def test_notSupportedExtension(self):
"""Tests exception throwing when reading file with unsupported extension.
"""
fpath = os.path.join(TESTDIR, 'illusions', 'void.pdb')
with self.assertRaises(ia.structure.StructureError):
ia.read(fpath)
def test_wrongFileType(self):
"""Tests exception throwing when reading file with wrong user-defined type.
"""
fpath = os.path.join(TESTDIR, 'data', 'mini.pdb')
with self.assertRaises(ia.structure.StructureError):
ia.read(fpath, ftype='cif')
def test_missingFile(self):
"""Tests exception throwing when reading non-existent file.
"""
fpath = os.path.join(TESTDIR, 'illusions', 'void.pdb')
with self.assertRaises(ia.structure.StructureError):
ia.read(fpath)
def setUp(self):
pp_path = os.path.join(TESTDIR, 'data', 'protein_protein.cif')
pl_path = os.path.join(TESTDIR, 'data', 'protein_ligand.pdb')
pp_complex = ia.read(pp_path)
pl_complex = ia.read(pl_path)
self.pp_ia = ia.InteractionAnalyzer(pp_complex)
self.pl_ia = ia.InteractionAnalyzer(pl_complex)
def test_readCIF(self):
"""Tests reading/parsing a sample mmCIF file.
"""
fpath = os.path.join(TESTDIR, 'data', 'mini.cif')
s = ia.read(fpath)
top = s.topology
self.assertEqual(top.getNumAtoms(), self.n_atoms)
self.assertEqual(top.getNumResidues(), self.n_residues)
self.assertEqual(top.getNumChains(), self.n_chains)
def setUp(self):
fpath = os.path.join(TESTDIR, 'data', 'mini.pdb')
self.struct = ia.read(fpath)
def comb_int(pdbfile, project_id, itype, include_intra=False, **kwargs):
"""Analyzes the interactions in one or more PDB files.
Arguments
---------
....
"""
curdir = pathlib.Path('.').resolve(strict=True)
output_dir = curdir / str(
project_id[0]) / '02_interfacea_results' / f'{itype}'
output_dir.mkdir(parents=True, exist_ok=True)
# Setup interfacea
ia.set_log_level('minimal')
mol = ia.read(str(pdbfile)) # convert from Path to str.
analyzer = ia.InteractionAnalyzer(mol)
func = getattr(analyzer, f'get_{itype}', None)
if func is None:
raise ValueError(f'Unknown analysis function: get_{itype}')
kwargs['include_intra'] = include_intra
func(**kwargs)
df_table = analyzer.itable._table
df_table.columns = [
'itype', 'donor_chain', 'acceptor_chain', 'donor_resnm',
'acceptor_resnm', 'donor_resid', 'acceptor_resid', 'donor_atom',
'acceptor_atom'
]
if len(df_table) == 0:
logging.info(f'No interactions of type "{itype}" found in input file')
return
donor_list = df_table.apply(
lambda x: x['donor_resnm'] + str(x['donor_resid']), axis=1)
df_table.loc[:, 'donor'] = donor_list
donorC_list = df_table.apply(
lambda x, sep="_": x['donor'] + "_" + str(x['donor_chain']), axis=1)
df_table.loc[:, 'donorC'] = donorC_list
acceptor_list = df_table.apply(
lambda x: x['acceptor_resnm'] + str(x['acceptor_resid']), axis=1)
df_table.loc[:, 'acceptor'] = acceptor_list
acceptorC_list = df_table.apply(
lambda x, sep="_": x['acceptor'] + "_" + str(x['acceptor_chain']),
axis=1)
df_table.loc[:, 'acceptorC'] = acceptorC_list
donor_acceptor_list = df_table.apply(
lambda x, sep=":": x['donorC'] + sep + str(x['acceptorC']), axis=1)
df_table.loc[:, 'donor_acceptor'] = donor_acceptor_list
chain_type = df_table.apply(
lambda x: ("intra"
if (x["acceptor_chain"] == x["donor_chain"]) else "inter"),
axis=1)
df_table.loc[:, 'chain_type'] = chain_type
# You could probably move this to a data.py module.
# Made them sets since you are doing 'x in y' operations.
protein_residues = {
'ALA', 'ASN', 'CYS', 'GLU', 'HIS', 'LEU', 'MET', 'PRO', 'THR', 'TYR',
'ARG', 'ASP', 'GLN', 'GLY', 'ILE', 'LYS', 'PHE', 'SER', 'TRP', 'VAL'
}
dna_residues = {'DA', 'DC', 'DG', 'DT'}
prot_or_dna = []
for i in range(len(df_table.donor_resnm)):
d_is_dna = df_table.donor_resnm[i] in dna_residues
d_is_prot = df_table.donor_resnm[i] in protein_residues
a_is_dna = df_table.acceptor_resnm[i] in dna_residues
a_is_prot = df_table.acceptor_resnm[i] in protein_residues
if d_is_dna and a_is_dna:
cmplx_type = 'dna-dna'
elif d_is_prot and a_is_prot:
cmplx_type = 'protein-protein'
elif (d_is_dna and a_is_prot) or (d_is_prot and a_is_dna):
cmplx_type = 'protein-dna'
else:
cmplx_type = 'other' # because why not?
prot_or_dna.append(cmplx_type)
df_table["prot_or_dna"] = prot_or_dna
# renumber index of hbond dataframe
df_table.index = list(range(len(df_table)))
if itype == 'hbonds':
non_spp_atoms = {
"O2P", "O1P", "N", "O", "OC1", "OC2", "O4'", "O5'", "O3'", "H",
"HA"
}
specificity = []
for i in df_table.index:
specificity_acc = df_table["acceptor_atom"][i] in non_spp_atoms
specificity_donor = df_table["acceptor_atom"][i] in non_spp_atoms
if specificity_acc or specificity_donor:
specificity.append("non-specific")
else:
specificity.append("specific")
df_table['specificity'] = specificity
frame_no = pdbfile.stem.split('md_')[1]
df_table["time"] = [frame_no] * len(df_table)
logging.info(f'Writing "{itype}" bonds to disk...')
df_table.to_csv(str(output_dir / f'md_{frame_no}.pdb_{itype}_all.csv'),
index=False)
def comb_int(pdb: "pdb file", complexName, intType: "interaction type",
includeIntra, hbond_distance):
pathx = os.getcwd()
if not os.path.exists(f'{complexName}/03_interfacea_results/{intType}'):
os.makedirs(f'{complexName}/03_interfacea_results/{intType}',
exist_ok=True)
pwrite = f'{pathx}/{complexName}/03_interfacea_results/{intType}'
ia.set_log_level('minimal')
mol = ia.read(pdb)
analyzer = ia.InteractionAnalyzer(mol)
if not str(intType) == "hbonds":
y = "get_" + str(intType)
b = getattr(analyzer, y)
if str(includeIntra) == "False":
b()
else:
b(include_intra=includeIntra)
bb = analyzer.itable._table
else:
if str(includeIntra) == "False":
analyzer.get_hbonds(max_distance=float(hbond_distance))
else:
analyzer.get_hbonds(include_intra=includeIntra,
max_distance=float(hbond_distance))
bb = analyzer.itable._table
bonds = bb
bonds.columns = [
'itype', 'donor_chain', 'acceptor_chain', 'donor_resnm',
'acceptor_resnm', 'donor_resid', 'acceptor_resid', 'donor_atom',
'acceptor_atom'
]
df_table = bonds
try:
donor_list = df_table.apply(
lambda x: x['donor_resnm'] + str(x['donor_resid']), axis=1)
df_table.loc[:, 'donor'] = donor_list
donorC_list = df_table.apply(
lambda x, sep="_": x['donor'] + "_" + str(x['donor_chain']),
axis=1)
df_table.loc[:, 'donorC'] = donorC_list
acceptor_list = df_table.apply(
lambda x: x['acceptor_resnm'] + str(x['acceptor_resid']), axis=1)
df_table.loc[:, 'acceptor'] = acceptor_list
acceptorC_list = df_table.apply(
lambda x, sep="_": x['acceptor'] + "_" + str(x['acceptor_chain']),
axis=1)
df_table.loc[:, 'acceptorC'] = acceptorC_list
donor_acceptor_list = df_table.apply(
lambda x, sep=":": x['donorC'] + sep + str(x['acceptorC']), axis=1)
df_table.loc[:, 'donor_acceptor'] = donor_acceptor_list
chain_type = df_table.apply(
lambda x: "intra"
if (x["acceptor_chain"] == x["donor_chain"]) else "inter",
axis=1)
df_table.loc[:, 'chain_type'] = chain_type
proteinResidues = [
'ALA', 'ASN', 'CYS', 'GLU', 'HIS', 'LEU', 'MET', 'PRO', 'THR',
'TYR', 'ARG', 'ASP', 'GLN', 'GLY', 'ILE', 'LYS', 'PHE', 'SER',
'TRP', 'VAL'
]
dnaResidues = ['DA', 'DC', 'DG', 'DT']
prot_or_dna = []
for i in range(len(df_table.donor_resnm)):
if (((df_table.donor_resnm[i] in dnaResidues) and
(df_table.acceptor_resnm[i] in proteinResidues))
or ((df_table.donor_resnm[i] in proteinResidues) and
(df_table.acceptor_resnm[i] in dnaResidues))):
prot_or_dna.append("protein-dna")
elif (((df_table.donor_resnm[i] in proteinResidues) and
(df_table.acceptor_resnm[i] in proteinResidues))
or ((df_table.donor_resnm[i] in proteinResidues) and
(df_table.acceptor_resnm[i] in proteinResidues))):
prot_or_dna.append("protein-protein")
elif (((df_table.donor_resnm[i] in dnaResidues) and
(df_table.acceptor_resnm[i] in dnaResidues))
or ((df_table.donor_resnm[i] in dnaResidues) and
(df_table.acceptor_resnm[i] in dnaResidues))):
prot_or_dna.append("dna-dna")
df_table["prot_or_dna"] = prot_or_dna
# renumber index of hbond dataframe
df_table.index = range(len(df_table))
if str(intType) == "hbonds":
non_spp_atoms = [
"O2P", "O1P", "N", "O", "OC1", "OC2", "O4'", "O5'", "O3'", "H",
"HA"
]
x = []
for i in range(len(df_table)):
if (df_table["acceptor_atom"][i]
or df_table["donor_atom"][i]) in non_spp_atoms:
x.append("non-specific")
else:
x.append("specific")
df_table.loc[:, 'specificity'] = x
time = pdb.split("md_")[1].split(".")[0]
times = list(itertools.repeat(time, len(df_table)))
df_table.loc[:, "time"] = times
logging.info("Writing %s bonds to files...", intType)
df_table.to_csv(f'{pwrite}/md_{time}.pdb_{intType}_all.csv',
index=False)
except ValueError:
logging.info(f'Found 0 {intType} interactions !!')
def setUp(self):
fpath = os.path.join(TESTDIR, 'data', 'protein_ligand.pdb')
self.struct = ia.read(fpath)
def setUp(self):
self.pdb = os.path.join(TESTDIR, 'data', 'mini.pdb')
self.cif = os.path.join(TESTDIR, 'data', 'mini.cif')
self.struct = ia.read(self.pdb)
def setUp(self):
self.struct = ia.read(os.path.join(TESTDIR, 'data', 'mini_noH.pdb'))
def setUp(self):
self.s_allatom = ia.read(os.path.join(TESTDIR, 'data', 'mini.pdb'))
self.s_missing = ia.read(
os.path.join(TESTDIR, 'data', 'mini_incomplete.pdb'))