def solvate(struct='top/protein.pdb', top='top/system.top',
distance=0.9, boxtype='dodecahedron',
concentration=0, cation='NA', anion='CL',
water='spc', solvent_name='SOL', with_membrane=False,
ndx = 'main.ndx', mainselection = '"Protein"',
dirname='solvate',
**kwargs):
"""Put protein into box, add water, add counter-ions.
Currently this really only supports solutes in water. If you need
to embedd a protein in a membrane then you will require more
sophisticated approaches.
However, you *can* supply a protein already inserted in a
bilayer. In this case you will probably want to set *distance* =
``None`` and also enable *with_membrane* = ``True`` (using extra
big vdw radii for typical lipids).
.. Note:: The defaults are suitable for solvating a globular
protein in a fairly tight (increase *distance*!) dodecahedral
box.
:Arguments:
*struct* : filename
pdb or gro input structure
*top* : filename
Gromacs topology
*distance* : float
When solvating with water, make the box big enough so that
at least *distance* nm water are between the solute *struct*
and the box boundary.
Set *boxtype* to ``None`` in order to use a box size in the input
file (gro or pdb).
*boxtype* or *bt*: string
Any of the box types supported by :class:`~gromacs.tools.Editconf`
(triclinic, cubic, dodecahedron, octahedron). Set the box dimensions
either with *distance* or the *box* and *angle* keywords.
If set to ``None`` it will ignore *distance* and use the box
inside the *struct* file.
*bt* overrides the value of *boxtype*.
*box*
List of three box lengths [A,B,C] that are used by :class:`~gromacs.tools.Editconf`
in combination with *boxtype* (``bt`` in :program:`editconf`) and *angles*.
Setting *box* overrides *distance*.
*angles*
List of three angles (only necessary for triclinic boxes).
*concentration* : float
Concentration of the free ions in mol/l. Note that counter
ions are added in excess of this concentration.
*cation* and *anion* : string
Molecule names of the ions. This depends on the chosen force field.
*water* : string
Name of the water model; one of "spc", "spce", "tip3p",
"tip4p". This should be appropriate for the chosen force
field. If an alternative solvent is required, simply supply the path to a box
with solvent molecules (used by :func:`~gromacs.genbox`'s *cs* argument)
and also supply the molecule name via *solvent_name*.
*solvent_name*
Name of the molecules that make up the solvent (as set in the itp/top).
Typically needs to be changed when using non-standard/non-water solvents.
["SOL"]
*with_membrane* : bool
``True``: use special ``vdwradii.dat`` with 0.1 nm-increased radii on
lipids. Default is ``False``.
*ndx* : filename
How to name the index file that is produced by this function.
*mainselection* : string
A string that is fed to :class:`~gromacs.tools.Make_ndx` and
which should select the solute.
*dirname* : directory name
Name of the directory in which all files for the solvation stage are stored.
*includes*
List of additional directories to add to the mdp include path
*kwargs*
Additional arguments are passed on to
:class:`~gromacs.tools.Editconf` or are interpreted as parameters to be
changed in the mdp file.
"""
structure = realpath(struct)
topology = realpath(top)
# arguments for editconf that we honour
editconf_keywords = ["box", "bt", "angles", "c", "center", "aligncenter",
"align", "translate", "rotate", "princ"]
editconf_kwargs = dict((k,kwargs.pop(k,None)) for k in editconf_keywords)
editconf_boxtypes = ["triclinic", "cubic", "dodecahedron", "octahedron", None]
# needed for topology scrubbing
scrubber_kwargs = {'marker': kwargs.pop('marker',None)}
# sanity checks and argument dependencies
bt = editconf_kwargs.pop('bt')
boxtype = bt if bt else boxtype # bt takes precedence over boxtype
if not boxtype in editconf_boxtypes:
msg = "Unsupported boxtype {boxtype!r}: Only {boxtypes!r} are possible.".format(**vars())
logger.error(msg)
raise ValueError(msg)
if editconf_kwargs['box']:
distance = None # if box is set then user knows what she is doing...
# handle additional include directories (kwargs are also modified!)
mdp_kwargs = cbook.add_mdp_includes(topology, kwargs)
if water.lower() in ('spc', 'spce'):
water = 'spc216'
elif water.lower() == 'tip3p':
water = 'spc216'
logger.warning("TIP3P water model selected: using SPC equilibrated box "
"for initial solvation because it is a reasonable starting point "
"for any 3-point model. EQUILIBRATE THOROUGHLY!")
# By default, grompp should not choke on a few warnings because at
# this stage the user cannot do much about it (can be set to any
# value but is kept undocumented...)
grompp_maxwarn = kwargs.pop('maxwarn',10)
# clean topology (if user added the marker; the default marker is
# ; Gromacs auto-generated entries follow:
n_removed = cbook.remove_molecules_from_topology(topology, **scrubber_kwargs)
with in_dir(dirname):
logger.info("[{dirname!s}] Solvating with water {water!r}...".format(**vars()))
if boxtype is None:
hasBox = False
ext = os.path.splitext(structure)[1]
if ext == '.gro':
hasBox = True
elif ext == '.pdb':
with open(structure) as struct:
for line in struct:
if line.startswith('CRYST'):
hasBox = True
break
if not hasBox:
msg = "No box data in the input structure {structure!r} and boxtype is set to None".format(**vars())
logger.exception(msg)
raise MissingDataError(msg)
distance = boxtype = None # ensures that editconf just converts
editconf_kwargs.update({'f': structure, 'o': 'boxed.gro',
'bt': boxtype, 'd': distance})
gromacs.editconf(**editconf_kwargs)
if with_membrane:
vdwradii_dat = get_lipid_vdwradii() # need to clean up afterwards
logger.info("Using special vdW radii for lipids {0!r}".format(vdw_lipid_resnames))
try:
gromacs.genbox(p=topology, cp='boxed.gro', cs=water, o='solvated.gro')
except:
if with_membrane:
# remove so that it's not picked up accidentally
utilities.unlink_f(vdwradii_dat)
raise
logger.info("Solvated system with %s", water)
with open('none.mdp','w') as mdp:
mdp.write('; empty mdp file\ninclude = {include!s}\nrcoulomb = 1\nrvdw = 1\nrlist = 1\n'.format(**mdp_kwargs))
qtotgmx = cbook.grompp_qtot(f='none.mdp', o='topol.tpr', c='solvated.gro',
p=topology, stdout=False, maxwarn=grompp_maxwarn)
qtot = round(qtotgmx)
logger.info("[{dirname!s}] After solvation: total charge qtot = {qtotgmx!r} = {qtot!r}".format(**vars()))
if concentration != 0:
logger.info("[{dirname!s}] Adding ions for c = {concentration:f} M...".format(**vars()))
# target concentration of free ions c ==>
# N = N_water * c/c_water
# add ions for concentration to the counter ions (counter ions are less free)
#
# get number of waters (count OW ... works for SPC*, TIP*P water models)
rc,output,junk = gromacs.make_ndx(f='topol.tpr', o='ow.ndx',
input=('keep 0', 'del 0', 'a OW*', 'name 0 OW', '', 'q'),
stdout=False)
groups = cbook.parse_ndxlist(output)
gdict = {g['name']: g for g in groups} # overkill...
N_water = gdict['OW']['natoms'] # ... but dict lookup is nice
N_ions = int(N_water * concentration/CONC_WATER) # number of monovalents
else:
N_ions = 0
# neutralize (or try -neutral switch of genion???)
n_cation = n_anion = 0
if qtot > 0:
n_anion = int(abs(qtot))
elif qtot < 0:
n_cation = int(abs(qtot))
n_cation += N_ions
n_anion += N_ions
if n_cation != 0 or n_anion != 0:
# sanity check:
assert qtot + n_cation - n_anion < 1e-6
logger.info("[{dirname!s}] Adding n_cation = {n_cation:d} and n_anion = {n_anion:d} ions...".format(**vars()))
gromacs.genion(s='topol.tpr', o='ionized.gro', p=topology,
pname=cation, nname=anion, np=n_cation, nn=n_anion,
input=solvent_name)
else:
# fake ionized file ... makes it easier to continue without too much fuzz
try:
os.unlink('ionized.gro')
except OSError, err:
if err.errno != errno.ENOENT:
raise
os.symlink('solvated.gro', 'ionized.gro')
qtot = cbook.grompp_qtot(f='none.mdp', o='ionized.tpr', c='ionized.gro',
p=topology, stdout=False, maxwarn=grompp_maxwarn)
if abs(qtot) > 1e-4:
wmsg = "System has non-zero total charge qtot = {qtot:g} e.".format(**vars())
warnings.warn(wmsg, category=BadParameterWarning)
logger.warn(wmsg)
# make main index
try:
make_main_index('ionized.tpr', selection=mainselection, ndx=ndx)
except GromacsError, err:
# or should I rather fail here?
wmsg = "Failed to make main index file %r ... maybe set mainselection='...'.\n"\
"The error message was:\n%s\n" % (ndx, str(err))
logger.warn(wmsg)
warnings.warn(wmsg, category=GromacsFailureWarning)
def solvate(struct='top/protein.pdb',
top='top/system.top',
distance=0.9,
boxtype='dodecahedron',
concentration=0,
cation='NA',
anion='CL',
water='spc',
solvent_name='SOL',
with_membrane=False,
ndx='main.ndx',
mainselection='"Protein"',
dirname='solvate',
**kwargs):
"""Put protein into box, add water, add counter-ions.
Currently this really only supports solutes in water. If you need
to embedd a protein in a membrane then you will require more
sophisticated approaches.
However, you *can* supply a protein already inserted in a
bilayer. In this case you will probably want to set *distance* =
``None`` and also enable *with_membrane* = ``True`` (using extra
big vdw radii for typical lipids).
.. Note:: The defaults are suitable for solvating a globular
protein in a fairly tight (increase *distance*!) dodecahedral
box.
:Arguments:
*struct* : filename
pdb or gro input structure
*top* : filename
Gromacs topology
*distance* : float
When solvating with water, make the box big enough so that
at least *distance* nm water are between the solute *struct*
and the box boundary.
Set *boxtype* to ``None`` in order to use a box size in the input
file (gro or pdb).
*boxtype* or *bt*: string
Any of the box types supported by :class:`~gromacs.tools.Editconf`
(triclinic, cubic, dodecahedron, octahedron). Set the box dimensions
either with *distance* or the *box* and *angle* keywords.
If set to ``None`` it will ignore *distance* and use the box
inside the *struct* file.
*bt* overrides the value of *boxtype*.
*box*
List of three box lengths [A,B,C] that are used by :class:`~gromacs.tools.Editconf`
in combination with *boxtype* (``bt`` in :program:`editconf`) and *angles*.
Setting *box* overrides *distance*.
*angles*
List of three angles (only necessary for triclinic boxes).
*concentration* : float
Concentration of the free ions in mol/l. Note that counter
ions are added in excess of this concentration.
*cation* and *anion* : string
Molecule names of the ions. This depends on the chosen force field.
*water* : string
Name of the water model; one of "spc", "spce", "tip3p",
"tip4p". This should be appropriate for the chosen force
field. If an alternative solvent is required, simply supply the path to a box
with solvent molecules (used by :func:`~gromacs.genbox`'s *cs* argument)
and also supply the molecule name via *solvent_name*.
*solvent_name*
Name of the molecules that make up the solvent (as set in the itp/top).
Typically needs to be changed when using non-standard/non-water solvents.
["SOL"]
*with_membrane* : bool
``True``: use special ``vdwradii.dat`` with 0.1 nm-increased radii on
lipids. Default is ``False``.
*ndx* : filename
How to name the index file that is produced by this function.
*mainselection* : string
A string that is fed to :class:`~gromacs.tools.Make_ndx` and
which should select the solute.
*dirname* : directory name
Name of the directory in which all files for the solvation stage are stored.
*includes*
List of additional directories to add to the mdp include path
*kwargs*
Additional arguments are passed on to
:class:`~gromacs.tools.Editconf` or are interpreted as parameters to be
changed in the mdp file.
"""
structure = realpath(struct)
topology = realpath(top)
# arguments for editconf that we honour
editconf_keywords = [
"box", "bt", "angles", "c", "center", "aligncenter", "align",
"translate", "rotate", "princ"
]
editconf_kwargs = dict((k, kwargs.pop(k, None)) for k in editconf_keywords)
editconf_boxtypes = [
"triclinic", "cubic", "dodecahedron", "octahedron", None
]
# needed for topology scrubbing
scrubber_kwargs = {'marker': kwargs.pop('marker', None)}
# sanity checks and argument dependencies
bt = editconf_kwargs.pop('bt')
boxtype = bt if bt else boxtype # bt takes precedence over boxtype
if not boxtype in editconf_boxtypes:
msg = "Unsupported boxtype {boxtype!r}: Only {boxtypes!r} are possible.".format(
**vars())
logger.error(msg)
raise ValueError(msg)
if editconf_kwargs['box']:
distance = None # if box is set then user knows what she is doing...
# handle additional include directories (kwargs are also modified!)
mdp_kwargs = cbook.add_mdp_includes(topology, kwargs)
if water.lower() in ('spc', 'spce'):
water = 'spc216'
elif water.lower() == 'tip3p':
water = 'spc216'
logger.warning(
"TIP3P water model selected: using SPC equilibrated box "
"for initial solvation because it is a reasonable starting point "
"for any 3-point model. EQUILIBRATE THOROUGHLY!")
# By default, grompp should not choke on a few warnings because at
# this stage the user cannot do much about it (can be set to any
# value but is kept undocumented...)
grompp_maxwarn = kwargs.pop('maxwarn', 10)
# clean topology (if user added the marker; the default marker is
# ; Gromacs auto-generated entries follow:
n_removed = cbook.remove_molecules_from_topology(topology,
**scrubber_kwargs)
with in_dir(dirname):
logger.info(
"[{dirname!s}] Solvating with water {water!r}...".format(**vars()))
if boxtype is None:
hasBox = False
ext = os.path.splitext(structure)[1]
if ext == '.gro':
hasBox = True
elif ext == '.pdb':
with open(structure) as struct:
for line in struct:
if line.startswith('CRYST'):
hasBox = True
break
if not hasBox:
msg = "No box data in the input structure {structure!r} and boxtype is set to None".format(
**vars())
logger.exception(msg)
raise MissingDataError(msg)
distance = boxtype = None # ensures that editconf just converts
editconf_kwargs.update({
'f': structure,
'o': 'boxed.gro',
'bt': boxtype,
'd': distance
})
gromacs.editconf(**editconf_kwargs)
if with_membrane:
vdwradii_dat = get_lipid_vdwradii() # need to clean up afterwards
logger.info("Using special vdW radii for lipids {0!r}".format(
vdw_lipid_resnames))
try:
gromacs.genbox(p=topology,
cp='boxed.gro',
cs=water,
o='solvated.gro')
except:
if with_membrane:
# remove so that it's not picked up accidentally
utilities.unlink_f(vdwradii_dat)
raise
logger.info("Solvated system with %s", water)
with open('none.mdp', 'w') as mdp:
mdp.write(
'; empty mdp file\ninclude = {include!s}\nrcoulomb = 1\nrvdw = 1\nrlist = 1\n'
.format(**mdp_kwargs))
qtotgmx = cbook.grompp_qtot(f='none.mdp',
o='topol.tpr',
c='solvated.gro',
p=topology,
stdout=False,
maxwarn=grompp_maxwarn)
qtot = round(qtotgmx)
logger.info(
"[{dirname!s}] After solvation: total charge qtot = {qtotgmx!r} = {qtot!r}"
.format(**vars()))
if concentration != 0:
logger.info(
"[{dirname!s}] Adding ions for c = {concentration:f} M...".
format(**vars()))
# target concentration of free ions c ==>
# N = N_water * c/c_water
# add ions for concentration to the counter ions (counter ions are less free)
#
# get number of waters (count OW ... works for SPC*, TIP*P water models)
rc, output, junk = gromacs.make_ndx(f='topol.tpr',
o='ow.ndx',
input=('keep 0', 'del 0',
'a OW*', 'name 0 OW',
'', 'q'),
stdout=False)
groups = cbook.parse_ndxlist(output)
gdict = {g['name']: g for g in groups} # overkill...
N_water = gdict['OW']['natoms'] # ... but dict lookup is nice
N_ions = int(N_water * concentration /
CONC_WATER) # number of monovalents
else:
N_ions = 0
# neutralize (or try -neutral switch of genion???)
n_cation = n_anion = 0
if qtot > 0:
n_anion = int(abs(qtot))
elif qtot < 0:
n_cation = int(abs(qtot))
n_cation += N_ions
n_anion += N_ions
if n_cation != 0 or n_anion != 0:
# sanity check:
assert qtot + n_cation - n_anion < 1e-6
logger.info(
"[{dirname!s}] Adding n_cation = {n_cation:d} and n_anion = {n_anion:d} ions..."
.format(**vars()))
gromacs.genion(s='topol.tpr',
o='ionized.gro',
p=topology,
pname=cation,
nname=anion,
np=n_cation,
nn=n_anion,
input=solvent_name)
else:
# fake ionized file ... makes it easier to continue without too much fuzz
try:
os.unlink('ionized.gro')
except OSError, err:
if err.errno != errno.ENOENT:
raise
os.symlink('solvated.gro', 'ionized.gro')
qtot = cbook.grompp_qtot(f='none.mdp',
o='ionized.tpr',
c='ionized.gro',
p=topology,
stdout=False,
maxwarn=grompp_maxwarn)
if abs(qtot) > 1e-4:
wmsg = "System has non-zero total charge qtot = {qtot:g} e.".format(
**vars())
warnings.warn(wmsg, category=BadParameterWarning)
logger.warn(wmsg)
# make main index
try:
make_main_index('ionized.tpr', selection=mainselection, ndx=ndx)
except GromacsError, err:
# or should I rather fail here?
wmsg = "Failed to make main index file %r ... maybe set mainselection='...'.\n"\
"The error message was:\n%s\n" % (ndx, str(err))
logger.warn(wmsg)
warnings.warn(wmsg, category=GromacsFailureWarning)
def solvate_sol(struct='top/protein.pdb', top='top/system.top',
distance=0.9, boxtype='dodecahedron',
water='tip4p', solvent_name='SOL', with_membrane=False,
dirname='solvate',
**kwargs):
structure = realpath(struct)
topology = realpath(top)
# arguments for editconf that we honour
editconf_keywords = ["box", "bt", "angles", "c", "center", "aligncenter",
"align", "translate", "rotate", "princ"]
editconf_kwargs = dict((k,kwargs.pop(k,None)) for k in editconf_keywords)
editconf_boxtypes = ["triclinic", "cubic", "dodecahedron", "octahedron", None]
# needed for topology scrubbing
scrubber_kwargs = {'marker': kwargs.pop('marker',None)}
# sanity checks and argument dependencies
bt = editconf_kwargs.pop('bt')
boxtype = bt if bt else boxtype # bt takes precedence over boxtype
if not boxtype in editconf_boxtypes:
msg = "Unsupported boxtype {boxtype!r}: Only {boxtypes!r} are possible.".format(**vars())
logger.error(msg)
raise ValueError(msg)
if editconf_kwargs['box']:
distance = None # if box is set then user knows what she is doing...
if water.lower() in ('spc', 'spce'):
water = 'spc216'
elif water.lower() == 'tip3p':
water = 'spc216'
logger.warning("TIP3P water model selected: using SPC equilibrated box "
"for initial solvation because it is a reasonable starting point "
"for any 3-point model. EQUILIBRATE THOROUGHLY!")
# clean topology (if user added the marker; the default marker is
# ; Gromacs auto-generated entries follow:
n_removed = cbook.remove_molecules_from_topology(topology, **scrubber_kwargs)
with in_dir(dirname):
logger.info("[{dirname!s}] Solvating with water {water!r}...".format(**vars()))
if boxtype is None:
hasBox = False
ext = os.path.splitext(structure)[1]
if ext == '.gro':
hasBox = True
elif ext == '.pdb':
with open(structure) as struct:
for line in struct:
if line.startswith('CRYST'):
hasBox = True
break
if not hasBox:
msg = "No box data in the input structure {structure!r} and boxtype is set to None".format(**vars())
logger.exception(msg)
raise MissingDataError(msg)
distance = boxtype = None # ensures that editconf just converts
editconf_kwargs.update({'f': structure, 'o': 'boxed.gro',
'bt': boxtype, 'd': distance})
gromacs.editconf(**editconf_kwargs)
if with_membrane:
vdwradii_dat = get_lipid_vdwradii() # need to clean up afterwards
logger.info("Using special vdW radii for lipids {0!r}".format(vdw_lipid_resnames))
try:
gromacs.genbox(p=topology, cp='boxed.gro', cs=water, o='solvated.gro')
except:
if with_membrane:
# remove so that it's not picked up accidentally
utilities.unlink_f(vdwradii_dat)
raise
logger.info("Solvated system with %s", water)
return {'struct': realpath(dirname, 'solvated.gro'),}
def solvate_sol(struct='top/protein.pdb',
top='top/system.top',
distance=0.9,
boxtype='dodecahedron',
water='tip4p',
solvent_name='SOL',
with_membrane=False,
dirname='solvate',
**kwargs):
structure = realpath(struct)
topology = realpath(top)
# arguments for editconf that we honour
editconf_keywords = [
"box", "bt", "angles", "c", "center", "aligncenter", "align",
"translate", "rotate", "princ"
]
editconf_kwargs = dict((k, kwargs.pop(k, None)) for k in editconf_keywords)
editconf_boxtypes = [
"triclinic", "cubic", "dodecahedron", "octahedron", None
]
# needed for topology scrubbing
scrubber_kwargs = {'marker': kwargs.pop('marker', None)}
# sanity checks and argument dependencies
bt = editconf_kwargs.pop('bt')
boxtype = bt if bt else boxtype # bt takes precedence over boxtype
if not boxtype in editconf_boxtypes:
msg = "Unsupported boxtype {boxtype!r}: Only {boxtypes!r} are possible.".format(
**vars())
logger.error(msg)
raise ValueError(msg)
if editconf_kwargs['box']:
distance = None # if box is set then user knows what she is doing...
if water.lower() in ('spc', 'spce'):
water = 'spc216'
elif water.lower() == 'tip3p':
water = 'spc216'
logger.warning(
"TIP3P water model selected: using SPC equilibrated box "
"for initial solvation because it is a reasonable starting point "
"for any 3-point model. EQUILIBRATE THOROUGHLY!")
# clean topology (if user added the marker; the default marker is
# ; Gromacs auto-generated entries follow:
n_removed = cbook.remove_molecules_from_topology(topology,
**scrubber_kwargs)
with in_dir(dirname):
logger.info(
"[{dirname!s}] Solvating with water {water!r}...".format(**vars()))
if boxtype is None:
hasBox = False
ext = os.path.splitext(structure)[1]
if ext == '.gro':
hasBox = True
elif ext == '.pdb':
with open(structure) as struct:
for line in struct:
if line.startswith('CRYST'):
hasBox = True
break
if not hasBox:
msg = "No box data in the input structure {structure!r} and boxtype is set to None".format(
**vars())
logger.exception(msg)
raise MissingDataError(msg)
distance = boxtype = None # ensures that editconf just converts
editconf_kwargs.update({
'f': structure,
'o': 'boxed.gro',
'bt': boxtype,
'd': distance
})
gromacs.editconf(**editconf_kwargs)
if with_membrane:
vdwradii_dat = get_lipid_vdwradii() # need to clean up afterwards
logger.info("Using special vdW radii for lipids {0!r}".format(
vdw_lipid_resnames))
try:
gromacs.genbox(p=topology,
cp='boxed.gro',
cs=water,
o='solvated.gro')
except:
if with_membrane:
# remove so that it's not picked up accidentally
utilities.unlink_f(vdwradii_dat)
raise
logger.info("Solvated system with %s", water)
return {
'struct': realpath(dirname, 'solvated.gro'),
}
#!/usr/bin/env python
import sys
import os
import gromacs
import numpy as np
solute = sys.argv[1]
outname = solute.split(".")[0] + "_b" + ".gro"
gromacs.editconf(f=solute,
box=list((input("Enter the box size: ").split())),
o=outname)
# center=list(input("Enter the position for solute: ").split()),
#!/usr/bin/env python
import gromacs
import sys, os
grofile = sys.argv[1]
gromacs.editconf(f=grofile, translate=list(input("Enter the translate vector: ").split()), o="out.gro")
def add_box_mutation(self):
"""
Function to add the solvent and run a minimization of the local amino acid with the waters included
Output:
system.gro -- file containing the complete system minimized after the mutation
"""
# Read the solvent
os.system("grep ATOM {path}/solvent/solvent_{itera}.pdb | grep -v ENDMDL > {path}/solvent.pdb".format(path=self.path,itera=self.last_iteration))
# Concatenate complex and system
os.system("cat {path}/complex.pdb {path}/solvent.pdb > {path}/system.pdb".format(path=self.path))
rc,sout,serr=gromacs.editconf(f=self.path+"/system.pdb", o=self.path+"/system_mod.pdb", stdout=False)
os.system("mv {}/system_mod.pdb {}/system.pdb".format(self.path,self.path))
# Make an index of the system
rc,sout,serr=gromacs.make_ndx(f=self.path+"/system.pdb", o=self.path+"/index.ndx", stdout=False, input=('chain {} \n q'.format(self.pep_chain)))
# Copy the topol files of the target chains, which are the same always
if self.target=="protein":
for ch in self.chain_join:
os.system("cp {}/topol_Protein_chain_{}.itp {}/system_Protein_chain_{}.itp".format(self.path,ch,self.path,ch))
if self.target=="drug":
for ch in self.chain_join:
os.system("cp {}/topol_Drug_chain_{}.itp {}/system_Drug_chain_{}.itp".format(self.path,ch,self.path,ch))
# Copy the topol.top to system.top
os.system("cp {}/topol.top {}/system.top".format(self.path,self.path))
os.system("cp {}/complex_Protein_chain_{}.itp {}/system_Protein_chain_{}.itp".format(self.path,self.pep_chain,self.path,self.pep_chain))
os.system("sed -i 's/topol_/system_/g' {}/system.top".format(self.path))
# Select water and ions within 0.2 distance of the residue
rc,sout,serr=gromacs.make_ndx(f=self.path+"/system.pdb", o=self.path+"/index.ndx", stdout=False, input=('chain {}'.format(self.pep_chain),'q'))
rc,sout,serr=gromacs.select(f=self.path+"/system.pdb", n=self.path+"/index.ndx", s=self.path+"/system.pdb", on=self.path+"/index_sol.ndx", stdout=False, select="group Water_and_ions and same residue as within 0.2 of (group ch{} and resnr {})".format(self.pep_chain,self.pep_position))
# Solve the issue with atoms overlapped with the selected residue
values=[x.strip() for x in open(self.path+"/index_sol.ndx")]
atomsSOL=[]
for i,v in enumerate(values):
if i!=0:
info=v.split()
atomsSOL=atomsSOL+info
# List of the atoms that will be deleted
atomsDelete=[]
# Check the overlapped atoms
for a in atomsSOL:
# Obtain the list of atoms from the index file
bash = "awk '$2 == '{}' {{print $6','$7','$8}}' {}/system.pdb".format(a,self.path)
coordinates = subprocess.check_output(['bash','-c', bash])
comp=coordinates.strip().split()
comparison=[]
for c in comp: comparison.append(float(c))
ndComp=np.array(comparison)
distancesSOL=[]
# Read the structure in biopython
parser = PDBParser()
structure = parser.get_structure('PEP', self.path+"/system.pdb")
model = structure[0]
# Check the distances with all the atoms from the selected residue
for residue in model[self.pep_chain]:
resC=residue.get_resname()
resNumber=residue.get_full_id()[3][1]
if resNumber==self.pep_position:
for atom in residue:
idAtom = atom.get_id()
if idAtom[0].isdigit() == False:
if resC=="ILE" and idAtom=="CD": idAtom="CD1"
diff = atom.coord - ndComp
diffValue=np.sqrt(np.sum(diff * diff))
distancesSOL.append(float(diffValue))
# Threshold to determine which atoms can be overlapped
if min(distancesSOL)<1.0:
if a not in atomsDelete: atomsDelete.append(a)
# Selection of the final atoms that will be included in the index
final_index=[]
for element in atomsSOL:
flag=0
for delete in atomsDelete:
if abs(int(element)-int(delete))<=2: flag=1
if flag==0:
final_index.append(element)
# Update of the index sol file
new_index=open(self.path+"/index_sol2.ndx","w")
new_index.write("{}\n".format(values[0]))
group=[]
counter=1
for ele in final_index:
if counter <15:
group.append(ele)
counter+=1
else:
group.append(ele)
new_index.write(" ".join(group)+" \n")
counter=1
group=[]
new_index.write(" ".join(group)+" ")
new_index.close()
# Update the file
os.system("mv {}/index_sol2.ndx {}/index_sol.ndx".format(self.path,self.path))
ref_ndx = NDX()
ref_ndx.read(self.path+"/index.ndx")
bash="grep '\[' {}/index.ndx | wc -l".format(self.path)
number_index = subprocess.check_output(['bash','-c', bash])
index_ref=int(number_index)-1
#index_ref=len(ref_ndx)-1
# Create the side chain index in a template file
os.system("echo 'name 0 overlap' > %s/template" %self.path)
os.system("echo '\"SideChain\" & \"ch{}\" & r {}' >> {}/template".format(self.pep_chain,str(self.pep_position),self.path))
os.system("echo '\"overlap\" | \"SideChain_&_ch{}_&_r_{}\"' >> {}/template".format(self.pep_chain,str(self.pep_position),self.path))
os.system("echo '\"System\" &! \"overlap_SideChain_&_ch{}_&_r_{}\"' >> {}/template".format(self.pep_chain,str(self.pep_position),self.path))
os.system("echo 'q' >> {}/template".format(self.path))
# Create an index joining both created before
os.system("gmx -quiet make_ndx -f {path}/system.pdb -n {path}/index_sol.ndx {path}/index.ndx -o {path}/total_index.ndx < {path}/template".format(path=self.path))
os.system("sed -i 's/System_&_\!overlap_SideChain_&_ch{}_&_r_{}/to_block/g' {}/total_index.ndx".format(self.pep_chain,str(self.pep_position),self.path))
# Generate the gro file
rc,sout,serr=gromacs.editconf(f=self.path+"/system.pdb", o=self.path+"/system.gro", stdout=False)
# Prepare the files for the minimization and run
rc,sout,serr=gromacs.grompp(f=self.path+"/mdp/minim_overlap.mdp", o=self.path+"/systemNEW.tpr", p=self.path+"/system.top", n=self.path+"/total_index.ndx", c=self.path+"/system.gro", stdout=False)
gromacs.utilities.unlink_gmx("mdout.mdp")
print("Running second minimization ...")
rc,sout,serr=gromacs.mdrun(deffnm=self.path+"/systemNEW", stdout=False)
# Copy the system.gro file that will be used to run the last minimization
os.system("cp {}/systemNEW.gro {}/system.gro".format(self.path,self.path))
os.system("sed -i '$ d' {}/system.gro".format(self.path))
os.system("tail -n1 {path}/npt-pbc.gro >> {path}/system.gro".format(path=self.path))
# Delete temporal files
os.system("rm {path}/complex.pdb {path}/solvent.pdb {path}/systemNEW* {path}/template {path}/index.ndx {path}/index_sol.ndx {path}/total_index.ndx *.itp".format(path=self.path))
def run_minim_complex(self,run_minim=False):
"""
Function to run a local minimization on the side chain that was mutated
Arguments:
run_minim -- boolean flag that will control if the minimization is run or not
Output:
complex.pdb -- new complex pdb with the minimization and the new itp files
"""
# Get the chain with the peptide to generate a novel itp file
os.system("python3 {}/src/scores/get_chains.py {}/complex.pdb {}".format(self.path_scores,self.path,self.path))
rc,sout,serr=gromacs.pdb2gmx(f=self.path+"/complex_"+self.pep_chain+".pdb", p=self.path+"/binder.top", o=self.path+"/complex_"+self.pep_chain+".gro", stdout=False, input=('6','6'))
os.system("sed -i '/forcefield/d' {}/binder.top".format(self.path))
os.system("sed -i '/\[ system \]/,$d' {}/binder.top".format(self.path))
os.system("mv {}/binder.top {}/complex_Protein_chain_{}.itp".format(self.path,self.path,self.pep_chain))
rc,sout,serr=gromacs.editconf(f=self.path+"/complex_"+self.pep_chain+".gro", o=self.path+"/complex_"+self.pep_chain+".pdb", stdout=False)
# Fix the amino acid nomenclature
os.system("for i in ASP ARG HIS HIE HID HIP LYS GLU SER THR ASN GLN CYS CYX GLY PRO ALA VAL ILE LEU MET PHE TYR TRP; do sed -i s/\"$i \"/\"$i {}\"/g {}/complex_{}.pdb; done".format(self.pep_chain,self.path,self.pep_chain))
for i,ch in enumerate(self.chain_join):
if i==0:
os.system("grep ATOM {}/complex_{}.pdb > {}/complex.pdb".format(self.path,ch,self.path))
os.system("echo 'TER' >> {}/complex.pdb".format(self.path))
else:
os.system("grep ATOM {}/complex_{}.pdb >> {}/complex.pdb".format(self.path,ch,self.path))
os.system("echo 'TER' >> {}/complex.pdb".format(self.path))
# Get the new complex.pdb and the peptide chain itp file and delete temporal files
os.system("grep ATOM {}/complex_{}.pdb >> {}/complex.pdb".format(self.path,self.pep_chain,self.path))
os.system("echo 'TER' >> {}/complex.pdb".format(self.path))
os.system("rm {}/complex_*.pdb".format(self.path))
os.system("rm {}/complex_*.gro".format(self.path))
os.system("rm {}/chains.seq".format(self.path))
os.system("head -n -18 {}/complex_Protein_chain_{}.itp > {}/temp; mv {}/temp {}/complex_Protein_chain_{}.itp".format(self.path,self.pep_chain,self.path,self.path,self.path,self.pep_chain))
# Copy the topol files of the target chains, which are the same always
# Copy the topol files of the target chains, which are the same always
if self.target=="protein":
for ch in self.chain_join:
os.system("cp {}/topol_Protein_chain_{}.itp {}/complex_Protein_chain_{}.itp".format(self.path,ch,self.path,ch))
if self.target=="drug":
for ch in self.chain_join:
os.system("cp {}/topol_Drug_chain_{}.itp {}/complex_Drug_chain_{}.itp".format(self.path,ch,self.path,ch))
# Copy the topol.top to complex.top and delete all the additional atoms
os.system("cp {}/topol.top {}/complex.top".format(self.path,self.path))
os.system("sed -i '/Ion/d' {}/complex.top".format(self.path))
os.system("sed -i '/SOL/d' {}/complex.top".format(self.path))
os.system("sed -i '/NA/d' {}/complex.top".format(self.path))
os.system("sed -i '/CL/d' {}/complex.top".format(self.path))
os.system("sed -i '/solvent/d' {}/complex.top".format(self.path))
os.system("sed -i 's/topol_/complex_/g' {}/complex.top".format(self.path))
# Get a pdb of the complex where an index will be created
rc,sout,serr=gromacs.make_ndx(f=self.path+"/complex.pdb", o=self.path+"/reference.ndx", stdout=False, input=('q'))
ref_ndx = NDX()
ref_ndx.read(self.path+"/reference.ndx")
#index_ref=len(ref_ndx)-1
bash="grep '\[' {}/reference.ndx | wc -l".format(self.path)
number_index = subprocess.check_output(['bash','-c', bash])
index_ref=int(number_index)-1
gromacs.utilities.unlink_gmx(self.path+"/reference.ndx")
# Create the side chain index
input_for_ndx=()
counter=index_ref
input_for_ndx+=('chain {}'.format(self.pep_chain),); counter+=1
input_for_ndx+=('name {} binder'.format(counter),);
input_for_ndx+=('"SideChain" & "binder"'+' & r {}'.format(self.pep_position),); counter+=1
input_for_ndx+=('"System" &! {}'.format(counter),); counter+=1
input_for_ndx+=('name {} scmut'.format(counter),);
sentence=""
for i,ch in enumerate(self.chain_join):
if i==0: sentence=sentence+"chain {}".format(ch)
else: sentence=sentence+" | chain {}".format(ch)
input_for_ndx+=(sentence,); counter+=1
input_for_ndx+=('name {} target'.format(counter),)
input_for_ndx+=('\"target\" | \"binder\"',); counter+=1
input_for_ndx+=('name {} complex'.format(counter),)
input_for_ndx+=('q',)
# Generate the index file
rc,sout,serr=gromacs.make_ndx(f=self.path+"/complex.pdb", o=self.path+"/scmut.ndx", stdout=False, input=input_for_ndx)
# Generate the gro file
rc,sout,serr=gromacs.editconf(f=self.path+"/complex.pdb", o=self.path+"/complex.gro", stdout=False)
# Add a small box for the residues
os.system("sed -i '$ d' {}/complex.gro".format(self.path))
os.system('echo " 20.0 20.0 20.0" >> {path}/complex.gro'.format(path=self.path))
# Prepare the files for the minimization
rc,sout,serr=gromacs.grompp(f=self.path+"/mdp/minim_scmut.mdp", o=self.path+"/complex.tpr", p=self.path+"/complex.top", n=self.path+"/scmut.ndx", c=self.path+"/complex.gro", stdout=False)
gromacs.utilities.unlink_gmx("mdout.mdp")
# Run the minimization of the side chain alone and the residues around it
if run_minim:
# Run the minimization
print("Running first minimization ...")
rc,sout,serr=gromacs.mdrun(deffnm=self.path+"/complex", stdout=False)
# Get the complex pdb file
rc,sout,serr=gromacs.trjconv(f=self.path+"/complex.gro",s=self.path+"/complex.tpr", n=self.path+"/scmut.ndx", o=self.path+"/min_complex.pdb",stdout=False,input=("complex"))
os.system("rm posre.itp {path}/complex.tpr {path}/complex.top; grep -v ENDMDL {path}/min_complex.pdb | grep -v MODEL > {path}/complex.pdb; rm {path}/min_complex.pdb {path}/complex.log {path}/complex.trr {path}/complex.edr {path}/scmut.ndx".format(path=self.path))
#tr_vector= np.asarray([0, 0, u1.dimensions[2]/10])
#print(tr_vector)
###SET UP THE PROTEIN BOX
print("This stage is to setup protein box to combine to membrane box!!!")
#boxsize = input("enter the box size: ").split()
z_box = float(input("enter the box size along z: "))
x_box = u1.dimensions[0] / 10
y_box = u1.dimensions[1] / 10
boxsize = [x_box, y_box, z_box]
#print(boxsize)
#print(type(z_box))
center = [
x_box / 2, y_box / 2,
float(input("enter the coordinates you want to place protein along z: "))
]
filename = input("provide the file name of residue: ")
outname = filename.split(".")[0]
outname_b = outname + "_b" + ".gro"
gromacs.editconf(f=filename, o=outname_b, box=boxsize, center=center)
outname_bw = outname + "_bw" + ".gro"
gromacs.solvate(cp=outname_b, o="out.gro")
gromacs.editconf(f="out.gro", translate=tr_vector, o=outname_bw)
#
##
#### COMBINE MEMBRANE GRO FILE AND PEPTIDE GRO FILE
u2 = mda.Universe(outname_bw)
u12 = mda.Merge(u2.atoms, u1.atoms)
u12.atoms.write(str(sys.argv[1]).split(".")[0] + "_" + outname + ".gro")
os.rename(
protein_name + '.D00000001', './inactives/incomplete/' +
protein_name + '_inactive_logFile')
modelname = ('./inactives/incomplete/' + protein_name +
'_inactive.pdb')
briefname = ('./inactives/incomplete/' + protein_name +
'_inactive')
briefername = (protein_name + '_inactive')
dir_name = ('./inactives/incomplete/')
is_active = 0
for filename in glob.glob("./" + protein_name + "*"):
os.remove(filename)
#mutate_model.py
gromacs.editconf(f=modelname, resnr=first_res, o=modelname)
if re.search('no_mutation', mutation) is not None:
print 'No mutations here'
else:
print "Looks like we've got a mutation. Let's check it out. \n"
different_mutations = re.split('&', mutation)
for mutant_res in range(0, len(different_mutations)):
is_mutated = re.search(r"([a-z])([0-9]+)([a-z])",
different_mutations[mutant_res], re.I)
if is_mutated:
mutations_list = is_mutated.groups()
respos = mutations_list[1]
restyp = pdb.Polypeptide.one_to_three(
mutations_list[0]) #get three letter code
dir_name = ('./inactives/complete/')
is_active = 0
else:
os.rename(protein_name+'.B99990001.pdb', './inactives/incomplete/'+protein_name+'_inactive.pdb')
os.rename(protein_name+'.D00000001', './inactives/incomplete/'+protein_name+'_inactive_logFile')
modelname = ('./inactives/incomplete/'+protein_name+'_inactive.pdb')
briefname = ('./inactives/incomplete/'+protein_name+'_inactive')
briefername = (protein_name+'_inactive')
dir_name = ('./inactives/incomplete/')
is_active = 0
for filename in glob.glob("./"+protein_name+"*"):
os.remove(filename)
#mutate_model.py
gromacs.editconf(f = modelname, resnr = first_res, o = modelname)
if re.search('no_mutation', mutation) is not None:
print 'No mutations here'
else:
print "Looks like we've got a mutation. Let's check it out. \n"
different_mutations = re.split('&', mutation)
for mutant_res in range(0, len(different_mutations)):
is_mutated = re.search(r"([a-z])([0-9]+)([a-z])", different_mutations[mutant_res], re.I)
if is_mutated:
mutations_list = is_mutated.groups()
respos = mutations_list[1]
restyp = pdb.Polypeptide.one_to_three(mutations_list[0]) #get three letter code
#makes use of the optimize function in modeller