def mutate_pose(pose, mutations):
"""Applies list of mutations to the given template pose and returns a mutated version
Args:
pose: PyRosetta Pose() object representing a loaded pdb structure
mutations: list of amino acid swaps to apply, format is: [(int, char), ..., (int, char)]
where char is a string of length 1 in "ACDEFGHIKLMNPQRSTVWY"
Returns:
mutant_pose containing the specified amino acid swaps
Notes:
- this procedure doesn't modify the input pose
"""
mutant_pose = Pose()
mutant_pose.assign(pose)
for aa_num, aa_replacement in mutations:
# ensure mutation is valid and apply it
assert isinstance(aa_num, int)
assert isinstance(aa_replacement, str) and len(aa_replacement) == 1
mutant_pose = mutate_residue(mutant_pose, aa_num, aa_replacement)
# specify a pose packer to repack the mutation region
pose_packer = standard_packer_task(mutant_pose)
pose_packer.restrict_to_repacking()
# =================================
# mark's hack segment
# =================================
# This is a hack, but I want to test. Can't set a movemap, resfiles
# might be the way to go. Freeze all residues.
pose_packer.temporarily_fix_everything()
# Let's release the PI domain
for i in range(1110, 1388):
pose_packer.temporarily_set_pack_residue(i, True)
# =================================
# specify the rotamer mover and apply repacking
packmover = PackRotamersMover(get_fa_scorefxn(), pose_packer)
packmover.apply(mutant_pose)
return mutant_pose
def mutateRes(self, res, chain, new_res):
new_res = new_res.split(":")
new_res = new_res[2]
res = self.pose.pdb_info().pdb2pose(chain, int(res))
pack_radius = tkSimpleDialog.askfloat(
title="Pack radius",
prompt="Please enter the desired neighbor packing radius (A)",
initialvalue=5.0)
if pack_radius == None: return
#print radius
print self.score_class.score(self.pose)
print "Mutating to " + new_res
mutate_residue(self.pose, res, new_res, pack_radius,
self.score_class.score)
print self.score_class.score(self.pose)
print "Mutagenesis Complete."
return self.pose
def mutate_pose(pose, mutations):
"""Applies list of mutations to the given template pose and returns a mutated version
Args:
pose: PyRosetta Pose() object representing a loaded pdb structure
mutations: list of amino acid swaps to apply, format is: [(int, char), ..., (int, char)]
where char is a string of length 1 in "ACDEFGHIKLMNPQRSTVWY"
Returns:
mutant_pose containing the specified amino acid swaps
Notes:
- this procedure doesn't modify the input pose
"""
mutant_pose = Pose()
mutant_pose.assign(pose)
for aa_num, aa_replacement in mutations:
assert isinstance(aa_num, int)
assert isinstance(aa_replacement, str) and len(aa_replacement) == 1
scorefxn = get_fa_scorefxn()
pose_num = find_py_rosetta_res_num(
mutant_pose,
'B',
aa_num,
)
# Use this mutate_residue for automatic repacking based on distance (angstroms)
# distance can be set with using an int in the fourth arguement position. Please run 0,2,5
mutant_pose = mutate_residue(mutant_pose, pose_num, aa_replacement, 0,
scorefxn)
# use the mutate_residue below for manually specifying packing residues with the pose_packer
# code below. Try the entire pdb_range, as well as setting to the aa_num list passed to
# the function
# mutant_pose = mutate_residue(mutate_residue, pose_num, aa_replacement)
# kims lines from D050 example
# =================================
# pose_packer = standard_packer_task(mutant_pose)
# pose_packer.restrict_to_repacking()
# This is a hack, but I want to test. Can't set a movemap, resfiles
# might be the way to go. Freeze all residues.
# pose_packer.temporarily_fix_everything()
# Let's release the PI domain
# for i in range(1097, 1364):
# pose_num = find_py_rosetta_res_num(mutant_pose, 'B', i)
# pose_packer.temporarily_set_pack_residue(pose_num,True)
# packmover = PackRotamersMover(scorefxn, pose_packer)
# packmover.apply(mutant_pose)
# =================================
return mutant_pose
def compute_ddG(pose, sfxn, resnum, aa, repack_radius, sc_file):
# Score Native Pose
native_score = sfxn(pose)
# Perform Mutation at residue <resnum> to amino acid <aa>
mutated_pose = mutate_residue(pose, resnum, aa, repack_radius, sfxn)
# Score Mutated Pose
mutant_score = sfxn(mutated_pose)
# If specified the user, print the breakdown of ddG values into a file
print_ddG_breakdown(pose, mutated_pose, sfxn, resnum, aa, sc_file)
# return scores
return aa, round(mutant_score,
3), round(native_score,
3), round(mutant_score - native_score, 3)
def mutate_pose(pose, mutations):
"""Applies list of mutations to the given template pose and returns a mutated version
Args:
pose: PyRosetta Pose() object representing a loaded pdb structure
mutations: list of amino acid swaps to apply, format is: [(int, char), ..., (int, char)]
where char is a string of length 1 in "ACDEFGHIKLMNPQRSTVWY"
Returns:
mutant_pose containing the specified amino acid swaps
Notes:
- this procedure doesn't modify the input pose
"""
mutant_pose = Pose()
mutant_pose.assign(pose)
for aa_num, aa_replacement in mutations:
assert isinstance(aa_num, int)
assert isinstance(aa_replacement, str) and len(aa_replacement) == 1
scorefxn = get_fa_scorefxn()
pose_num = find_py_rosetta_res_num(mutant_pose, 'B',aa_num,)
# Use this mutate_residue for automatic repacking based on distance (angstroms)
# distance can be set with using an int in the fourth arguement position. Please run 0,2,5
mutant_pose = mutate_residue(mutant_pose, pose_num, aa_replacement, 0, scorefxn)
# use the mutate_residue below for manually specifying packing residues with the pose_packer
# code below. Try the entire pdb_range, as well as setting to the aa_num list passed to
# the function
# mutant_pose = mutate_residue(mutate_residue, pose_num, aa_replacement)
# kims lines from D050 example
# =================================
# pose_packer = standard_packer_task(mutant_pose)
# pose_packer.restrict_to_repacking()
# This is a hack, but I want to test. Can't set a movemap, resfiles
# might be the way to go. Freeze all residues.
# pose_packer.temporarily_fix_everything()
# Let's release the PI domain
# for i in range(1097, 1364):
# pose_num = find_py_rosetta_res_num(mutant_pose, 'B', i)
# pose_packer.temporarily_set_pack_residue(pose_num,True)
# packmover = PackRotamersMover(scorefxn, pose_packer)
# packmover.apply(mutant_pose)
# =================================
return mutant_pose
def mutate_pose(pose, mutations):
"""Applies list of mutations to the given template pose and returns a mutated version
Args:
pose: PyRosetta Pose() object representing a loaded pdb structure
mutations: list of amino acid swaps to apply, format is: [(int, char), ..., (int, char)]
where char is a string of length 1 in "ACDEFGHIKLMNPQRSTVWY"
Returns:
mutant_pose containing the specified amino acid swaps
Notes:
- this procedure doesn't modify the input pose
"""
mutant_pose = Pose()
mutant_pose.assign(pose)
for aa_num, aa_replacement in mutations:
# ensure mutation is valid and apply it
assert isinstance(aa_num, int)
assert isinstance(aa_replacement, str) and len(aa_replacement) == 1
#Use the find_pyrosetta_res_num() to automatically convert from pdb to Rosetta numbering
pose_num = find_pyrosetta_res_num(mutate_pose, 'B', aa_num)
mutant_pose = mutate_residue(mutant_pose, pose_num, aa_replacement)
# specify a pose packer to repack the mutation region
pose_packer = standard_packer_task(mutant_pose)
pose_packer.restrict_to_repacking()
# =================================
# mark's hack segment
# =================================
# This is a hack, but I want to test. Can't set a movemap, resfiles
# might be the way to go. Freeze all residues.
pose_packer.temporarily_fix_everything()
# Let's release the PI domain
for i in range(1110, 1388):
pose_num = find_pyrosetta_res_num(mutate_pose, 'B', i)
pose_packer.temporarily_set_pack_residue(pose_num, True)
# =================================
# specify the rotamer mover and apply repacking
packmover = PackRotamersMover(get_fa_scorefxn(), pose_packer)
packmover.apply(mutant_pose)
return mutant_pose
def runFoldxSimpleMutator(mutant, pdbs):
output = open('list.txt', 'w')
fns = ''
for pdb in pdbs:
fns += pdb + '\n'
output.write(fns)
output.close()
m=mutant[2:-1]
here=mutant[-1]
name=rev_resdict[mutant[-1]]+mutant[2:-1]+'_'+pdbs
print("name of file",str(name))
initial_pose=pose_from_pdb(pdbs)
res = initial_pose.residue(int(mutant[2:-1]))
#Set up ScoreFunction.
sf = get_fa_scorefxn()
pose2=mutate_residue( initial_pose, int(mutant[2:-1]),mutant[-1],10,sf )
print("mutant", mutant)
print("pdbs", pdbs)
pose2.dump_pdb(str(name))
def main():
# Initialize Rosetta.
init(extra_options='-mute basic -mute core')
# Constants
PACK_RADIUS = 10.0
#Population size
N = 37
#Beta (temp term)
beta = 1
#look up what the first stored value was in the files to get the threshold
threshold = float(-534.687360627 / 2)
#Set up ScoreFunction
sf = get_fa_scorefxn()
#Set up MoveMap.
mm = MoveMap()
mm.set_bb(True)
mm.set_chi(True)
#Prepare data headers
data = ['Generation,RevertTo,OrgScore,RevScore,Change,Prob\n']
# Get the reversions file, the output file the score_mutant_pdb has made
variant_scores = open('mh_rep_3_37.csv')
#get just the mutation we want to revert to
lines = variant_scores.readlines()
var_line = lines[
2] #gets the Nth line how ever long you want the burn to be
var_line = var_line.split(',')[0]
var_loc = int(filter(str.isdigit, var_line))
var_rev = var_line[:1]
gen = 1
#get all the pdb files
sort_list = sorted(glob.glob('*.pdb'), key=numericalSort)
for i in range(1, len(sort_list) - 15):
#calc reversion for next 15 moves
for infile in sorted(glob.glob('*.pdb'), key=numericalSort)[i:i + 15]:
#for each mutation
var_line = lines[
gen +
1] #gets the Nth line how ever long you want the burn to be
var_line = var_line.split(',')[0]
var_loc = int(filter(str.isdigit, var_line))
var_rev = var_line[:1]
print "Current File Being Processed is: " + infile
initial_pose = pose_from_pdb(infile)
initial_score = sf(initial_pose)
print("init scored")
mutant_pose = mutate_residue(initial_pose, var_loc, var_rev,
PACK_RADIUS, sf)
variant_score = sf(mutant_pose)
probability = calc_prob_mh(variant_score, initial_score, N, beta,
threshold)
print(
str(gen) + "," + var_line + "," + str(initial_score) + "," +
str(variant_score) + "," + str(variant_score - initial_score) +
"," + str(probability) + "\n")
data.append(
str(gen) + "," + var_line + "," + str(initial_score) + "," +
str(variant_score) + "," + str(variant_score - initial_score) +
"," + str(probability) + "\n")
gen += 1
print '\nDONE'
data_filename = 'rep_3_mh_37_rev_15_score.csv'
with open(data_filename, "w") as f:
f.writelines(data)
def main():
#read in the file made by the forward sim
args = sys.argv
inputfile = args[1]
data = open(inputfile)
first_line = data.readlines()[1]
var_line=first_line.split(',')
start_stab=var_line[1]
#the first entry in the file is the wild type structure, calc the threshold using this
threshold=float(start_stab)+10
print(threshold)
# Initialize Rosetta.
init(extra_options='-mute basic -mute core')
# Constants
PACK_RADIUS = 0
#Population size
N = 100
#Beta (temp term)
beta = .6
#Set up ScoreFunction
sf = get_fa_scorefxn()
#Set up MoveMap.
mm = MoveMap()
mm.set_bb(True)
mm.set_chi(True)
min_mover = MinMover()
min_mover.movemap(mm)
min_mover.score_function(sf)
min_mover.min_type('dfpmin_armijo_nonmonotone')
#Prepare data headers
data = ['pdbfile_target,pdbfile_used,step,RevertTo,Change,Pos,From,OrgScore,RevScore,Change,Prob\n']
# Get the reversions file, the output file the score_mutant_pdb has made
variant_scores=open(inputfile)
#get just the mutation we want to revert to
lines= variant_scores.readlines()
var_line=lines[500] #gets the Nth line how ever long you want the burn to be
print "staring here", var_line
var_line=var_line.split(',')[0]
var_loc=int(filter(str.isdigit, var_line))
var_rev=var_line[:1]
gen=1
#get all the pdb files
sort_list=sorted(glob.glob('*[0-9].pdb'), key=numericalSort)
sort_list=sort_list[-1016:] #include the last 1000 and some pdbs, the 16 is because we want the ones that happened before the 500th mutation too.
for i in range(1,len(sort_list)-30):
step=-15
#calc reversion for next 15 moves
for infile in sort_list[i:i+31]:
#for each mutation
var_line=lines[gen+500] #gets the Nth line how ever long you want the burn to be
var_line=var_line.split(',')[0]
print(var_line)
var_loc=int(filter(str.isdigit, var_line))
var_rev=""
old=""
if(step<0):
var_rev=var_line[len(var_line)-1:len(var_line)]
old=var_line[:1]
else:
var_rev=var_line[:1]
old=var_line[len(var_line)-1:len(var_line)]
print "Current File Being Processed is: " + infile
print "revering to:", var_rev
print "at:", var_loc
#get the pdb you want to revert and make the reversion
initial_pose = pose_from_pdb(infile)
mutant_pose = mutate_residue(initial_pose, var_loc , var_rev, PACK_RADIUS, sf)
#repack mut
task1 = standard_packer_task(mutant_pose)
task1.restrict_to_repacking()
task1.or_include_current(True)
packer_rotamers_mover1 = RotamerTrialsMover(sf,task1)
packer_rotamers_mover1.apply(mutant_pose)
#repack init
task2 = standard_packer_task(initial_pose)
task2.restrict_to_repacking()
task2.or_include_current(True)
pack_rotamers_mover2 = RotamerTrialsMover(sf, task2)
pack_rotamers_mover2.apply(initial_pose)
#apply min mover
min_mover.apply(mutant_pose)
min_mover.apply(initial_pose)
#get scores
variant_score = sf(mutant_pose)
initial_score = sf(initial_pose)
#get prob
probability = calc_prob_mh(variant_score, initial_score, N, beta, threshold)
print(str(gen+499)+".pdb"+","+str(infile)+","+str(step)+","+ str(var_line) + ","+str(var_rev)+","+str(var_loc)+","+str(old)+"," +str(initial_score) + "," + str(variant
_score) + "," + str(variant_score - initial_score)+ ","+ str(probability)+ "\n")
data.append(str(gen+499)+".pdb"+","+str(infile)+","+str(step)+","+ str(var_line) + ","+str(var_rev)+","+str(var_loc)+","+str(old)+"," +str(initial_score) + "," + str(v
ariant_score) + "," + str(variant_score - initial_score)+ ","+ str(probability)+ "\n")
step=step+1
gen+=1
print '\nDONE'
data_filename = 'premutate_rep1_bb_T_ch_T.csv'
with open(data_filename, "w") as f:
f.writelines(data)
def main():
#takes name of pdb file without the extention
args = sys.argv
pdb_file = args[1]
#set up timer to figure out how long the code took to run
t0 = time()
# Initialize Rosetta.
init(extra_options='-mute basic -mute core')
# Constants
PACK_RADIUS = 10.0
#Amino acids, notice there is no C
AAs = ("A", "D", "E", "F", "G", "H", "I", "K", "L", "M", "N", "P", "Q",
"R", "S", "T", "V", "W", "Y")
#Number of mutations to accept
max_accept_mut = 1500
#Population size
N = 100
#Beta (temp term)
beta = 1
#Prepare data headers
data = ['Variant,Rosetta Score,"delta-delta-G",Probability,Generation\n']
#Load and clean up pdb file
name = pdb_file + ".pdb"
cleanATOM(name)
clean_name = pdb_file + ".clean.pdb"
initial_pose = pose_from_pdb(clean_name)
#Set up ScoreFunction
sf = get_fa_scorefxn()
#Set up MoveMap.
mm = MoveMap()
#change these for more or less flexability
mm.set_bb(True)
mm.set_chi(True)
#Pack and minimize initial pose to remove clashes.
pre_pre_packing_score = sf(initial_pose)
task = standard_packer_task(initial_pose)
task.restrict_to_repacking()
task.or_include_current(True)
pack_rotamers_mover = RotamerTrialsMover(sf, task)
pack_rotamers_mover.apply(initial_pose)
min_mover = MinMover()
min_mover.movemap(mm)
min_mover.score_function(sf)
min_mover.min_type('dfpmin_armijo_nonmonotone')
min_mover.apply(initial_pose)
post_pre_packing_score = sf(initial_pose)
#Set threshold for selection
threshold = pre_pre_packing_score / 2
data.append('WT,' + str(post_pre_packing_score) + ',0.0 ,0.0,0\n')
#number of residues to select from
n_res = initial_pose.total_residue()
#start sim
i = 0
gen = 0
while i < max_accept_mut:
#update the number of generations that have pased
gen += 1
print 'accepts:', i
#pick a place to mutate
mut_location = random.randint(1, n_res)
#get the amino acid at that position
res = initial_pose.residue(mut_location)
#don't mess with C, just choose again
while (res.name1() == 'C'):
mut_location = random.randint(1, n_res)
#get the amino acid at that position
res = initial_pose.residue(mut_location)
#choose the amino acid to mutate to
new_mut_key = random.randint(0, len(AAs) - 1)
proposed_res = AAs[new_mut_key]
#don't bother mutating to the same amino acid it just takes more time
while (proposed_res == res.name1()):
new_mut_key = random.randint(0, len(AAs) - 1)
proposed_res = AAs[new_mut_key]
#make the mutation
#this is actually a really bad model, and probably shouldnt be used. In new version is repack the whole thing, then reminimize, I should also backrub it.
mutant_pose = mutate_residue(initial_pose, mut_location, proposed_res,
PACK_RADIUS, sf)
#score mutant
variant_score = sf(mutant_pose)
#get the probability that the mutation will be accepted
probability = calc_prob_mh(variant_score, post_pre_packing_score, N,
beta, threshold)
#test to see if mutation is accepted
if random.random() < probability:
#create a name for the mutant if its going to be kept
variant_name = res.name1() + str(initial_pose.pdb_info().number(
mut_location)) + str(proposed_res)
# Assuming 1000 burn in phase, take this if out if you want to store everything
if i > 1000:
#save name and energy change
data.append(variant_name + "," + str(variant_score) + "," +
str(variant_score - post_pre_packing_score) + "," +
str(probability) + "," + str(gen) + "\n")
pdb_name = str(i) + ".pdb"
mutant_pose.dump_pdb(pdb_name)
#update the wildtype
initial_pose = mutant_pose
post_pre_packing_score = variant_score
#update number of accepts
i += 1
print '\nMutations and scoring complete.'
t1 = time()
# Output results.
data_filename = pdb_file[:-5] + 'mh_1500_rep3.csv'
with open(data_filename, "w") as f:
f.writelines(data)
print 'Data written to:', data_filename
print 'program takes %f' % (t1 - t0)
) ##where the WT cas9 should be located???
## not sure if completely correct???? add changes if not.
## initializing rosetta:
rosetta.init()
# import cleaning module for PDB to be usable
from toolbox import cleanATOM
cleanATOM("\4UN3.pdb") # cleaned PDB file to use for analysis
var_pose = pose_from_pdb("\4UN3.pdb") # initial pose created from clean pdb
#inputted residue number of interest
Num = raw_input("enter residue number:\n")
for i in range(0, 20):
# list of Amino Acids to substitute
AA_lst = "ACDEFGHIKLMNPQRSTVWY"
AA_var = AA_lst[i]
var_pose = pose_from_pdb("4UN3." + AA_var + ".clean.pdb")
mutate_residue(var_pose, Num,
AA_var) # where Num = residue number to substitute AA
# for sanity checking purposes: prints out changed 4UN3 pdb pose protein profile
# (sequence, # of res, what is located at Num residue - if the substitution occured)
print var_pose
print var_pose.sequence()
print "Protein has", var_pose.total_residue(), "residues."
print var_pose.residue(Num).name() # where Num is a residue number
## not sure if completely correct???? add changes if not.
## initializing rosetta:
rosetta.init()
# import cleaning module for PDB to be usable
from toolbox import cleanATOM
cleanATOM("\4UN3.pdb") # cleaned PDB file to use for analysis
var_pose = pose_from_pdb("\4UN3.pdb") # initial pose created from clean pdb
#inputted residue number of interest
Num = raw_input("enter residue number:\n")
for i in range(0, 20):
# list of Amino Acids to substitute
AA_lst = "ACDEFGHIKLMNPQRSTVWY"
AA_var = AA_lst[i]
var_pose = pose_from_pdb("4UN3." + AA_var + ".clean.pdb")
mutate_residue(var_pose, Num , AA_var) # where Num = residue number to substitute AA
# for sanity checking purposes: prints out changed 4UN3 pdb pose protein profile
# (sequence, # of res, what is located at Num residue - if the substitution occured)
print var_pose
print var_pose.sequence()
print "Protein has", var_pose.total_residue(), "residues."
print var_pose.residue(Num).name() # where Num is a residue number
def main(args):
parser = OptionParser(usage="usage: %prog [OPTIONS] [TESTS]")
parser.set_description(main.__doc__)
#input options
parser.add_option(
'--in_pdb',
'-p',
action="store",
help="Input PDB file.",
)
parser.add_option(
'--in_span',
'-s',
action="store",
help="Input spanfile.",
)
parser.add_option(
'--out',
'-o',
action="store",
default='ddG.out',
help="Output filename with pose residue numbering. Default: 'ddG.out'",
)
parser.add_option(
'--res',
'-r',
action="store",
help="Pose residue number to mutate.",
)
parser.add_option(
'--mut',
'-m',
action="store",
help=
"One-letter code of residue identity of the mutant. Example: A181F would be 'F'",
)
parser.add_option(
'--repack_radius',
'-a',
action="store",
default=0,
help="Repack the residues within this radius",
)
parser.add_option(
'--output_breakdown',
'-b',
action="store",
default="scores.sc",
help=
"Output mutant and native score breakdown by weighted energy term into a scorefile",
)
parser.add_option(
'--include_pH',
'-t',
action="store",
default=0,
help="Include pH energy terms: pH_energy and fa_elec. Default false.",
)
parser.add_option(
'--pH_value',
'-q',
action="store",
default=7,
help=
"Predict ddG and specified pH value. Default 7. Will not work if include pH is not passed",
)
#parse options
(options, args) = parser.parse_args(args=args[1:])
global Options
Options = options
# Check the required inputs (PDB file, spanfile) are present
if (not Options.in_pdb or not Options.in_span or not Options.res):
sys.exit(
"Must provide flags '-in_pdb', '-in_span', and '-res'! Exiting...")
# Initialize Rosetta options from user options. Enable pH mode if applicable
rosetta_options = ""
standard_options = "-membrane_new:setup:spanfiles " + Options.in_span + " -run:constant_seed -in:ignore_unrecognized_res"
if (Options.include_pH):
print Options.pH_value
if (float(Options.pH_value) < 0 or float(Options.pH_value) > 14):
sys.exit("Specified pH value must be between 0-14: Exiting...")
else:
pH_options = " -pH_mode -value_pH " + str(Options.pH_value)
rosetta_options = standard_options + pH_options
else:
rosetta_options = standard_options
# Initialize Rosetta based on user inputs
rosetta.init(extra_options=rosetta_options)
# Load Pose, & turn on the membrane
pose = pose_from_file(Options.in_pdb)
# Add Membrane to Pose
add_memb = rosetta.protocols.membrane.AddMembraneMover()
add_memb.apply(pose)
# Setup in a topology based membrane
init_mem_pos = rosetta.protocols.membrane.MembranePositionFromTopologyMover(
)
init_mem_pos.apply(pose)
# check the user has specified a reasonable value for the pH
sfxn = rosetta.core.scoring.ScoreFunction()
if (Options.include_pH):
# Create a membrane energy function enabled by pH mode
# Includes two terms not standard in the smoothed energy function: pH energy
# and fa_elec
sfxn = create_score_function("mpframework_pHmode_fa_2015")
else:
# Create a smoothed membrane full atom energy function (pH 7 calculations)
sfxn = create_score_function("mpframework_smooth_fa_2012")
# Repack the native rotamer and residues within the repack radius
native_res = pose.residue(int(Options.res)).name1()
repacked_native = mutate_residue(pose, int(Options.res), native_res,
Options.repack_radius, sfxn)
# to output score breakdown, start by printing the score labels in
# the top of the file
print_score_labels_to_file(repacked_native, sfxn, Options.output_breakdown)
# Compute mutations
if (Options.mut):
with file(Options.out, 'a') as f:
ddGs = compute_ddG(repacked_native, sfxn, int(Options.res),
Options.mut, Options.repack_radius,
Options.output_breakdown)
f.write(Options.in_pdb + " " + Options.res + " " + str(ddGs[0]) +
" " + str(ddGs[1]) + " " + str(ddGs[2]) + " " +
str(ddGs[3]) + "\n")
f.close
else:
AAs = [
'A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N', 'P',
'Q', 'R', 'S', 'T', 'V', 'W', 'Y'
]
for aa in AAs:
with file(Options.out, 'a') as f:
ddGs = compute_ddG(repacked_native, sfxn, int(Options.res), aa,
Options.repack_radius,
Options.output_breakdown)
f.write(
str(ddGs[0]) + " " + str(ddGs[1]) + " " + str(ddGs[2]) +
" " + str(ddGs[3]) + "\n")
f.close
AA
# Check for disulfide special case.
if res.name() == 'CYD':
disulfide_partner = res.residue_connection_partner(
res.n_residue_connections())
temp_pose = Pose()
temp_pose.assign(initial_pose)
# (Packing causes seg fault if current CYS residue is not
# also converted before mutating.)
change_cys_state(seq_pos, 'CYS',
temp_pose.conformation())
change_cys_state(disulfide_partner, 'CYS',
temp_pose.conformation())
# Mutate protein.
mutant_pose = mutate_residue(temp_pose, seq_pos, AA,
PACK_RADIUS, sf)
else:
# Mutate protein.
mutant_pose = mutate_residue(initial_pose, seq_pos, AA,
PACK_RADIUS, sf)
# Minimize.
if args.minimize:
min_mover.apply(mutant_pose)
# Score.
variant_score = sf(mutant_pose)
data.append(variant_name + "," + \
str(variant_score) + "," + \
str(variant_score - post_pre_packing_score) + "\n")
def main():
parser = argparse.ArgumentParser()
parser.add_argument('pdb_filename', action="store", type=str)
parser.add_argument('replicate_number', action="store", type=int)
inputs = parser.parse_args()
#takes name of pdb file without the extention
pdb_file = inputs.pdb_filename
prot_name = pdb_file.split('/')[-1].split('.')[0]
#set up timer to figure out how long the code took to run
t0 = time()
fasta_file = pdb_file.replace('/structures/',
'/fastas/').replace('.pdb', '.fasta')
records = list(SeqIO.parse(fasta_file, 'fasta'))
assert len(records) == 1
wt_seq = str(records[0].seq)
# Initialize Rosetta.
#init(extra_options='-mute basic -mute core')
init(extra_options=
'-mute basic -mute core -rebuild_disulf false -detect_disulf false')
########################
# Constants
########################
PACK_RADIUS = 12.0
#Amino acids
AAs = ("A", "C", "D", "E", "F", "G", "H", "I", "K", "L", "M", "N", "P",
"Q", "R", "S", "T", "V", "W", "Y")
AAs_choice_dict = {}
for aa in AAs:
AAs_choice_dict[aa] = [other_aa for other_aa in AAs if other_aa != aa]
#Number of mutations to accept
max_accept_mut = 10 * len(wt_seq)
#max_accept_mut = 2048
#Population size
N = 1000
#Beta (temp term)
beta = 1
#Fraction of the WT stability value to shoot for
threshold_fraction = 0.5
########################
########################
#Prepare data headers
data = ['Variant,Rosetta Score,"delta-delta-G",Probability,Generation\n']
#Load a clean pdb file
initial_pose = pose_from_pdb(pdb_file)
if '.clean' in pdb_file:
pdb_file = ''.join(pdb_file.split('.clean'))
#Set up ScoreFunction
sf = get_fa_scorefxn()
#Set up MoveMap.
mm = MoveMap()
mm.set_bb(True)
mm.set_chi(True)
#Pack and minimize initial pose to remove clashes.
pre_pre_packing_score = sf(initial_pose)
task = standard_packer_task(initial_pose)
task.restrict_to_repacking()
task.or_include_current(True)
pack_rotamers_mover = RotamerTrialsMover(sf, task)
pack_rotamers_mover.apply(initial_pose)
min_mover = MinMover()
min_mover.movemap(mm)
min_mover.score_function(sf)
min_mover.min_type('dfpmin_armijo_nonmonotone')
min_mover.apply(initial_pose)
post_pre_packing_score = sf(initial_pose)
#Threshold for selection
threshold = post_pre_packing_score * threshold_fraction
print 'threshold:', threshold
data.append('WT,' + str(post_pre_packing_score) + ',0.0,0.0,0\n')
#number of residues to select from
n_res = initial_pose.total_residue()
#start evolution
i = 0
gen = 0
while i < max_accept_mut:
#update the number of generations that have pased
gen += 1
#print 'accepts:', i
#pick a place to mutate
mut_location = random.randint(1, n_res)
#get the amino acid at that position
res = initial_pose.residue(mut_location)
#choose the amino acid to mutate to
#new_mut_key = random.randint(0,len(AAs)-1)
#proposed_res = AAs[new_mut_key]
proposed_res = random.choice(AAs_choice_dict[res.name1()])
#make the mutation
mutant_pose = mutate_residue(initial_pose, mut_location, proposed_res,
PACK_RADIUS, sf)
#score mutant
variant_score = sf(mutant_pose)
#get the probability that the mutation will be accepted
probability = calc_prob_mh(variant_score, post_pre_packing_score, N,
beta, threshold)
#test to see if mutation is accepted
if random.random() < probability:
#create a name for the mutant if its going to be kept
variant_name = res.name1() + str(initial_pose.pdb_info().number(
mut_location)) + str(proposed_res)
#save name and energy change
data.append(variant_name + "," + str(variant_score) + "," +
str(variant_score - post_pre_packing_score) + "," +
str(probability) + "," + str(gen) + "\n")
# if i == (max_accept_mut - 1):
# final_pdb_name=pdb_file.replace('.pdb', '_thresh={}_Neff={}_beta={}_i={}_nmut={}.pdb'.format(threshold_fraction, N, beta, inputs.replicate_number, i))
# mutant_pose.dump_pdb(final_pdb_name)
#update the wildtype
initial_pose = mutant_pose
post_pre_packing_score = variant_score
#update number of accepts
i += 1
print '\nMutations and scoring complete.'
t1 = time()
# Output results.
output_filename = '../Results/{}/{}_thresh={}_Neff={}_beta={}_i={}.csv'.format(
prot_name, prot_name, threshold_fraction, N, beta,
inputs.replicate_number)
with open(output_filename, "w") as outfile:
outfile.writelines(data)
print 'Data written to:', output_filename
print 'program takes %f' % (t1 - t0)
# PyRosetta imports
from toolbox import mutate_residue
from rosetta import init, pose_from_sequence
# Initialize PyRosetta
init()
# Create Ala12
print('Creating Ala12...')
seq = 12*'A'
pose = pose_from_sequence(seq)
# Mutate residue 5 to K
print('Mutating Fifth Ala to Lys...')
mutant = mutate_residue(pose, 5, 'K')
# Load mutant into ParmEd
print('Loading into ParmEd...')
struct = load_rosetta(mutant)
# Load AMBER-99SBildn and TIP3P parameters
print('Loading AMBER parameters...')
ff = ForceField('amber99sbildn.xml', 'tip3p.xml')
# Solvate Structure
print('Solvating...')
mod = Modeller(struct.topology, struct.positions)
mod.addSolvent(ff, model='tip3p', boxSize=Vec3(4, 4, 4)*nanometers,
positiveIon='Na+', negativeIon='Cl-',
ionicStrength=0.1*molar)
def runFoldxSimpleMutator(mutant, pdbs):
output = open('list.txt', 'w')
fns = ''
for pdb in pdbs:
fns += pdb + '\n'
output.write(fns)
output.close()
print("muatint")
print(mutant)
#print(pdbs)
m=mutant[2:-1]
here=mutant[-1]
#print(m)
#print(mutant)
#print(here)
name=rev_resdict[mutant[-1]]+mutant[2:-1]+'_'+pdbs
print("name of file",str(name))
initial_pose=pose_from_pdb(pdbs)
res = initial_pose.residue(int(mutant[2:-1]))
#Set up ScoreFunction.
sf = get_fa_scorefxn()
# Set up MoveMap.
#mm = MoveMap()
#mm.set_bb(True)
#mm.set_chi(True)
# Pack and minimize initial pose to remove clashes.
#pre_pre_packing_score = sf( initial_pose)
#task = standard_packer_task( initial_pose)
#task.restrict_to_repacking()
#task.or_include_current(True)
#pack_rotamers_mover = RotamerTrialsMover(sf, task)
#pack_rotamers_mover.apply(initial_pose)
#min_mover = MinMover()
#min_mover.movemap(mm)
#min_mover.score_function(sf)
#min_mover.min_type('linmin')
print("loaded file")
#pose2=mutate_residue(pose, m, here)
pose2=mutate_residue( initial_pose, int(mutant[2:-1]),mutant[-1],10,sf )
print("mutant", mutant)
print("pdbs", pdbs)
# Set up ScoreFunction.
#sf = get_fa_scorefxn()
# Set up MoveMap.
#mm = MoveMap()
#mm.set_bb(True)
#mm.set_chi(True)
# Pack and minimize initial pose to remove clashes.
#pre_pre_packing_score = sf(pose2)
#task = standard_packer_task(pose2)
#task.restrict_to_repacking()
#task.or_include_current(True)
#pack_rotamers_mover = RotamerTrialsMover(sf, task)
#pack_rotamers_mover.apply(pose2)
#min_mover = MinMover()
#min_mover.movemap(mm)
#min_mover.score_function(sf)
#min_mover.min_type('linmin')
#min_mover.apply(pose2)
#post_pre_packing_score = sf(pose2)
#sf.show(pose2)
pose2.dump_pdb(str(name))