def runSimulations(knockouts=True):
print "starting Simulations"
data = {}
targets = [
'CPK213', 'HATPase', 'NOGC1', 'NAD', 'ABA', 'Microtubule', 'Depolar',
'InsP3', 'SphK12', 'ABH1', 'InsP6', 'CIS', 'AnionEM', 'GAPC',
'KEfflux', 'H2OEfflux', 'VPpase', 'PP2CA', 'MRP5', 'CPK23',
'Vacidification', 'DAG', 'ROP11', 'NO', 'pHc', 'PIP21', 'PEPC',
'NitrocGMP', 'HAB1', 'DAGK', 'PLDd', 'PC', 'CPK6', 'PA', 'PLDa', 'PLC',
'PI3P5K', 'ROS', 'AtRAC1', 'OST1', 'cGMP', 'Ca2ATPase', 'GCR1', 'RCN1',
'PIP2', 'QUAC1', 'S1P', 'Malate', 'KOUT', 'NADPH', 'MAPK912', 'KEV',
'SCAB1', 'CaIM', 'TCTP', 'VATPase', 'GPA1', 'PtdIns35P2', 'GTP',
'GEF1410', 'ARP23', 'PtdInsP4', 'Sph', 'ABI1', 'NIA12', 'ADPRc',
'RCARs', 'PtdInsP3', 'Nitrite', 'ABI2', 'SPP1', 'RBOH', 'Actin',
'ERA1', 'NtSyp121', 'Ca2c', 'GHR1', 'cADPR', 'SLAH3', 'SLAC1'
]
for target in targets:
if knockouts is True:
mtext = boolean2.modify_states(text=text, turnoff=target)
fname = 'knockouts.json'
else:
mtext = boolean2.modify_states(text=text, turnon=target)
fname = 'overexpression.json'
model = boolean2.Model(mode='async', text=mtext)
coll = util.Collector()
for i in xrange(repeat):
model.initialize(missing=util.randbool)
model.iterate(steps=steps)
coll.collect(states=model.states, nodes='Closure')
data[target] = {'Timesteps': coll.get_averages(normalize=True)}
data[target]['Closure AUC'] = sum(data[target]['Timesteps']['Closure'])
with open(fname, 'w') as fp:
json.dump(data, fp)
def runSimulations(knockouts=True):
print "starting Simulations"
data = {}
#use the following set of targets if running the simulation for the reduced model
#targets = ['NOGC1', 'PLDdel', 'InsP3', 'nitrocGMP', 'CIS', 'Actin', 'AnionEM', 'K_efflux', 'PP2CA', 'H2O_Efflux', 'DAG', 'NO', 'pHc', 'PEPC', 'HAB1', 'PA',
#'PLDa', 'PLC', 'PI3P5K', 'OST1', 'SLAH3', 'ABA', 'H_ATPase', 'Malate', 'KOUT', 'Depolarization', 'QUAC1', 'CaIM', 'TCTP', 'AtRAC1', 'SPHK12', 'Ca_ATPase',
#'CPKa', 'CPKb', 'ABI2', 'Microtubule_Depolymerization', 'Ca', 'ABI1', 'NIA12', 'MPK', 'RCARs', 'VATPase', 'Vacuolar_Acidification', 'ROP11', 'RBOH', 'KEV',
#'GHR1', 'SLAC1', 'WT']
#use the following set of targets when running the simulation for the full model
#targets = ['CPK321', 'H_ATPase', 'NOGC1', 'ABA', 'Microtubule_Depolymerization', 'Depolarization', 'InsP3', 'SPHK12', 'ABH1', 'InsP6', 'CIS', 'AnionEM',
#'GAPC12', 'K_efflux', 'H2O_Efflux', 'VPPase', 'PP2CA', 'MRP5', 'CPK23', 'Vacuolar_Acidification', 'DAG', 'ROP11', 'NO', 'pHc', 'PIP', 'PEPC', 'nitrocGMP',
#'HAB1', 'DAGK', 'PLDdel', 'PC', 'CPK6', 'PA', 'PLDa', 'PLC', 'PI3P5K', 'ROS', 'AtRAC1', 'OST1', 'cGMP', 'Ca2_ATPase', 'GCR1', 'RCN1', 'QUAC1', 'S1P',
#'Malate', 'KOUT', 'NADPH', 'MPK912', 'KEV', 'SCAB1', 'CaIM', 'TCTP', 'VATPase', 'GPA1', 'PtdIns35P2', 'GTP', 'GEF', 'ARP_Complex', 'PtdInsP4', 'Sph',
#'ABI1', 'NIA12', 'ADPRc', 'RCARs', 'PtdInsP3', 'Nitrite', 'ABI2', 'SPP1', 'RBOH', 'Actin_Reorganization', 'ERA1', 'NtSyp121', 'Ca2', 'GHR1', 'cADPR',
#'SLAH3', 'SLAC1', 'WT', 'PtdIns45P2']
for target in targets:
print 'Processing target', target
if knockouts is True:
mtext = boolean2.modify_states(text=text, turnoff=target)
fname = 'results_KO.json'
else:
mtext = boolean2.modify_states(text=text, turnon=target)
fname = 'results_CA.json'
model = boolean2.Model(mode='async', text=mtext)
coll = util.Collector()
for i in xrange(repeat):
model.initialize(missing=util.randbool)
model.iterate(steps=steps)
coll.collect(states=model.states, nodes='Closure')
data[target] = {'Timesteps': coll.get_averages(normalize=True)}
data[target]['Closure AUC'] = sum(data[target]['Timesteps']['Closure'])
with open(fname, 'w') as fp:
json.dump(data, fp)
def run(text, nodes, repeat, steps):
"""
Runs the simulation and collects the nodes into a collector,
a convenience class that can average the values that it collects.
"""
coll = util.Collector()
for i in xrange(repeat):
engine = Model(mode='async', text=text)
engine.RULE_GETVALUE = new_getvalue
# minimalist initial conditions, missing nodes set to false
engine.initialize(missing=util.false)
engine.iterate(steps=steps)
coll.collect(states=engine.states, nodes=nodes)
print '- completed'
avgs = coll.get_averages(normalize=True)
return avgs
def run_mutations(text, repeat, steps):
"Runs the asynchronous model with different mutations"
# WT does not exist so it won't affect anything
data = {}
knockouts = 'WT S1P PA pHc ABI1 ROS'.split()
for target in knockouts:
print('- target %s' % target)
mtext = boolean2.modify_states(text=text, turnoff=target)
model = Model(mode='async', text=mtext)
coll = util.Collector()
for i in range(repeat):
# unintialized nodes set to random
model.initialize(missing=util.randbool)
model.iterate(steps=steps)
coll.collect(states=model.states, nodes=model.nodes)
data[target] = coll.get_averages(normalize=True)
return data
def all_ss_model_w_fix(str_file,
str_mode,
timecourse,
csv_out_txt,
geneon=[],
geneoff=[]):
'''
A function to generate a list of all possible starting states of a model. Note that this function is a
modification of the all_ss_model() function and allows for specific nodes to be fixed on or off.
str_file: as a string, write the name of the file containing the rules for the boolean model
str_mode: enter the mode of model that is going to be used, ie sync or async
numnodes: the number of nodes in the model
:return:
A list of dictionaries with all possible starting states of the network.
'''
Bool1 = file(str_file).read()
# Generate a new version of the model that allows the genes to be fixed on or off by removing updating rules for
# them. This will not override the initialized value however, and that must be updated to be assigned on or off
# separately.
on = geneon
off = geneoff
Bool2 = tokenizer.modify_states(Bool1, on, off)
model = Model(text=Bool2, mode=str_mode)
initializer = state.all_initial_states(model.nodes, limit=None)
n = 0
d = []
# Utilized in the for loops for the loading bar
load_status_divisor = len(model.nodes) - len(geneoff) - len(geneon)
# The BooleanNet Data Collector. Here it is implemented to gather data on the states of the nodes in the model.
coll = util.Collector()
# Wiley Stoeber. 5/8/18. Create a modified version of the initializer that will pass over initial states that
# contradict the gene set mode
initializer_new = []
if geneoff != [] or geneon != []:
for data_init in initializer:
data = data_init[0]
for i in range(len(geneoff)):
if data[str(geneoff[i])]:
initializer_new.append(data_init)
for i in range(len(geneon)):
if data[str(geneon[i])]:
initializer_new.append(data_init)
for data, initfunc in initializer_new:
# Fixes genes on or off (True or False) at their starting state.
for i in range(len(geneoff)):
data.update({str(geneoff[i]): False})
for i in range(len(geneon)):
data.update({str(geneon[i]): True})
# Initialize the model with the given pre-computed initial conditions stored in the data variable.
# for a given model with Z nodes, there are 2 to the power of Z starting states.
model.initialize(defaults=data)
model.iterate(steps=timecourse)
e = model.detect_cycles()
nodes = [
'Apoptosis', 'Proliferation', 'Angiogenesis', 'Differentiation'
]
d.append(list(model.detect_cycles()))
d[n].append(model.fp())
d[n].append(model.first)
d[n].append(model.last)
detect_states = 0 - e[1]
coll.collect(states=model.states[detect_states:], nodes=nodes)
# Converts collected data back to immutable tuple
# d[n] = tuple(d[n])
# Show data as it is generated. For debug purposes
print d[n]
# this print function is the status bar output.
print((n) / float(pow(2, load_status_divisor))) * 100, "% done."
n += 1
else:
for data, initfunc in initializer:
# Fixes genes on or off (True or False) at their starting state.
for i in range(len(geneoff)):
data.update({str(geneoff[i]): False})
for i in range(len(geneon)):
data.update({str(geneon[i]): True})
# Initialize the model with the given pre-computed initial conditions stored in the data variable.
# for a given model with Z nodes, there are 2 to the power of Z starting states.
model.initialize(defaults=data)
model.iterate(steps=timecourse)
e = model.detect_cycles()
nodes = [
'Apoptosis', 'Proliferation', 'Angiogenesis', 'Differentiation'
]
d.append(list(model.detect_cycles()))
d[n].append(model.fp())
d[n].append(model.first)
d[n].append(model.last)
detect_states = 0 - e[1]
coll.collect(states=model.states[detect_states:], nodes=nodes)
# Converts collected data back to immutable tuple
# d[n] = tuple(d[n])
# Show data as it is generated. For debug purposes
print d[n]
# this print function is the status bar output.
print((n) / float(pow(2, load_status_divisor))) * 100, "% done."
n += 1
# Add the avg on state of the nodes specified by the user. They will output to new columns in row 1 of the data
avgs = coll.get_averages(normalize=True)
Angiogenesis = avgs['Angiogenesis']
Proliferation = avgs['Proliferation']
Apoptosis = avgs['Apoptosis']
Differentiation = avgs['Differentiation']
# Append the average Data to the data set
d[0].append(Apoptosis[0])
d[0].append(Proliferation[0])
d[0].append(Angiogenesis[0])
d[0].append(Differentiation[0])
# header names for pandas dataframe
headers = ['Index', 'CycleLength', 'CycleFingerprint', 'FirstState', 'LastState',\
'Avg_Apoptosis', 'Avg_Proliferation', 'Avg_Angiogenesis', 'Avg_Differentiation']
# convert information to a pandas dataframe
df = pd.DataFrame(d)
df.columns = headers
print
# Export data to csv
with open(csv_out_txt, 'wb') as out:
csv_out = csv.writer(out)
csv_out.writerow(headers)
for row in d:
csv_out.writerow(row)
return df
else:
return 0
def hybrid_f(delta, vegfr, icd, jagged, notch):
if delta == 1 and vegfr == 1 and icd == 1 and jagged == 1 and notch == 1:
return 1
else:
return 0
def other(tip, hybrid, stalk):
if tip == 0 and hybrid == 0 and stalk == 0:
return 1
else:
return 0
coll = util.Collector()
flag = True
N = 10
sim = int(30)
t0 = 0
choices_list = ['cis_delta', 'cis_jagged', 'trans_delta', 'trans_jagged']
#while flag == True:
d_ss = []
j_ss = []
i_ss = []
n_ss = []
vr_ss = []
v_ss = []
d_ss_j = []
def BoolMod(timecourse, booldata, str_mode):
coll = util.Collector()
model = Model(text=booldata, mode=str_mode)
initializer = state.all_initial_states(model.nodes, limit=None)
# the data is the inital data, the func is the initializer
n = 0
for data, initfunc in initializer:
# shows the initial values
print((n) / float(32768)) * 100, "% done."
n = n + 1
model.initialize(missing=initfunc)
model.iterate(steps=timecourse)
# takes all nodes
nodes = model.nodes
coll.collect(states=model.states, nodes=nodes)
# --------------- Detect Cycles ------------------#
print model.report_cycles()
# Return results
avgs = coll.get_averages(normalize=True)
data = pd.DataFrame(avgs)
pd.DataFrame.to_csv(data, "test.csv")
print avgs
print model.fp()
# ------------- Retrieve the Data -------------#
# 6-gene input signature
#ALK = avgs.get('ALK')
#MDK = avgs.get('MDK')
#TrkA = avgs.get('TrkA')
#NGF = avgs.get('NGF')
#TrkB = avgs.get('TrkB')
#BDNF = avgs.get('BDNF')
# Model outcome states
Differentiation = avgs.get('Differentiation')
Apoptosis = avgs.get('Apoptosis')
Proliferation = avgs.get('Proliferation')
Angiogenesis = avgs.get('Angiogenesis')
# Nodes at Issue
#DNADamage = avgs.get('DNADamage')
#p53 = avgs.get('p53')
# Other Nodes
#MDM2 = avgs.get('MDM2')
#MAPK = avgs.get('MAPK')
#p27 = avgs.get('p27')
#FoxO = avgs.get('FoxO')
#AKT = avgs.get('AKT')
#Ras = avgs.get('Ras')
#MYCN = avgs.get('MYCN')
#MTOR = avgs.get('MTOR')
#IP3 = avgs.get('IP3')
### Time axis (x)
t = range(0, timecourse + 1)
# Create plots with pre-defined labels. Try to make this a for loop
fig, ax = plt.subplots()
ax.plot(t, Differentiation, label='Differentiation')
ax.plot(t, Apoptosis, label='Apoptosis')
ax.plot(t, Angiogenesis, label='Angiogenesis')
ax.plot(t, Proliferation, label='Proliferation')
# ax.plot(t, TrkA, label='TrkA')
# ax.plot(t, TrkB, label = 'TrkB')
# ax.plot(t, MYCN, label = 'MYCN')
# ax.plot(t, NGF, label = 'NGF')
# ax.plot(t, MDK, label = 'MDK')
# ax.plot(t, ALK, label = 'ALK')
# ax.plot(t, Ras, label = 'Ras')
# x.plot(t, AKT, label = 'AKT')
# ax.plot(t, FoxO, label = 'FoxO')
# ax.plot(t, p27, label = 'P27')
# ax.plot(t, p53, label = 'P53')
# Legends
legend = ax.legend(loc=0, shadow=True, fontsize='medium')
plt.xlabel('Iterations')
plt.ylabel('On Proportion')
plt.title("Asynchronous Updating Model")
# beautify
legend.get_frame().set_facecolor('#C0C0C0')
# View Plot
plt.show()
return avgs
def all_ss_model_w_fix(str_file, str_mode, timecourse, csv_out_txt, geneon=[], geneoff=[], dumpevery=1000,\
nodes_for_averages=['Apoptosis', 'Proliferation', 'Angiogenesis', 'Differentiation']):
'''
A function to generate a list of all possible starting states of a model. Note that this function is a
modification of the all_ss_model() function and allows for specific nodes to be fixed on or off.
str_file: as a string, write the name of the file containing the rules for the boolean model
str_mode: enter the mode of model that is going to be used, ie sync or async
numnodes: the number of nodes in the model
:return:
A list of dictionaries with all possible starting states of the network.
'''
def dumper():
'''
will dump the data into a CSV file of name csv_out_txt
:return: none
'''
with open(csv_out_txt, 'a') as csvfile:
datadumper = csv.writer(csvfile, lineterminator='\n')
for row in d:
datadumper.writerow(row)
return
# header names for pandas dataframe and CSV data dump file
headers = ['Index', 'CycleLength', 'CycleFingerprint', 'FirstState', 'LastState', str(nodes_for_averages[0]),\
str(nodes_for_averages[1]), str(nodes_for_averages[2]), str(nodes_for_averages[3])]
# Init a CSV to contain the data generated over the course of the run
with open(csv_out_txt, 'wb') as out:
csv_out = csv.writer(out)
csv_out.writerow(headers)
Bool1 = file(str_file).read()
# Generate a new version of the model that allows the genes to be fixed on or off by removing updating rules for
# them. This will not override the initialized value however, and that must be updated to be assigned on or off
# separately.
on = geneon
off = geneoff
Bool2 = tokenizer.modify_states(Bool1, on, off)
model = Model(text=Bool2, mode=str_mode)
initializer = state.all_initial_states(model.nodes, limit=None)
# Utilized in the for loops for the loading bar
load_status_divisor = len(model.nodes) - len(geneoff) - len(geneon)
# The BooleanNet Data Collector. Here it is implemented to gather data on the states of the nodes in the model.
coll = util.Collector()
# Wiley Stoeber. 5/8/18. Create a modified version of the initializer that will pass over initial states that
# contradict the gene set mode
initializer_new = []
if geneoff != [] or geneon != []:
d = []
p = 0
n = 0
for data_init in initializer:
data = data_init[0]
for i in range(len(geneoff)):
if data[str(geneoff[i])]:
initializer_new.append(data_init)
for i in range(len(geneon)):
if data[str(geneon[i])]:
initializer_new.append(data_init)
for data, initfunc in initializer_new:
# Fixes genes on or off (True or False) at their starting state.
for i in range(len(geneoff)):
data.update({str(geneoff[i]): False})
for i in range(len(geneon)):
data.update({str(geneon[i]): True})
# Initialize the model with the given pre-computed initial conditions stored in the data variable.
# for a given model with Z nodes, there are 2 to the power of Z starting states.
model.initialize(defaults=data)
model.iterate(steps=timecourse)
e = model.detect_cycles()
nodes = nodes_for_averages
d.append(list(model.detect_cycles()))
d[p].append(model.fp())
d[p].append(model.first)
d[p].append(model.last)
detect_states = 0 - e[1]
coll.collect(states=model.states[detect_states:], nodes=nodes)
# Console output for debugging and progress tracking
print 'The fingerprint is', d[p][2]
print 'The cycle length is', d[p][1]
prc = ((n) / float(pow(2, load_status_divisor))) * 100
print '%.2f' % prc + "% done."
print '\n'
# Iterate the model
n += 1
p += 1
if p == dumpevery:
dumper()
p = 0
d = []
dumper()
d = []
else:
d = []
p = 0
n = 0
for data, initfunc in initializer:
# Fixes genes on or off (True or False) at their starting state.
for i in range(len(geneoff)):
data.update({str(geneoff[i]): False})
for i in range(len(geneon)):
data.update({str(geneon[i]): True})
# Initialize the model with the given pre-computed initial conditions stored in the data variable.
# for a given model with Z nodes, there are 2 to the power of Z starting states.
model.initialize(defaults=data)
model.iterate(steps=timecourse)
e = model.detect_cycles()
nodes = nodes_for_averages
d.append(list(model.detect_cycles()))
d[p].append(model.fp())
d[p].append(model.first)
d[p].append(model.last)
detect_states = 0 - e[1]
coll.collect(states=model.states[detect_states:], nodes=nodes)
# Console output for debugging and progress tracking
print 'The fingerprint is', d[p][2]
print 'The cycle length is', d[p][1]
prc = ((n) / float(pow(2, load_status_divisor))) * 100
print '%.2f' % prc + "% done."
print '\n'
# Iterate the model
n += 1
p += 1
if p == dumpevery:
dumper()
p = 0
d = []
dumper()
d = []
# Generate a pandas dataframe of the dump file
df = pd.read_csv(csv_out_txt)
# Add the avg on state of the nodes specified by the user. They will output to new columns in row 1 of the data
if nodes_for_averages != []:
avgs = coll.get_averages(normalize=True)
a1 = avgs[nodes_for_averages[0]]
b1 = avgs[nodes_for_averages[1]]
c1 = avgs[nodes_for_averages[2]]
d1 = avgs[nodes_for_averages[3]]
# Set the averages values in the dataframe.
df.set_value(0, 'Apoptosis', a1[0])
df.set_value(0, 'Proliferation', b1[0])
df.set_value(0, 'Differentiation', d1[0])
df.set_value(0, 'Angiogenesis', c1[0])
df.to_csv(csv_out_txt)
return df
def BoolModPlot(timecourse, samples, booldata, str_mode):
coll = util.Collector()
for i in range(samples):
model = Model(text=booldata, mode=str_mode)
model.initialize()
model.iterate(steps=timecourse)
print model.states
# takes all nodes
nodes = model.nodes
coll.collect(states=model.states, nodes=nodes)
# --------------- Detect Cycles ------------------#
print model.report_cycles()
# Return results
avgs = coll.get_averages(normalize=True)
data = pd.DataFrame(avgs)
pd.DataFrame.to_csv(data, "test.csv")
# ------------- Retrieve the Data -------------#
# 6-gene input signature
ALK = avgs.get('ALK')
MDK = avgs.get('MDK')
TrkA = avgs.get('TrkA')
NGF = avgs.get('NGF')
TrkB = avgs.get('TrkB')
BDNF = avgs.get('BDNF')
# Model outcome states
Differentiation = avgs.get('Differentiation')
Apoptosis = avgs.get('Apoptosis')
Proliferation = avgs.get('Proliferation')
Angiogenesis = avgs.get('Angiogenesis')
# Nodes at Issue
DNADamage = avgs.get('DNADamage')
p53 = avgs.get('p53')
# Other Nodes
MDM2 = avgs.get('MDM2')
MAPK = avgs.get('MAPK')
p27 = avgs.get('p27')
FoxO = avgs.get('FoxO')
AKT = avgs.get('AKT')
Ras = avgs.get('Ras')
MYCN = avgs.get('MYCN')
MTOR = avgs.get('MTOR')
IP3 = avgs.get('IP3')
### Time axis (x)
t = range(0, timecourse + 1)
# Create plots with pre-defined labels. Try to make this a for loop
fig, ax = plt.subplots()
ax.plot(t, Differentiation, label='Differentiation')
ax.plot(t, Apoptosis, label='Apoptosis')
ax.plot(t, Angiogenesis, label='Angiogenesis')
ax.plot(t, Proliferation, label='Proliferation')
# ax.plot(t, TrkA, label='TrkA')
# ax.plot(t, TrkB, label = 'TrkB')
# ax.plot(t, MYCN, label = 'MYCN')
# ax.plot(t, NGF, label = 'NGF')
# ax.plot(t, MDK, label = 'MDK')
# ax.plot(t, ALK, label = 'ALK')
# ax.plot(t, Ras, label = 'Ras')
# ax.plot(t, AKT, label = 'AKT')
# ax.plot(t, FoxO, label = 'FoxO')
# ax.plot(t, p27, label = 'P27')
# ax.plot(t, p53, label = 'P53')
# Legends
legend = ax.legend(loc=0, shadow=True, fontsize='medium')
plt.xlabel('Iterations')
plt.ylabel('On Proportion')
plt.title("Asynchronous Updating Model")
# beautify
legend.get_frame().set_facecolor('#C0C0C0')
# View Plot
plt.show()
return avgs
