'].map(
lambda x: csr_matrix_to_sparse(x).tolist())
compression = None
if desc_path[-3:] == '.gz':
compression = 'gzip'
# DF are joined by index (pdbid) since some might be missing
df.join(df_desc, how='inner').to_csv(desc_path,
float_format='%.5g',
compression=compression)