def test_zinc_finger(tmp_path):
gmx.show_log()
##################################
# ## Create the topologie: ###
##################################
prot = gmx.GmxSys(name='1jd4', coor_file=PDB_1JD4)
prot.prepare_top(out_folder=os.path.join(tmp_path, 'top_DIAP1'),
vsite='hydrogens',
ignore_ZN=False)
top_coor = pdb_manip.Coor(prot.coor_file)
assert top_coor.num == 3292
prot.switch_ion_octa_dummy()
top_coor = pdb_manip.Coor(prot.coor_file)
assert top_coor.num == 3304
prot.solvate_add_ions(out_folder=os.path.join(tmp_path, 'top_sys'),
maxwarn=3)
prot.em(out_folder=os.path.join(tmp_path, 'em_DIAP1'),
nsteps=10,
constraints='none')
em_coor = pdb_manip.Coor(prot.coor_file)
assert em_coor.num == 56366
ener_pd = prot.get_ener(['Potential'])
assert ener_pd['Potential'].values[-1] < -155000
def test_cys_bond_charmm(tmp_path):
gmx.show_log()
##################################
# ## Create the topologie: ###
##################################
prot = gmx.GmxSys(name='1dpx', coor_file=PDB_1DPX)
prot.prepare_top(out_folder=os.path.join(tmp_path, 'top_DISU'),
vsite='hydrogens',
ignore_ZN=False)
top_coor = pdb_manip.Coor(prot.coor_file)
assert top_coor.num == 2096
prot.solvate_add_ions(out_folder=os.path.join(tmp_path, 'top_sys'),
maxwarn=3)
prot.em(out_folder=os.path.join(tmp_path, 'em_DISU'),
nsteps=10,
constraints='none')
em_coor = pdb_manip.Coor(prot.coor_file)
assert em_coor.num == 27086
cystein_s_index = em_coor.get_index_selection({
'name': ['SG'],
'res_name': ['CYS']
})
distance = pdb_manip.Coor.atom_dist(em_coor.atom_dict[cystein_s_index[0]],
em_coor.atom_dict[cystein_s_index[-1]])
assert distance < 2.1
def test_insert_ethanol(tmp_path):
gmx.show_log()
##################################
# ## Create the topologie: ###
##################################
prot = gmx.GmxSys(name='1y0m', coor_file=PDB_1Y0M)
prot.prepare_top(out_folder=os.path.join(tmp_path, 'top_SH3'))
top_coor = pdb_manip.Coor(prot.coor_file)
assert top_coor.num == 996
prot.solvate_add_ions(out_folder=os.path.join(tmp_path, 'top_sys'))
prot.em(out_folder=os.path.join(tmp_path, 'em_SH3'),
nsteps=10,
constraints='none')
em_coor = pdb_manip.Coor(prot.coor_file)
assert em_coor.num == 15383
ener_pd = prot.get_ener(['Potential'])
assert ener_pd['Potential'].values[-1] < -155000
###################################
# ### Create Ethanol system ###
###################################
smile = 'CCO'
eth_pdb = os.path.join(tmp_path, 'ethanol.pdb')
charge = ambertools.smile_to_pdb(smile, eth_pdb, 'ETH')
assert charge == 0
eth_sys = gmx.GmxSys(name='ETH', coor_file=eth_pdb)
eth_sys.prepare_top_ligand(out_folder=os.path.join(tmp_path, 'eth_top'),
ff='amber99sb-ildn',
include_mol={'ETH': smile})
eth_sys.create_box(name=None, dist=0.5)
####################################################
# # Insert 4 copy of ethanol in the SH3 system: ###
####################################################
prot.insert_mol_sys(mol_gromacs=eth_sys,
mol_num=10,
new_name='SH3_ETH',
out_folder=os.path.join(tmp_path, 'top_ETH_SH3'))
################################
# ## Minimize the system ###
################################
prot.em_2_steps(out_folder=os.path.join(tmp_path, 'em_ETH_SH3'),
no_constr_nsteps=10,
constr_nsteps=10)
prot_lig_coor = pdb_manip.Coor(prot.coor_file)
assert 15300 < prot_lig_coor.num < 15518
prot.display_history()
def test_insert_peptide_vsite(tmp_path):
gmx.show_log()
##################################
# ## Create the topologie: ###
##################################
prot = gmx.GmxSys(name='1y0m', coor_file=PDB_1Y0M)
prot.prepare_top(out_folder=os.path.join(tmp_path, 'top_SH3'),
vsite='hydrogens')
top_coor = pdb_manip.Coor(prot.coor_file)
assert top_coor.num == 1064
prot.solvate_add_ions(out_folder=os.path.join(tmp_path, 'top_sys'))
prot.em(out_folder=os.path.join(tmp_path, 'em_SH3'),
nsteps=10,
constraints='none')
em_coor = pdb_manip.Coor(prot.coor_file)
assert em_coor.num == 15337
ener_pd = prot.get_ener(['Potential'])
assert ener_pd['Potential'].values[-1] < -155000
###################################
# ## Create a DD peptide ###
###################################
pep = gmx.GmxSys(name='DD')
pep.create_peptide(sequence='DD',
out_folder=os.path.join(tmp_path, 'top_DD'),
em_nsteps=10,
equi_nsteps=0,
vsite='hydrogens')
####################################################
# # Insert 4 copy of ethanol in the SH3 system: ###
####################################################
prot.insert_mol_sys(mol_gromacs=pep,
mol_num=10,
new_name='SH3_DD',
out_folder=os.path.join(tmp_path, 'top_DD_SH3'))
################################
# ## Minimize the system ###
################################
prot.em_2_steps(out_folder=os.path.join(tmp_path, 'em_DD_SH3'),
no_constr_nsteps=10,
constr_nsteps=10)
prot_lig_coor = pdb_manip.Coor(prot.coor_file)
assert 15300 < prot_lig_coor.num < 15518
prot.display_history()
def make_amber_top_mol_rdkit(pdb_in,
res_name,
smile,
charge_model="bcc",
atom_type="gaff",
remove_h=True):
full_coor = pdb_manip.Coor(pdb_in)
# Select coor:
mol_coor = full_coor.select_part_dict(selec_dict={'res_name': [res_name]})
# Change first residue to 1, as it is the res from rdkit output
res_list = mol_coor.get_attribute_selection(attribute='res_num')
index_list = mol_coor.get_index_selection(
selec_dict={'res_num': [res_list[0]]})
mol_coor.change_index_pdb_field(index_list, change_dict={'res_num': 1})
# Remove hydrogens:
if remove_h:
to_del_list = []
for atom_num, atom in mol_coor.atom_dict.items():
if atom['name'].startswith('H'):
to_del_list.append(atom_num)
mol_coor.del_atom_index(to_del_list)
mol_coor.write_pdb(res_name + '.pdb', check_file_out=False)
# Add hydrogens:
# add_hydrogen(res_name+'.pdb', res_name+'_h.pdb')
charge = add_hydrogen_rdkit(res_name + '.pdb', smile, res_name + '_h.pdb')
# Get only one molecule
mol_h_coor = pdb_manip.Coor(res_name + '_h.pdb')
res_list = mol_h_coor.get_attribute_selection(attribute='uniq_resid')
mol_uniq_coor = mol_h_coor.select_part_dict(
selec_dict={'uniq_resid': [res_list[0]]})
# Save coordinates:
mol_uniq_coor.write_pdb(res_name + '_h_unique.pdb', check_file_out=False)
# Compute topologie with acpype:
gmxsys = acpype(res_name + '_h_unique.pdb',
res_name,
net_charge=charge,
charge_model="bcc",
atom_type="gaff")
return ({
'GmxSys': gmxsys,
'coor': os_command.full_path_and_check(res_name + '_h.pdb'),
'num': len(res_list)
})
def test_solv_water_free(tmp_path):
mol_free = FreeEner('DEN', f'{tmp_path}/indene_water_solv')
mol_free.water_box_from_SMILE('C1C=Cc2ccccc12')
start_coor = pdb_manip.Coor(mol_free.gmxsys.coor_file)
assert start_coor.num == 1625
# To avoid domain decomposition errors:
# Use only one proc
mol_free.gmxsys.nt = 1
mol_free.equilibrate_solvent_box(em_steps=100,
dt=0.002,
prod_time=0.02,
short_steps=500)
delta_coul = 0.5
coul_list = np.arange(0, 1 + delta_coul, delta_coul)
vdw_coul = 0.5
vdw_list = np.arange(0, 1 + vdw_coul, vdw_coul)
mol_free.run(lambda_coul_list=coul_list,
lambda_vdw_list=vdw_list,
em_steps=100,
nvt_time=0.1,
npt_time=0.1,
prod_time=0.1,
temp_groups='System')
dg_solv, dg_std_solv = mol_free.get_free_ener()
print(dg_solv, dg_std_solv)
assert ((10 < dg_solv) and (dg_solv < 30))
def test_plot_3D(tmp_path):
"""
Test plot_pseudo_3D with chains.
"""
prot_coor = pdb_manip.Coor(PDB_1JD4)
plot_chain = prot_coor.plot_pseudo_3D('chain')
plot_properties = plot_chain.properties()
assert plot_properties['color'].shape == (191, 4)
assert len(plot_properties['segments']) == 191
np.testing.assert_allclose(plot_properties['color'][0],
[0.66666667, 0., 0.10666667, 1.],
rtol=1e-06)
np.testing.assert_allclose(plot_properties['color'][-1],
[1., 0.33333333, 0.83333333, 1.],
rtol=1e-06)
plot_beta = prot_coor.plot_pseudo_3D('beta')
plot_properties = plot_beta.properties()
assert plot_properties['color'].shape == (191, 4)
assert len(plot_properties['segments']) == 191
np.testing.assert_allclose(plot_properties['color'][0],
[0., 0.666667, 0.576288, 1.],
rtol=1e-06)
np.testing.assert_allclose(plot_properties['color'][-1],
[0.333333, 0.650895, 1., 1.],
rtol=1e-05)
def test_set_protonate_amber(tmp_path):
gmx.show_log()
##########################################
# ## Create the topologie at PH 4.0 ###
##########################################
res_prot_dict = {
'GLH': {
'res_num': [9, 24, 31, 57]
},
'ASH': {
'res_num': [3, 70]
},
'HIP': {
'res_num': [28, 35]
},
'HID': {
'res_num': [175]
},
'HIE': {
'res_num': [214]
}
}
prot = gmx.GmxSys(name='1RXZ_ph4', coor_file=PDB_1RXZ)
prot.prepare_top(out_folder=os.path.join(tmp_path, 'top_1RXZ_ph4'),
ph=7.0,
res_prot_dict=res_prot_dict,
ff="amber99sb-ildn")
top_coor = pdb_manip.Coor(prot.coor_file)
assert top_coor.num == 4081
top_1RXZ = gmx.TopSys(prot.top_file)
assert top_1RXZ.charge() == -4
def smile_to_pdb(smile, pdb_out, mol_name, method_3d='rdkit', iter_num=5000):
"""
"""
if method_3d == 'openbabel':
from openbabel import pybel
conf = pybel.readstring("smi", smile)
# Get charge
charge = conf.charge
conf.make3D(forcefield='mmff94', steps=iter_num)
conf.write(format='pdb', filename=pdb_out, overwrite=True)
elif method_3d == 'rdkit':
from rdkit.Chem import AllChem as Chem
conf = Chem.MolFromSmiles(smile)
conf = Chem.AddHs(conf)
# Get charge
charge = Chem.GetFormalCharge(conf)
Chem.EmbedMolecule(conf)
Chem.MMFFOptimizeMolecule(conf,
mmffVariant='MMFF94',
maxIters=iter_num)
Chem.MolToPDBFile(conf, filename=pdb_out)
# Change resname of pdb file to `self.mol_name`
coor = pdb_manip.Coor(pdb_out)
index_list = coor.get_index_selection(selec_dict={'res_name': ['UNL']})
coor.change_index_pdb_field(index_list, change_dict={'res_name': mol_name})
coor.write_pdb(pdb_out, check_file_out=False)
return (charge)
def test_protonate_ph4_7_amber(tmp_path):
gmx.show_log()
##########################################
# ## Create the topologie at PH 4.0 ###
##########################################
prot = gmx.GmxSys(name='1RXZ_ph4', coor_file=PDB_1RXZ)
prot.prepare_top(out_folder=os.path.join(tmp_path, 'top_1RXZ_ph4'),
ph=4.0,
ff="amber99sb-ildn")
top_coor = pdb_manip.Coor(prot.coor_file)
top_1RXZ = gmx.TopSys(prot.top_file)
if (version.parse(pdb2pqr.__version__) < version.parse("3.5")):
assert top_coor.num == 4107
assert top_1RXZ.charge() == 22
else:
assert top_coor.num == 4106
assert top_1RXZ.charge() == 21
##########################################
# ## Create the topologie at PH 7.0 ###
##########################################
prot = gmx.GmxSys(name='1RXZ_ph7', coor_file=PDB_1RXZ)
prot.prepare_top(out_folder=os.path.join(tmp_path, 'top_1RXZ_ph7'),
ph=7.0,
ff="amber99sb-ildn")
top_coor = pdb_manip.Coor(prot.coor_file)
assert top_coor.num == 4073
top_1RXZ = gmx.TopSys(prot.top_file)
assert top_1RXZ.charge() == -12
##########################################
# ## Create the topologie at PH 10.0 ###
##########################################
# Remark: Amber allow lysine unprotonated
prot = gmx.GmxSys(name='1RXZ_ph10', coor_file=PDB_1RXZ)
prot.prepare_top(out_folder=os.path.join(tmp_path, 'top_1RXZ_ph10'),
ph=10.0,
ff="amber99sb-ildn")
top_coor = pdb_manip.Coor(prot.coor_file)
assert top_coor.num == 4071
top_1RXZ = gmx.TopSys(prot.top_file)
assert top_1RXZ.charge() == -14
def test_insert_peptide_vsite(tmp_path):
# Gromacs verions >= 2021 support cyclic peptides
gmx.show_log()
cyclic_pep = gmx.GmxSys(name='5vav', coor_file=PDB_5VAV)
top_coor = pdb_manip.Multi_Coor(cyclic_pep.coor_file)
assert top_coor.coor_list[0].num == 209
cyclic_pep.cyclic_peptide_top(
out_folder=os.path.join(tmp_path, 'cyclic/top'))
top_coor = pdb_manip.Coor(cyclic_pep.coor_file)
assert top_coor.num == 209
cyclic_top = gmx.TopSys(cyclic_pep.top_file)
assert cyclic_top.prot_res_num() == 14
cyclic_top.display()
cyclic_pep.em(out_folder=os.path.join(tmp_path, 'cyclic/em/'),
nsteps=10,
create_box_flag=True)
cyclic_amber_pep = gmx.GmxSys(name='5vav_amber', coor_file=PDB_5VAV)
top_coor = pdb_manip.Coor(cyclic_pep.coor_file)
assert top_coor.num == 209
cyclic_amber_pep.cyclic_peptide_top(out_folder=os.path.join(
tmp_path, 'cyclic/top'),
ff='amber99sb-ildn')
top_coor = pdb_manip.Coor(cyclic_pep.coor_file)
assert top_coor.num == 209
cyclic_amber_top = gmx.TopSys(cyclic_amber_pep.top_file)
print(cyclic_amber_top.charge())
cyclic_amber_pep.em(out_folder=os.path.join(tmp_path, 'cyclic/em/'),
nsteps=10,
create_box_flag=True)
def test_smina_rigid(tmp_path, capsys):
# Convert to str to avoid problem with python 3.5
TEST_OUT = str(tmp_path)
# Redirect pdb_manip logs
pdb_manip.show_log()
# Extract center and max_sizer:
lig_coor = pdb_manip.Coor(os.path.join(TEST_PATH, 'lig.pdbqt'))
center_lig = lig_coor.center_of_mass()
max_size = lig_coor.get_max_size()
print("Center coordinates is {:.1f} {:.1f} {:.1f}, maximum dimension"
" is {:.1f} Å".format(*center_lig, max_size))
captured = capsys.readouterr()
assert bool(re.match('Succeed to read file .+/input/lig.pdbqt , 50 '
'atoms found\nDo a rotation of 99.71°\nCenter '
'coordinates is 13.1 22.5 5.5, maximum dimension is '
'18.0 Å\n',
captured.out))
# Create Docking object
test_dock = docking.Docking(
name='test_smina',
rec_pdbqt=os.path.join(TEST_PATH, 'rec.pdbqt'),
lig_pdbqt=os.path.join(TEST_PATH, 'lig.pdbqt'))
out_dock = os.path.join(TEST_OUT, '{}_dock.pdb'.format('test_smina'))
test_dock.run_docking(out_dock,
num_modes=10,
energy_range=1,
exhaustiveness=2,
dock_bin='smina',
center=center_lig,
grid_npts=[max_size + 5] * 3,
seed=1)
captured = capsys.readouterr()
capture_line = captured.out.split('\n')
assert bool(re.match(
("smina --ligand .+lig.pdbqt --receptor .+rec.pdbqt --log "
".+test_smina_dock_log.txt --num_modes 10 --exhaustiveness 2"
" --energy_range 1 --out .+test_smina_dock.pdb "
"--size_x 23.00 --size_y 23.00 --size_z 23.00"
" --center_x 13.08 --center_y 22.52 --center_z 5.54"
" --seed 1"),
capture_line[0]))
rmsd_list = test_dock.compute_dock_rmsd(test_dock.lig_pdbqt)
assert len(rmsd_list) >= 1
assert rmsd_list[0] < 15
assert len(test_dock.affinity) >= 1
assert test_dock.affinity[1]['affinity'] < -10
def make_amber_top_mol(pdb_in,
res_name,
charge,
charge_model="bcc",
atom_type="gaff",
remove_h=True):
full_coor = pdb_manip.Coor(pdb_in)
# Select coor:
mol_coor = full_coor.select_part_dict(selec_dict={'res_name': [res_name]})
# Remove hydrogens:
if remove_h:
to_del_list = []
for atom_num, atom in mol_coor.atom_dict.items():
if atom['name'][0] == 'H':
to_del_list.append(atom_num)
mol_coor.del_atom_index(to_del_list)
mol_coor.write_pdb(res_name + '.pdb')
# Add hydrogens:
add_hydrogen(res_name + '.pdb', res_name + '_h.pdb')
# Get only one molecule
mol_h_coor = pdb_manip.Coor(res_name + '_h.pdb')
res_list = mol_h_coor.get_attribute_selection(attribute='uniq_resid')
mol_uniq_coor = mol_h_coor.select_part_dict(
selec_dict={'uniq_resid': [res_list[0]]})
# Save coordinates:
mol_uniq_coor.write_pdb(res_name + '_h_unique.pdb')
# Compute topologie with acpype:
gmxsys = acpype(res_name + '_h_unique.pdb',
res_name,
net_charge=charge,
charge_model="bcc",
atom_type="gaff")
return ({
'GmxSys': gmxsys,
'coor': os_command.full_path_and_check(res_name + '_h.pdb'),
'num': len(res_list)
})
def test_solv_oct(tmp_path):
mol_free = FreeEner('DEN', f'{tmp_path}/indene_oct_solv')
mol_free.octanol_box_from_SMILE('C1C=Cc2ccccc12')
start_coor = pdb_manip.Coor(mol_free.gmxsys.coor_file)
assert start_coor.num == 1502
mol_free.gmxsys.nt = 1
mol_free.equilibrate_solvent_box(em_steps=100,
dt=0.002,
prod_time=0.02,
short_steps=500)
def test_protonate_ph4_7_12_charmm(tmp_path):
gmx.show_log()
##########################################
# ## Create the topologie at PH 4.0 ###
##########################################
prot = gmx.GmxSys(name='1RXZ_ph4', coor_file=PDB_1RXZ)
prot.prepare_top(out_folder=os.path.join(tmp_path, 'top_1RXZ_ph4'), ph=4.0)
top_coor = pdb_manip.Coor(prot.coor_file)
assert top_coor.num == 4108
top_1RXZ = gmx.TopSys(prot.top_file)
assert top_1RXZ.charge() == 23
##########################################
# ## Create the topologie at PH 7.0 ###
##########################################
prot = gmx.GmxSys(name='1RXZ_ph7', coor_file=PDB_1RXZ)
prot.prepare_top(out_folder=os.path.join(tmp_path, 'top_1RXZ_ph7'), ph=7.0)
top_coor = pdb_manip.Coor(prot.coor_file)
assert top_coor.num == 4073
top_1RXZ = gmx.TopSys(prot.top_file)
assert top_1RXZ.charge() == -12
##########################################
# ## Create the topologie at PH 10.0 ###
##########################################
# Remark: Charmm doesn't allow lysine unprotonated
prot = gmx.GmxSys(name='1RXZ_ph10', coor_file=PDB_1RXZ)
prot.prepare_top(out_folder=os.path.join(tmp_path, 'top_1RXZ_ph10'),
ph=10.0)
top_coor = pdb_manip.Coor(prot.coor_file)
assert top_coor.num == 4073
top_1RXZ = gmx.TopSys(prot.top_file)
assert top_1RXZ.charge() == -12
def test_pdb2pqr_dna(tmp_path):
"""
Check that pdb2pqr produce something with dna
"""
ff = "CHARMM"
pdb_manip.show_log()
##########################################
# ## Compute protonation at PH 4.0 ###
##########################################
out_file = os.path.join(tmp_path, '1D30_charmm_ph4.pqr')
pdb2pqr.compute_pdb2pqr(os.path.join(PDB_1D30), out_file, ff=ff, ph=4.0)
prot_coor = pdb_manip.Coor(out_file)
assert prot_coor.num == 486
def test_free_bind(tmp_path):
dna_free = FreeEner('DAP', f'{tmp_path}/1D30_solv')
dna_free.prepare_complex_pdb(PDB_1D30,
'NC(=N)c1ccc(cc1)c2[nH]c3cc(ccc3c2)C(N)=N')
start_coor = pdb_manip.Coor(dna_free.gmxsys.coor_file)
assert start_coor.num == 20973
dna_free.equilibrate_complex(em_steps=100,
HA_time=0.001,
CA_time=0.002,
CA_LOW_time=0.02,
dt=0.002,
dt_HA=0.001,
temp=300,
receptor_grp='DNA',
short_steps=500)
dna_free.compute_add_intermol_from_traj(ref_coor=None, rec_group='DNA')
dg_rest_water = dna_free.get_water_restr()
print(dg_rest_water)
assert ((5.5 < dg_rest_water) and (dg_rest_water < 9.5))
dna_free.plot_intermol_restr()
delta_restr = 0.5
restr_list = np.arange(0, 1 + delta_restr, delta_restr)
delta_coul = 0.5
coul_list = np.arange(0, 1 + delta_coul, delta_coul)
vdw_coul = 0.5
vdw_list = np.arange(0, 1 + vdw_coul, vdw_coul)
dna_free.run(lambda_restr_list=restr_list,
lambda_coul_list=coul_list,
lambda_vdw_list=vdw_list,
em_steps=50,
nvt_time=0.05,
npt_time=0.05,
prod_time=0.25,
temp_groups='System')
dna_free.extend_lambda_prod(prod_time=0.5)
dg_bind, dg_std_bind = dna_free.get_free_ener()
print(dg_bind, dg_std_bind)
assert ((0 < dg_bind) and (dg_bind < 200))
# Need to think about using alchemlyb as a dependance or not
dna_free.plot_convergence(dt=0.25, graph_out=f'{tmp_path}/alchem.png')
dna_free.compute_convergence_gbar(dt=0.25)
dna_free.plot_convergence_graph(graph_out=f'{tmp_path}/bar.png')
def add_hydrogen_rdkit(pdb_in, smile, pdb_out):
"""Add hydrogen to a pdb file using the ``rdkit`` library:
:param pdb_in: pdb input
:type pdb_in: str
:param pdb_out: pdb output
:type pdb_out: str
:Example:
>>> from pdb_manip_py import pdb_manip
>>> pdb_manip.show_log()
>>> TEST_OUT = getfixture('tmpdir')
>>> # print(TEST_OUT)
>>> add_hydrogen_rdkit(pdb_in=os.path.join(TEST_PATH,'four_phenol.pdb'),\
smile="C1=CC=C(C=C1)O",\
pdb_out=os.path.join(TEST_OUT,'four_phenol_h.pdb')) #doctest: +ELLIPSIS
Succeed to read file ...four_phenol.pdb , 28 atoms found
Succeed to save file ...four_phenol_0.pdb
Succeed to read file ...four_phenol_0.pdb , 7 atoms found
Succeed to read file ...four_phenol_0_h.pdb , 13 atoms found
Succeed to save file ...four_phenol_0_h.pdb
Succeed to read file ...four_phenol_0_h.pdb , 13 atoms found
Succeed to save file ...four_phenol_0_h.pdb
Succeed to save file ...four_phenol_1.pdb
Succeed to read file ...four_phenol_1.pdb , 7 atoms found
Succeed to read file ...four_phenol_1_h.pdb , 13 atoms found
Succeed to save file ...four_phenol_1_h.pdb
Succeed to read file ...four_phenol_1_h.pdb , 13 atoms found
Succeed to save file ...four_phenol_1_h.pdb
Succeed to save file ...four_phenol_2.pdb
Succeed to read file ...four_phenol_2.pdb , 7 atoms found
Succeed to read file ...four_phenol_2_h.pdb , 13 atoms found
Succeed to save file ...four_phenol_2_h.pdb
Succeed to read file ...four_phenol_2_h.pdb , 13 atoms found
Succeed to save file ...four_phenol_2_h.pdb
Succeed to save file ...four_phenol_3.pdb
Succeed to read file ...four_phenol_3.pdb , 7 atoms found
Succeed to read file ...four_phenol_3_h.pdb , 13 atoms found
Succeed to save file ...four_phenol_3_h.pdb
Succeed to read file ...four_phenol_3_h.pdb , 13 atoms found
Succeed to save file ...four_phenol_3_h.pdb
Succeed to save concat file: ...four_phenol_h.pdb
0
>>> phenol_coor = pdb_manip.Coor(os.path.join(TEST_OUT,\
'four_phenol_h.pdb')) #doctest: +ELLIPSIS
Succeed to read file ...four_phenol_h.pdb , 52 atoms found
"""
full_coor = pdb_manip.Coor(pdb_in)
# Change first residue to 1, as it is the res from rdkit output
res_list = full_coor.get_attribute_selection(attribute='res_num')
pdb_list = []
pdb_del_list = []
for i, res in enumerate(res_list):
# Extract residue
one_res = full_coor.select_part_dict(selec_dict={'res_num': [res]})
out_pdb = '{}_{}.pdb'.format(pdb_in[:-4], i)
one_res.write_pdb(out_pdb)
pdb_del_list.append(out_pdb)
# Add hydrogens
out_h_pdb = '{}_{}_h.pdb'.format(pdb_in[:-4], i)
charge = add_hydrogen_rdkit_one_mol(out_pdb, smile, out_h_pdb)
pdb_list.append(out_h_pdb)
pdb_del_list.append(out_h_pdb)
# Update residue number:
one_res_h = pdb_manip.Coor(out_h_pdb)
one_res_h.change_pdb_field(change_dict={"res_num": i + 1})
one_res_h.write_pdb(out_h_pdb, check_file_out=False)
pdb_manip.Coor.concat_pdb(*pdb_list, pdb_out=pdb_out)
# Delete intermediate files
for pdb in pdb_del_list:
os_command.delete_file(pdb)
return charge
def test_autodock_cpu(tmp_path, capsys):
# Convert to str to avoid problem with python 3.5
TEST_OUT = str(tmp_path)
# Redirect pdb_manip logs
pdb_manip.show_log()
# Extract center and max_sizer:
lig_coor = pdb_manip.Coor(os.path.join(TEST_PATH, 'lig.pdbqt'))
center_lig = lig_coor.center_of_mass()
max_size = lig_coor.get_max_size()
print("Center coordinates is {:.1f} {:.1f} {:.1f}, maximum dimension"
" is {:.1f} Å".format(*center_lig, max_size))
captured = capsys.readouterr()
assert bool(
re.match(
"File name doesn't finish with .pdb read it as .pdb"
" anyway\n"
'Succeed to read file .+/input/lig.pdbqt , 50 '
'atoms found\nDo a rotation of 99.71°\nCenter '
'coordinates is 13.1 22.5 5.5, maximum dimension is '
'18.0 Å\n', captured.out))
# Create Docking object
test_dock = docking.Docking(name='test_autodock',
rec_pdbqt=os.path.join(TEST_PATH, 'rec.pdbqt'),
lig_pdbqt=os.path.join(TEST_PATH, 'lig.pdbqt'))
# Prepare Grid
spacing = 0.375
test_dock.prepare_grid(out_folder=TEST_OUT,
spacing=spacing,
center=center_lig,
grid_npts=[int(max_size / spacing)] * 3)
captured = capsys.readouterr()
assert bool(
re.match(
("python2.+ .+prepare_gpf4.py -r rec.pdbqt -l lig.pdbqt -o "
"test_autodock.gpf -p npts=48,48,48 -p "
"gridcenter=13.08,22.52,5.54\nautogrid4 -p test_autodock.gpf -l "
"test_autodock.gpf_log"), captured.out))
test_dock.run_autodock_cpu(out_folder=TEST_OUT, nrun=2)
rmsd_list = test_dock.compute_dock_rmsd(test_dock.lig_pdbqt)
assert len(rmsd_list) == 2
assert rmsd_list[0] < 15
assert len(test_dock.affinity) == 2
assert test_dock.affinity[1]['affinity'] < -10
assert bool(test_dock.lig_pdbqt.endswith("lig.pdbqt"))
assert bool(test_dock.rec_pdbqt.endswith("rec.pdbqt"))
assert bool(test_dock.dock_pdb.endswith("test_autodock_vmd.pdb"))
assert bool(test_dock.dock_log.endswith("test_autodock.dlg"))
assert bool(test_dock.gpf.endswith("test_autodock.gpf"))
# Read test_dock.dock_pdb
coor_dock = pdb_manip.Multi_Coor(test_dock.dock_pdb)
assert len(coor_dock.coor_list) == 2
assert len(coor_dock.coor_list[0].atom_dict) == 50
def test_pdb2pqr_ph4_7_12_charmm(tmp_path):
"""
Test pdb2pqr at ph 4, 7 and 12 with the charmm ff.
"""
ff = "CHARMM"
pdb_manip.show_log()
##########################################
# ## Compute protonation at PH 4.0 ###
##########################################
out_file = os.path.join(tmp_path, '4N1M_charmm_ph4.pqr')
pdb2pqr.compute_pdb2pqr(os.path.join(PDB_4N1M), out_file, ff=ff, ph=4.0)
prot_coor = pdb_manip.Coor(out_file)
assert prot_coor.num == 2559
HSD_index = prot_coor.get_index_selection({
'res_name': ['HSD'],
'name': ['CA']
})
HSE_index = prot_coor.get_index_selection({
'res_name': ['HSE'],
'name': ['CA']
})
HSP_index = prot_coor.get_index_selection({
'res_name': ['HSP'],
'name': ['CA']
})
assert len(HSD_index) == 0
assert len(HSE_index) == 0
assert len(HSP_index) == 5
##########################################
# ## Compute protonation at PH 7.0 ###
##########################################
out_file = os.path.join(tmp_path, '4N1M_charmm_ph7.pqr')
pdb2pqr.compute_pdb2pqr(os.path.join(PDB_4N1M), out_file, ff=ff, ph=7.0)
prot_coor = pdb_manip.Coor(out_file)
assert prot_coor.num == 2549
HSD_index = prot_coor.get_index_selection({
'res_name': ['HSD'],
'name': ['CA']
})
HSE_index = prot_coor.get_index_selection({
'res_name': ['HSE'],
'name': ['CA']
})
HSP_index = prot_coor.get_index_selection({
'res_name': ['HSP'],
'name': ['CA']
})
assert len(HSD_index) == 4
assert len(HSE_index) == 0
assert len(HSP_index) == 1
##########################################
# ## Compute protonation at PH 10.0 ###
out_file = os.path.join(tmp_path, '4N1M_charmm_ph10.pqr')
pdb2pqr.compute_pdb2pqr(os.path.join(PDB_4N1M), out_file, ff=ff, ph=10.0)
prot_coor = pdb_manip.Coor(out_file)
assert prot_coor.num == 2548
HSD_index = prot_coor.get_index_selection({
'res_name': ['HSD'],
'name': ['CA']
})
HSE_index = prot_coor.get_index_selection({
'res_name': ['HSE'],
'name': ['CA']
})
HSP_index = prot_coor.get_index_selection({
'res_name': ['HSP'],
'name': ['CA']
})
assert len(HSD_index) == 5
assert len(HSE_index) == 0
assert len(HSP_index) == 0
def test_prepare_ligand_recetor(tmp_path, capsys):
# Convert to str to avoid problem with python 3.5
TEST_OUT = str(tmp_path)
# Redirect pdb_manip logs
pdb_manip.show_log()
# Read 1hsg.pdb, extract lig.pdb and rec.pdb
coor_1hsg = pdb_manip.Coor(os.path.join(TEST_PATH, '1hsg.pdb'))
captured = capsys.readouterr()
assert bool(
re.match("Succeed to read file .+input/1hsg.pdb , 1686 atoms found\n",
captured.out))
# Extratc Protein:
# Keep only amino acid
rec_coor = coor_1hsg.select_part_dict(
selec_dict={'res_name': pdb_manip.PROTEIN_AA})
out_rec = os.path.join(TEST_OUT, 'rec.pdb')
rec_coor.write_pdb(out_rec)
captured = capsys.readouterr()
assert bool(re.match("Succeed to save file .+rec.pdb\n",
captured.out))
# Extract ligand:
lig_coor = coor_1hsg.select_part_dict(
selec_dict={'res_name': 'MK1'})
out_lig = os.path.join(TEST_OUT, 'lig.pdb')
lig_coor.write_pdb(out_lig)
captured = capsys.readouterr()
assert bool(re.match("Succeed to save file .+lig.pdb\n",
captured.out))
# Extract ligand center of mass and maximum dimension:
center_lig = lig_coor.center_of_mass()
max_size = lig_coor.get_max_size()
print("Center coordinates is {:.1f} {:.1f} {:.1f}, maximum dimension"
" is {:.1f} Å".format(*center_lig, max_size))
captured = capsys.readouterr()
assert bool(re.match('Do a rotation of 99.65°\nCenter coordinates is 13.1'
' 22.5 5.6, maximum dimension is 16.0 Å\n',
captured.out))
# Create Docking object
test_dock = docking.Docking('test',
rec_pdb=out_rec,
lig_pdb=out_lig)
# Prepare receptor
test_dock.prepare_receptor()
captured = capsys.readouterr()
assert bool(re.match(
("python2.+ .+/prepare_receptor4.py -r .+/rec.pdb"
" -A checkhydrogens -o .+/rec.pdbqt\n"),
captured.out))
# Check that receptor is fine
coor_rec = pdb_manip.Coor(test_dock.rec_pdbqt)
print('Protein atom number : {}'.format(coor_rec.select_part_dict(
{'res_name': pdb_manip.PROTEIN_AA}).num))
captured = capsys.readouterr()
assert bool(re.match(
"Succeed to read file .+rec.pdbqt , 1844 atoms found\n"
"Protein atom number : 1844\n",
captured.out))
# Prepare Ligand
test_dock.prepare_ligand(rigid=True)
captured = capsys.readouterr()
assert bool(re.match("python.+ .+prepare_ligand4.py -l lig.pdb -B "
"none -A hydrogens -o lig.pdbqt -Z\n",
captured.out))
# Check that ligand pdbqt is fine
coor_lig = pdb_manip.Coor(test_dock.lig_pdbqt)
print('Protein atom number : {}'.format(coor_lig.select_part_dict(
{'res_name': pdb_manip.PROTEIN_AA}).num))
captured = capsys.readouterr()
assert bool(re.match(
"Succeed to read file .+lig.pdbqt , 50 atoms found\n"
"Protein atom number : 0\n",
captured.out))
def test_autodock_2_rigid(tmp_path, capsys):
# Convert to str to avoid problem with python 3.5
TEST_OUT = str(tmp_path)
# Redirect pdb_manip logs
pdb_manip.show_log()
# Extract center and max_sizer:
lig_coor = pdb_manip.Coor(os.path.join(TEST_PATH, 'lig.pdbqt'))
center_lig = lig_coor.center_of_mass()
max_size = lig_coor.get_max_size()
print("Center coordinates is {:.1f} {:.1f} {:.1f}, maximum dimension"
" is {:.1f} Å".format(*center_lig, max_size))
captured = capsys.readouterr()
assert bool(re.match('Succeed to read file .+/input/lig.pdbqt , 50 '
'atoms found\nDo a rotation of 99.71°\nCenter '
'coordinates is 13.1 22.5 5.5, maximum dimension is '
'18.0 Å\n',
captured.out))
# Create Docking object
test_dock = docking.Docking(
name='test_autodock_2',
rec_pdbqt=os.path.join(TEST_PATH, 'rec.pdbqt'),
lig_pdbqt=os.path.join(TEST_PATH, 'lig.pdbqt'))
out_dock = os.path.join(TEST_OUT, '{}_dock.pdb'.format('test_autodock_2'))
test_dock.run_autodock_docking(out_dock,
num_modes=2,
center=center_lig,
grid_size=[max_size + 5] * 3)
captured = capsys.readouterr()
capture_line = captured.out.split('\n')
assert bool(re.match(
("python2.+ .+prepare_gpf4.py -r rec.pdbqt -l lig.pdbqt -o "
"test_autodock_2_dock.gpf -p npts=62,62,62 -p "
"gridcenter=13.08,22.52,5.54"),
capture_line[0]))
assert bool(re.match(
("autogrid4 -p test_autodock_2_dock.gpf "
"-l test_autodock_2_dock.gpf_log"),
capture_line[1]))
rmsd_list = test_dock.compute_dock_rmsd(test_dock.lig_pdbqt)
assert len(rmsd_list) == 2
assert rmsd_list[0] < 15
assert len(test_dock.affinity) == 2
assert test_dock.affinity[1]['affinity'] < -10
captured = capsys.readouterr()
test_dock.display()
captured = capsys.readouterr()
assert bool(re.match(
("name : test_autodock_2\n"
"lig_pdbqt : .+lig.pdbqt\n"
"rec_pdbqt : .+rec.pdbqt\n"
"dock_pdb : .+test_autodock_2_dock_vmd.pdb\n"
"dock_log : .+test_autodock_2_dock.dlg\n"
"gpf : .+test_autodock_2_dock.gpf\n"
"affinity : {1: .+affinity': -.+}}\n"
),
captured.out))
def test_autodock_rigid(tmp_path, capsys):
# Convert to str to avoid problem with python 3.5
TEST_OUT = str(tmp_path)
# Redirect pdb_manip logs
pdb_manip.show_log()
# Extract center and max_sizer:
lig_coor = pdb_manip.Coor(os.path.join(TEST_PATH, 'lig.pdbqt'))
center_lig = lig_coor.center_of_mass()
max_size = lig_coor.get_max_size()
print("Center coordinates is {:.1f} {:.1f} {:.1f}, maximum dimension"
" is {:.1f} Å".format(*center_lig, max_size))
captured = capsys.readouterr()
assert bool(re.match('Succeed to read file .+/input/lig.pdbqt , 50 '
'atoms found\nDo a rotation of 99.71°\nCenter '
'coordinates is 13.1 22.5 5.5, maximum dimension is '
'18.0 Å\n',
captured.out))
# Create Docking object
test_dock = docking.Docking(
name='test_autodock',
rec_pdbqt=os.path.join(TEST_PATH, 'rec.pdbqt'),
lig_pdbqt=os.path.join(TEST_PATH, 'lig.pdbqt'))
# Prepare Grid
spacing = 0.375
test_dock.prepare_grid(out_folder=TEST_OUT, spacing=spacing,
center=center_lig,
grid_npts=[int(max_size / spacing)] * 3)
captured = capsys.readouterr()
assert bool(re.match(
("python2.+ .+prepare_gpf4.py -r rec.pdbqt -l lig.pdbqt -o "
"test_autodock.gpf -p npts=48,48,48 -p "
"gridcenter=13.08,22.52,5.54\nautogrid4 -p test_autodock.gpf -l "
"test_autodock.gpf_log"),
captured.out))
test_dock.run_autodock(out_folder=TEST_OUT, nrun=1)
rmsd_list = test_dock.compute_dock_rmsd(test_dock.lig_pdbqt)
assert len(rmsd_list) >= 1
assert rmsd_list[0] < 15
captured = capsys.readouterr()
test_dock.display()
captured = capsys.readouterr()
assert bool(re.match(
("name : test_autodock\n"
"lig_pdbqt : .+lig.pdbqt\n"
"rec_pdbqt : .+rec.pdbqt\n"
"dock_pdb : .+test_autodock_vmd.pdb\n"
"dock_log : .+test_autodock.dlg\n"
"gpf : .+test_autodock.gpf\n"
"affinity : {1: .+affinity': -.+}}\n"
),
captured.out))
def add_hydrogen_rdkit_one_mol(pdb_in, smile, pdb_out):
"""Add hydrogen to a pdb file using the ``rdkit`` library:
:param pdb_in: pdb input
:type pdb_in: str
:param pdb_out: pdb output
:type pdb_out: str
:Example:
>>> from pdb_manip_py import pdb_manip
>>> pdb_manip.show_log()
>>> TEST_OUT = getfixture('tmpdir')
>>> # print(TEST_OUT)
>>> add_hydrogen_rdkit_one_mol(pdb_in=os.path.join(TEST_PATH,'phenol.pdb')\
,smile="C1=CC=C(C=C1)O",\
pdb_out=os.path.join(TEST_OUT,'phenol_h.pdb')) #doctest: +ELLIPSIS
Succeed to read file ...phenol_h.pdb , 13 atoms found
Succeed to save file ...phenol_h.pdb
0
>>> phenol_coor = pdb_manip.Coor(os.path.join(TEST_OUT,'phenol_h.pdb'))\
#doctest: +ELLIPSIS
Succeed to read file .../phenol_h.pdb , 13 atoms found
.. warning:
"""
try:
from rdkit.Chem import AllChem as Chem
# from rdkit.Chem import rdMolAlign as align
except ImportError:
logger.error('Could not load rdkit \nInstall it using conda:\n'
'conda install -c conda-forge rdkit')
sys.exit(1)
lig_pdb = Chem.MolFromPDBFile(pdb_in, removeHs=True)
lig_smile = Chem.MolFromSmiles(smile)
# Need to count the number of molecule
pdb_atom_num = lig_pdb.GetNumAtoms()
smile_atom_num = lig_smile.GetNumAtoms()
# If more than one molecule, add them
# in the smile string
if pdb_atom_num != smile_atom_num:
mol_num = pdb_atom_num / smile_atom_num
smile_list = [smile] * int(mol_num)
lig_smile = Chem.MolFromSmiles('.'.join(smile_list))
# Assign bond order on pdb using smile informations
newMol = Chem.AssignBondOrdersFromTemplate(lig_smile, lig_pdb)
# Add hydrogens to lig_smile, using lig_pdb as coordinates constraints
# This way is better than adding h to lig_pdb
# because acpype experience some issue
lig_smile_h = Chem.AddHs(lig_smile)
Chem.ConstrainedEmbed(lig_smile_h, newMol)
Chem.MolToPDBFile(lig_smile_h, pdb_out)
# OLD WAY :
# Add hydrogens
# newMol_h = Chem.AddHs(newMol)
# # Need to define how to match atoms form pdb to smile
# match_atom = newMol_h.GetSubstructMatch(lig_smile)
# cmap = {match_atom[i]: lig_pdb.GetConformer().
# GetAtomPosition(match_atom[i]) for i in range(len(match_atom))}
# # Hydrogens coordinates need to be computed
# # While keeping heavy atoms coordinates
# Chem.EmbedMolecule(newMol_h, coordMap=cmap)
# # Align new coordinates to old one
# align.AlignMol(newMol_h, newMol,
# atomMap=[[i, i] for i in range(len(match_atom))])
# Save coordinates
# Chem.MolToPDBFile(newMol_h, pdb_out)
# Change UNL residue name to original one
coor_start = pdb_manip.Coor(pdb_in)
res_name_list_start = coor_start.get_attribute_selection(
attribute='res_name')
if len(res_name_list_start) > 1:
res_name_list_start.remove('UNL')
coor = pdb_manip.Coor(pdb_out)
index_list = coor.get_index_selection(selec_dict={'res_name': ['UNL']})
coor.change_index_pdb_field(
index_list, change_dict={'res_name': res_name_list_start[0]})
coor.write_pdb(pdb_out, check_file_out=False)
# Return charge
return Chem.GetFormalCharge(lig_smile)
