def test_dna_rna(self):
"""Test if DNA and RNA is correctly processed as ligands"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/1tf6.pdb')
# DNA ligand four times consisting of 31 parts (composite)
self.assertEqual([len(ligand.members)
for ligand in tmpmol.ligands].count(31), 4)
for ligset in [
set((x[0] for x in ligand.members))
for ligand in tmpmol.ligands
]:
if len(ligset) == 4:
# DNA only contains four bases
self.assertEqual(ligset, {'DG', 'DC', 'DA', 'DT'})
def process_pdb(model,
attribution_fn,
pdbfile,
outpath,
input_dim,
radius=12,
bs=16):
mol = PDBComplex()
mol.output_path = outpath
mol.load_pdb(pdbfile, as_string=False)
for ligand in mol.ligands:
mol.characterize_complex(ligand)
create_folder_if_not_exists(outpath)
complexes = [
VisualizerDataWithMolecularInfo(mol, site)
for site in sorted(mol.interaction_sets)
if not len(mol.interaction_sets[site].interacting_res) == 0
]
[
visualize_in_pymol(model,
attribution_fn=attribution_fn,
output_dir=outpath,
plcomplex=plcomplex,
input_dim=input_dim,
radius=radius,
bs=bs) for plcomplex in complexes
]
print()
def test_1bma(self):
"""Binding of aminimide to porcine pancreatic elastase(1bma)
Reference: Peisach et al. Interaction of a Peptidomimetic Aminimide Inhibitor with Elastase. (1995)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/1bma.pdb')
bsid = '0QH:A:256'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Hydrogen bonds to val224 and Gln200
hbonds = {hbond.resnr for hbond in s.hbonds_pdon}
self.assertTrue({224, 200}.issubset(hbonds))
self.assertTrue({224, 200}.issubset(hbonds))
# hydrophobic interaction of Phe223 and val103
hydrophobics = {
hydrophobic.resnr
for hydrophobic in s.all_hydrophobic_contacts
}
self.assertTrue({223, 103}.issubset(hydrophobics))
# Water bridges to Ser203 not detected due to prioritization
waterbridges = {wb.resnr for wb in s.water_bridges}
self.assertTrue(set().issubset(waterbridges))
def test_1hpx(self):
"""
HIV-1 Protease complexes with the inhibitor KNI-272
Reference: Structure of HIV-1 protease with KNI-272, a tight-binding transition-state analog
containing allophenylnorstatine.
Note that the residue numbering is different in the publication and the PDB structure.
For residues in the B chain, the offset is -100 (e.g. Ile 50B in the PDB structure is Ile 150 in the paper).
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/1hpx.pdb')
bsid = 'KNI:B:900'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Hydrophobic contacts to Val82, Ile84, Ile150 as part of flap (S1, S1' sites)
hydroph = {
str(hyd.resnr) + hyd.reschain
for hyd in s.all_hydrophobic_contacts
}
self.assertTrue({'82A', '84A', '50B'}.issubset(hydroph))
# Hydrogen bonds
hbonds = {
str(hbond.resnr) + hbond.reschain
for hbond in s.hbonds_ldon + s.hbonds_pdon
}
# Additional hbond to 25B not detected (low angle?)
self.assertTrue({'29B', '48B', '27B', '25A'}.issubset(hbonds))
# Water bridges
waterbridges = {str(wb.resnr) + wb.reschain for wb in s.water_bridges}
# Waterbridge with Gly27 is detected instead of Ala28/Asp29
self.assertTrue({'50A', '50B', '29A'}.issubset(waterbridges))
def characterize_complex(pdb_file: str, binding_site_id: str) -> PLInteraction:
pdb_complex = PDBComplex()
pdb_complex.load_pdb(pdb_file)
for ligand in pdb_complex.ligands:
if ':'.join([ligand.hetid, ligand.chain, str(ligand.position)]) == binding_site_id:
pdb_complex.characterize_complex(ligand)
return pdb_complex.interaction_sets[binding_site_id]
def test_4kya(self):
"""Binding of non-classical TS inhibitor 3 with Toxoplasma gondii TS-DHFR(4kya)
Reference: Zaware et al. Structural basis of HIV-1 capsid recognition by PF74 and CPSF6(2014)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/4kya.pdb')
bsid = '1UG:E:702'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Hydrogen bonds to Ala609
hbonds = {hbond.resnr for hbond in s.hbonds_pdon}
self.assertTrue({609}.issubset(hbonds))
# Saltbridge to Asp513
saltb = {saltbridge.resnr for saltbridge in s.saltbridge_pneg}
self.assertTrue({513}.issubset(saltb))
# hydrophobic interaction of Ile402, Leu516, Phe520 and Met608
hydrophobics = {
hydrophobic.resnr
for hydrophobic in s.all_hydrophobic_contacts
}
self.assertTrue({402, 516, 520, 608}.issubset(hydrophobics))
# pi-stacking interaction with Trp403 and Phe520
pistackres = {pistack.resnr for pistack in s.pistacking}
self.assertTrue({403, 520}.issubset(pistackres))
def test_1aku(self):
"""Binding of Flavin mononucleotido with D.Vulgaris(1aku)
Reference: McCarthy et al. Crystallographic Investigation of the Role of Aspartate 95 in the Modulation of the
Redox Potentials of DesulfoVibrio Vulgaris Flavodoxin.(2002)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/1aku.pdb')
bsid = 'FMN:A:150'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Hydrogen bonds to Thr59
hbonds = {hbond.resnr for hbond in s.hbonds_pdon}
self.assertTrue({59}.issubset(hbonds))
# Water bridges to Asp63 and Tyr100
waterbridges = {wb.resnr for wb in s.water_bridges}
# Water bridge to Tyr100 not detected due to prioritization
self.assertTrue({63}.issubset(waterbridges))
# hydrophobic interaction of Trp60
hydrophobics = {
hydrophobic.resnr
for hydrophobic in s.all_hydrophobic_contacts
}
self.assertTrue({60}.issubset(hydrophobics))
# pi-stacking interaction with Tyr98
pistackres = {pistack.resnr for pistack in s.pistacking}
self.assertTrue({98}.issubset(pistackres))
def test_4rao(self):
"""Binding of (4rao)
Reference: Keough et al. Aza-acyclic Nucleoside Phosphonates Containing a Second Phosphonate Group
As Inhibitors of the Human, Plasmodium falciparum and vivax 6‑Oxopurine Phosphoribosyltransferases
and Their Prodrugs As Antimalarial Agents (2004)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/4rao.pdb')
bsid = '3L7:B:301'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Hydrogen bonds to Val187, Lys165, Thr141, Lys140, Gly139, Thr138, Asp137
hbonds = {hbond.resnr
for hbond in s.hbonds_pdon
} # res nr 100, 68, 69 and 199 in alternative conformation,
self.assertTrue({137, 138, 139, 140, 141, 165, 187}.issubset(hbonds))
# Water bridges to Asp137, Thr141, Met142, Arg199 and Gly139
# res nr 199 and 142 in alternative conformation
# Water bridges to 137m 141, 139 not detected due to prioritization
# pi-stacking interaction with Phe186
pistackres = {pistack.resnr for pistack in s.pistacking}
self.assertTrue({186}.issubset(pistackres))
def test_3r0t(self):
"""Binding of protein kinase CK2 alpha subunit in with the inhibitor CX-5279 (3r0t)
Reference: Battistutta et al. Unprecedented selectivity and structural determinants of a new class of protein
kinase CK2 inhibitors in clinical trials for the treatment of cancer (2011).
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/3r0t.pdb')
bsid = 'FU9:A:338'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Hydrogen bonds to Val116
hbonds = {hbond.resnr for hbond in s.hbonds_pdon}
self.assertTrue({116}.issubset(hbonds))
# Water bridge to Trp176
waterbridges = {wb.resnr for wb in s.water_bridges}
self.assertTrue({176}.issubset(waterbridges))
# Saltbridge to Ly68
saltb = {saltbridge.resnr for saltbridge in s.saltbridge_lneg}
self.assertTrue({68}.issubset(saltb))
# hydrophobic interaction of Val66, Phe113 and Ile174
hydrophobics = {
hydrophobic.resnr
for hydrophobic in s.all_hydrophobic_contacts
}
self.assertTrue({66, 113, 174}.issubset(hydrophobics))
# pi-stacking interaction with His160
pistackres = {pistack.resnr for pistack in s.pistacking}
self.assertTrue({160}.issubset(pistackres))
def test_3pxf(self):
"""Binding of ANS to CDK2 (3pxf)
Reference: Betzi et al. Discovery of a potential allosteric ligand binding site in CDK2 (2012)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/3pxf.pdb')
bsids = ['2AN:A:305', '2AN:A:304']
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) in bsids:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsids[0]] # 2AN:A:305
# Hydrogen bonding of Asp145 and Phe146
hbonds = {hbond.resnr for hbond in s.hbonds_pdon}
self.assertTrue({145, 146}.issubset(hbonds))
# Salt bridge by Lys33 to sulfonate group
saltb = {saltbridge.resnr for saltbridge in s.saltbridge_lneg}
self.assertTrue({33}.issubset(saltb))
# Naphtalene positioned between Leu55 and Lys56, indicating hydrophobic interactions
hydroph = {hydroph.resnr for hydroph in s.hydrophobic_contacts}
self.assertTrue({55, 56}.issubset(hydroph))
s = tmpmol.interaction_sets[bsids[1]] # 2AN:A:304
# Salt bridges to sulfonate group by Lys56 and His71
saltb = {saltbridge.resnr for saltbridge in s.saltbridge_lneg}
self.assertTrue({56, 71}.issubset(saltb))
# Napthalene with hydrophobic interactions to Ile52 and Leu76
hydroph = {hydroph.resnr for hydroph in s.hydrophobic_contacts}
self.assertTrue({52, 76}.issubset(hydroph))
def test_1bju(self):
"""Binding of ACPU to bovine tripsin(1bju)
Reference: Presnell et al. Oxyanion-Mediated Inhibition of Serine Proteases.(1998)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/1bju.pdb')
bsid = 'GP6:A:910'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
#@todo Publication show hydrogen bond interactions for Gly219
# Hydrogen bonds to Ser190, Ser195, Gly219 and Asp189
hbonds = {hbond.resnr for hbond in s.hbonds_pdon + s.hbonds_ldon}
self.assertTrue({189, 190, 195}.issubset(hbonds))
# Water bridges to Ser190 and Val227
# Water bridge to 190 not detected due to prioritization
waterbridges = {wb.resnr for wb in s.water_bridges}
self.assertTrue({227}.issubset(waterbridges))
# hydrophobic interaction of Leu99
hydrophobics = {
hydrophobic.resnr
for hydrophobic in s.all_hydrophobic_contacts
}
self.assertTrue({99}.issubset(hydrophobics))
# pi-stacking interaction with His57
pistackres = {pistack.resnr for pistack in s.pistacking}
self.assertTrue({57}.issubset(pistackres))
def test_3shy(self):
"""Binding of 5FO to PDE5A1 catalytic domain(3shy)
Reference: Xu et al. Utilization of halogen bond in lead optimization: A case study of rational design of potent
phosphodiesterase type 5 (PDE5) inhibitors.(2011)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/3shy.pdb')
bsid = '5FO:A:1'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Hydrogen bonds to Gln817
hbonds = {hbond.resnr for hbond in s.hbonds_pdon}
self.assertTrue({817}.issubset(hbonds))
# hydrophobic interaction of Tyr612
hydrophobics = {
hydrophobic.resnr
for hydrophobic in s.all_hydrophobic_contacts
}
self.assertTrue({612}.issubset(hydrophobics))
# pi-stacking interaction with Phe820
pistackres = {pistack.resnr for pistack in s.pistacking}
self.assertTrue({820}.issubset(pistackres))
# Halogen Bonding of Tyr612
halogens = {halogen.resnr for halogen in s.halogen_bonds}
self.assertTrue({612}.issubset(halogens))
def test_2w0s(self):
"""Binding of Vacc-TK to TDP (2w0s)
Reference: Caillat et al. Crystal structure of poxvirus thymidylate kinase: An unexpected dimerization
has implications for antiviral therapy (2008)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/2w0s.pdb')
bsid = 'BVP:B:1207' # Complex of BVDU with Magnesium Cofactor
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Hydrogen bonding of Tyr101 and Arg72
hbonds = {hbond.resnr for hbond in s.hbonds_pdon}
self.assertTrue({101, 72}.issubset(hbonds))
# Halogen Bonding of Asn65
halogens = {halogen.resnr for halogen in s.halogen_bonds}
self.assertTrue({65}.issubset(halogens))
# pi-stacking interaction with Phe68
pistackres = {pistack.resnr for pistack in s.pistacking}
self.assertTrue({68}.issubset(pistackres))
# Saltbridge to Arg41 and Arg93
saltb = {saltbridge.resnr for saltbridge in s.saltbridge_lneg}
self.assertTrue({41, 93}.issubset(saltb))
def test_4rdl(self):
"""Binding of Norovirus Boxer P domain with Lewis y tetrasaccharide(4rdl)
Reference: Hao et al. Crystal structures of GI.8 Boxer virus P dimers in complex with HBGAs, a novel
evolutionary path selected by the Lewis epitope..(2014)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/4rdl.pdb')
bsid = 'FUC:A:601'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[
bsid] # Instead of FUC-A-604 (sugar representative)
# Water bridges to Asn395
waterbridges = {wb.resnr for wb in s.water_bridges}
self.assertTrue({395}.issubset(waterbridges))
# Hydrogen bonds to Thr347, Gly348 and Asn395
hbonds = {hbond.resnr for hbond in s.hbonds_pdon}
self.assertTrue({347, 348, 395}.issubset(hbonds))
# hydrophobic interaction of Trp392
hydrophobics = {
hydrophobic.resnr
for hydrophobic in s.all_hydrophobic_contacts
}
self.assertTrue({392}.issubset(hydrophobics))
def test_ids(self):
"""Test if the atom IDs are correctly mapped from internal to original PDB."""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/1vsn.pdb')
bsid = 'NFT:A:283'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
for contact in s.hydrophobic_contacts:
if contact.restype == 'ALA' and contact.resnr == 133:
self.assertEqual(contact.ligatom_orig_idx, 1636)
self.assertEqual(contact.bsatom_orig_idx, 994)
if contact.restype == 'ASP' and contact.resnr == 61:
self.assertEqual(contact.ligatom_orig_idx, 1639)
self.assertEqual(contact.bsatom_orig_idx, 448)
for contact in s.hbonds_ldon + s.hbonds_pdon:
if contact.restype == 'GLN' and contact.resnr == 19:
self.assertEqual(contact.a_orig_idx, 1649)
self.assertEqual(contact.d_orig_idx, 153)
if contact.restype == 'CYS' and contact.resnr == 25:
self.assertEqual(contact.a_orig_idx, 1649)
self.assertEqual(contact.d_orig_idx, 183)
if contact.restype == 'ASN' and contact.resnr == 158:
self.assertEqual(contact.d_orig_idx, 1629)
self.assertEqual(contact.a_orig_idx, 1199)
for contact in s.halogen_bonds:
if contact.restype == 'TYR' and contact.resnr == 67:
self.assertEqual(contact.don.x_orig_idx, 1627)
self.assertEqual(contact.acc.o_orig_idx, 485)
if contact.restype == 'LEU' and contact.resnr == 157:
self.assertEqual(contact.don.x_orig_idx, 1628)
self.assertEqual(contact.acc.o_orig_idx, 1191)
def test_1hvi(self):
"""HIV-1 protease in complex with Diol inhibitor (1hvi)
Reference: Influence of Stereochemistry on Activity and Binding Modes for C2 Symmetry-Based
Diol Inhibitors of HIV-1 Protease (1994)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/1hvi.pdb')
bsid = 'A77:A:800'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Water bridges
waterbridges = {str(wb.resnr) + wb.reschain for wb in s.water_bridges}
# #@todo Water bridge with 50B not detected
self.assertTrue({
'50A'
}.issubset(waterbridges)) # Bridging Ile-B50 and Ile-A50 with ligand
# pi-cation Interactions
picat = {pication.resnr for pication in s.pication_laro}
self.assertEqual(
{8}, picat) # Described as weakly polar contact/stacking in paper
# Hydrogen bonds
hbonds = {
str(hbond.resnr) + hbond.reschain
for hbond in s.hbonds_pdon + s.hbonds_ldon
}
self.assertTrue({'25B', '27A', '27B', '48A', '48B'}.issubset(hbonds))
def test_1n7g(self):
"""Binding of NADPH to MURI from Arabidopsis thaliana (1n7g)
Reference: Mulichak et al. Structure of the MUR1 GDP-mannose 4, 6-dehydratase from Arabidopsis thaliana:
implications for ligand binding and specificity(2002)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/1n7g.pdb')
bsid = 'NDP:A:701'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Hydrogen bonds to Thr37, Gly38, Gln39, Asp40, Arg60, Leu92, Asp91, Ser63, Leu92, Ala115, Ser117,
# Tyr128, Tyr185, Lys189, His215 and Arg220
# Publication give the Prediction for Asp91 as hydrogen bond, when this contains two acceptor atoms.
hbonds = {hbond.resnr for hbond in s.hbonds_pdon}
# #@todo Hbond to 128 not detected
self.assertTrue(
{37, 38, 39, 40, 92, 63, 92, 115, 117, 185, 189, 215,
220}.issubset(hbonds))
# Water bridges to Gly35, Thr37, Gly38, Asp40, Arg60, Arg61, Ser63, Asn66, Ser117, Tyr128, Lys189, Arg220
waterbridges = {wb.resnr for wb in s.water_bridges}
# Hydrogen bonds to 35, 37, 38, 40, 63, 117, 128, 189, 220 not detected due to prioritization
self.assertTrue({60, 66, 61}.issubset(waterbridges))
# Saltbridge to arg60, Arg61, Arg69 and Arg220
saltb = {saltbridge.resnr for saltbridge in s.saltbridge_lneg}
# #@todo Additional saltbridges report to 69 and 200 (with large distances)
self.assertTrue({60, 61}.issubset(saltb))
# Cation-pi interactions with Arg60
picat = {pication.resnr for pication in s.pication_laro}
self.assertEqual({60}, picat)
def test_pi_stacking(self):
pdb_complex = PDBComplex()
pdb_complex.load_pdb('./pdb/4dst_protonated.pdb')
for ligand in pdb_complex.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == 'GCP:A:202':
pdb_complex.characterize_complex(ligand)
structure_report = StructureReport(pdb_complex,
outputprefix="test_")
structure_report.write_xml(as_string=True)
def test_4day(self):
config.PEPTIDES = ['C']
pdb_complex = PDBComplex()
pdb_complex.load_pdb('./pdb/4day.pdb')
for ligand in pdb_complex.ligands:
pdb_complex.characterize_complex(ligand)
structure_report = StructureReport(pdb_complex,
outputprefix="test_")
structure_report.write_xml(as_string=True)
config.PEPTIDES = []
def process_pdb(pdbfile, outpath, as_string=False, outputprefix='report'):
"""Analysis of a single PDB file. Can generate textual reports XML, PyMOL session files and images as output."""
if not as_string:
pdb_file_name = pdbfile.split('/')[-1]
startmessage = f'starting analysis of {pdb_file_name}'
else:
startmessage = 'starting analysis from STDIN'
logger.info(startmessage)
mol = PDBComplex()
mol.output_path = outpath
mol.load_pdb(pdbfile, as_string=as_string)
# @todo Offers possibility for filter function from command line (by ligand chain, position, hetid)
for ligand in mol.ligands:
mol.characterize_complex(ligand)
create_folder_if_not_exists(outpath)
# Generate the report files
streport = StructureReport(mol, outputprefix=outputprefix)
config.MAXTHREADS = min(config.MAXTHREADS, len(mol.interaction_sets))
######################################
# PyMOL Visualization (parallelized) #
######################################
if config.PYMOL or config.PICS:
from plip.visualization.visualize import visualize_in_pymol
complexes = [
VisualizerData(mol, site) for site in sorted(mol.interaction_sets)
if not len(mol.interaction_sets[site].interacting_res) == 0
]
if config.MAXTHREADS > 1:
logger.info(
f'generating visualizations in parallel on {config.MAXTHREADS} cores'
)
parfn = parallel_fn(visualize_in_pymol)
parfn(complexes, processes=config.MAXTHREADS)
else:
[visualize_in_pymol(plcomplex) for plcomplex in complexes]
if config.XML: # Generate report in xml format
streport.write_xml(as_string=config.STDOUT)
if config.TXT: # Generate report in txt (rst) format
streport.write_txt(as_string=config.STDOUT)
def _protein_ligand_interactions(
pdb: str, as_string: bool) -> Tuple[dict, str, dict]:
"""Static method to calculate protein-ligand interactions for each ligand in
the pdb file.
Parameters
----------
pdb : str
File or string containing the protein-ligand complex.
as_string : bool
Variable to know if the pdb passed is a string or a file.
Returns
-------
all_interactions : dict
Dictionary which keys are ligand ids and values are all the interaction data
for that ligand.
pdb_string : str
The corrected pdb stucture as a string.
ligands : dict
Dictionary which keys are ligand Ids and values are pybel molecules
"""
mol_system = PDBComplex()
mol_system.load_pdb(pdb, as_string=as_string)
mol_system.analyze()
pdb_string = mol_system.corrected_pdb
# Dictionary with interactions for each small molecule in the protein
all_interactions = mol_system.interaction_sets
# Store ligands so we can extract their smiles later on.
ligands = dict()
for ligand in mol_system.ligands:
n_atoms = len(ligand.atomorder)
ligand_id = ":".join(
[ligand.hetid, ligand.chain,
str(ligand.position)])
# Filter ions and molecules with less than 5 atoms
if ligand.type != "SMALLMOLECULE" or n_atoms <= 5:
all_interactions.pop(ligand_id)
continue
# ligand.mol is an openbabel molecule
ligands[ligand_id] = ligand.mol
return all_interactions, pdb_string, ligands
def test_2pvb(self):
"""Pike parvalbumin binding calcium (2pvb)
Reference: Harding. The architecture of metal coordination groups in proteins. (2004), Fig. 6
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/2pvb.pdb')
bsid = 'CA:A:110'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain, str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Ca atom with square pyramidal geometry (coordination number 5)
self.assertEqual(s.metal_complexes[0].coordination_num, 5)
self.assertEqual(s.metal_complexes[0].geometry, 'square.pyramidal')
def test_1vsn(self):
"""Binding of NFT to Cathepsin K (1vsn)
Reference: Li et al. Identification of a potent and selective non-basic cathepsin K inhibitor. (2006)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/1vsn.pdb')
bsid = 'NFT:A:283'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Hydrogen bonding to Gly66
hbonds = {hbond.resnr for hbond in s.hbonds_pdon}
self.assertTrue({66}.issubset(hbonds))
def test_1p5e(self):
"""Binding of TBS to CDK2(1p5e)
Reference: De Moliner et al. Alternative binding modes of an inhibitor to two different kinases. (2003)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/1p5e.pdb')
bsid = 'TBS:A:301'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Halogen Bonding of Ile10 and Leu83
halogens = {halogen.resnr for halogen in s.halogen_bonds}
self.assertTrue({10, 83}.issubset(halogens))
def test_1acj(self):
"""Binding of Tacrine (THA) to active-site gorge of acetylcholinesterase (1acj)
Reference: Harel et al. Quaternary ligand binding to aromatic residues in the active-site gorge of
acetylcholinesterase.. (1993)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/1acj.pdb')
bsid = 'THA:A:999'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# pi-stacking interaction with Phe330 and Trp84
pistackres = {pistack.resnr for pistack in s.pistacking}
self.assertTrue({330, 84}.issubset(pistackres))
def test_4qnb(self):
"""Binding of (4qnb)
Reference: Bhattacharya et al. Structural basis of HIV-1 capsid recognition by PF74 and CPSF6(2014)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/4qnb.pdb')
bsid = '1B0:A:301'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Hydrogen bonds to Asn57 and Lys70
hbonds = {hbond.resnr for hbond in s.hbonds_pdon}
self.assertTrue({57, 70}.issubset(hbonds))
# Cation-pi interactions with Lys70
picat = {pication.resnr for pication in s.pication_laro}
self.assertEqual({70}, picat)
def test_1osn(self):
"""Binding of VZV-tk to BVDU-MP (2reg)
Reference: Bird et al. Crystal structures of Varicella Zoster Virus Thyrimidine Kinase. (2003)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/1osn.pdb')
bsid = 'BVP:A:500'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Sandwiched pi-stacking involving Phe93 and Phe139
pistackres = {pistack.resnr for pistack in s.pistacking}
self.assertTrue({93, 139}.issubset(pistackres))
# Hydrogen bonding of Gln90
hbonds = {hbond.resnr for hbond in s.hbonds_pdon}
self.assertTrue({90}.issubset(hbonds))
def test_1eve(self):
"""Binding of anti-Alzheimer drug E2020 to acetylcholinesterase from Torpedo californica (1eve)
Reference: Chakrabarti et al. Geometry of nonbonded interactions involving planar groups in proteins. (2007)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/1eve.pdb')
bsid = 'E20:A:2001'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Aromatic stacking with Trp84 and Trp279
pistackres = {pistack.resnr for pistack in s.pistacking}
self.assertTrue({84, 279}.issubset(pistackres))
# Pi-Cation interaction of Phe330 with ligand
pication = {pication.resnr for pication in s.pication_paro}
self.assertTrue({330}.issubset(pication))
def test_3thy(self):
"""Binding of ADP tp MutS(3thy)
Reference: Shikha et al. Mechanism of mismatch recognition revealed by human MutSβ bound to unpaired DNA loops.(2012)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/3thy.pdb')
bsid = 'ADP:A:935'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Saltbridge to His295 and Lys675
saltb = {saltbridge.resnr for saltbridge in s.saltbridge_lneg}
self.assertTrue({675}.issubset(saltb))
# pi-stacking interaction with Tyr815
pistackres = {pistack.resnr for pistack in s.pistacking}
self.assertTrue({815}.issubset(pistackres))
def test_4alw(self):
"""Binding of benzofuropyrimidinones compound 3 to PIM-1 (4alw)
Reference: Tsuhako et al. The design, synthesis, and biological evaluation of PIM kinase inhibitors.(2012)
"""
tmpmol = PDBComplex()
tmpmol.load_pdb('./pdb/4alw.pdb')
bsid = 'HY7:A:1308'
for ligand in tmpmol.ligands:
if ':'.join([ligand.hetid, ligand.chain,
str(ligand.position)]) == bsid:
tmpmol.characterize_complex(ligand)
s = tmpmol.interaction_sets[bsid]
# Hydrogen bonds to Asp186
hbonds = {hbond.resnr for hbond in s.hbonds_pdon}
self.assertTrue({186}.issubset(hbonds))
# Saltbridge to A186 and Glu171
saltb = {saltbridge.resnr for saltbridge in s.saltbridge_pneg}
self.assertTrue({186, 171}.issubset(saltb))
