def execute(output):
sim = pt.Model(cell_volume=8e-16)
sim.seed(34)
sim.add_polymerase(name="rnapol", copy_number=10, speed=40, footprint=10)
sim.add_ribosome(copy_number=100, speed=30, footprint=10)
plasmid = pt.Genome(name="plasmid", length=605)
plasmid.add_promoter(name="p1", start=1, stop=10,
interactions={"rnapol": 2e8})
plasmid.add_terminator(name="t1", start=604, stop=605,
efficiency={"rnapol": 1.0})
plasmid.add_gene(name="rnapol", start=26, stop=225,
rbs_start=(26 - 15), rbs_stop=26, rbs_strength=1e7)
plasmid.add_gene(name="proteinX", start=241, stop=280,
rbs_start=(241 - 15), rbs_stop=241, rbs_strength=1e7)
plasmid.add_gene(name="proteinY", start=296, stop=595,
rbs_start=(296 - 15), rbs_stop=296, rbs_strength=1e7)
plasmid.add_weights([1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25,
0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0])
sim.register_genome(plasmid)
sim.simulate(time_limit=60, time_step=1, output=output + "_counts.tsv")
def test_overload(self):
plasmid = pt.Genome(name="T7",
length=305,
transcript_degradation_rate=1e-2,
transcript_degradation_rate_ext=1e-2,
rnase_footprint=9,
rnase_speed=20)
# Original method
plasmid.add_rnase_site(start=100, stop=110)
plasmid = pt.Genome(name="T7",
length=305,
transcript_degradation_rate_ext=1e-2,
rnase_footprint=9,
rnase_speed=20)
# alternate method that takes a rnase binding affinity specific to
# this site
plasmid.add_rnase_site(name="R6.5", start=220, stop=230, rate=5e-3)
def test_site_names_error_handling(self):
# this time don't set transcript_degredation_rate
plasmid = pt.Genome(name="T7",
length=305,
transcript_degradation_rate_ext=1e-2,
rnase_footprint=9,
rnase_speed=20)
plasmid.add_rnase_site(name="R1", start=280, stop=290, rate=4e-3)
# rnase binding site names must be unique
with self.assertRaises(RuntimeError):
plasmid.add_rnase_site(name="R1", start=220, stop=230, rate=5e-3)
def test_rate_error_handling(self):
plasmid = pt.Genome(name="T7",
length=305,
transcript_degradation_rate=1e-2,
transcript_degradation_rate_ext=1e-2,
rnase_footprint=9,
rnase_speed=20)
# Shouldn't be able to specify a unique binding rate constant if
# transcript_degredation_rate is set
with self.assertRaises(RuntimeError):
plasmid.add_rnase_site(name="R6.5", start=220, stop=230, rate=5e-3)
def pt_call(output_dir, genome_tracker_new, max_time):
"""
pinetree python interface containing all the information needed to conduct a simulation.
Input(s):
output_dir is a string containing information of the path to the directory in which all the saved files are stored by the program.
genome_tracker_new is the dataframe containing the most recently edited genomic data.
max_time is the amount of time for the infection cycle that pinetree is simulating.
Output(s):
Saves file containing transcript abundances data over time.
"""
sim = pt.Model(cell_volume=8e-16)
sim.seed(random.randint(0, 10e6))
sim.add_polymerase(name="rnapol", copy_number=4, speed=40, footprint=35)
sim.add_ribosome(copy_number=100, speed=30, footprint=30)
plasmid = pt.Genome(name="plasmid", length=genome_tracker_new['length_of_genome'],
transcript_degradation_rate_ext=1e-3,
rnase_speed=20,
rnase_footprint=10)
#Promoters
for i in range(genome_tracker_new['num_genes']):
if genome_tracker_new['promoter_{}'.format(i)]['start'] > 0:
plasmid.add_promoter(name="p{}".format(i), start=genome_tracker_new['promoter_{}'.format(i)]['start'], stop=genome_tracker_new['promoter_{}'.format(i)]['stop'],
interactions={"rnapol": genome_tracker_new['promoter_{}'.format(i)]['current_strength']})
#RNases
for i in range(genome_tracker_new['num_genes']):
if genome_tracker_new['rnase_{}'.format(i)]['start'] > 0:
plasmid.add_rnase_site(name='r{}'.format(i), start=genome_tracker_new['rnase_{}'.format(i)]['start'], stop=genome_tracker_new['rnase_{}'.format(i)]['stop'], rate=genome_tracker_new['rnase_{}'.format(i)]['current_strength'])
#Terminators
for i in range(1, genome_tracker_new['num_genes']+1):
if genome_tracker_new['terminator_{}'.format(i)]['start'] > 0:
plasmid.add_terminator(name="t{}".format(i), start=genome_tracker_new['terminator_{}'.format(i)]['start'], stop=genome_tracker_new['terminator_{}'.format(i)]['stop'],
efficiency={"rnapol": genome_tracker_new['terminator_{}'.format(i)]['current_strength']})
#Genes
for i in range(1, genome_tracker_new['num_genes']+1):
if genome_tracker_new['gene_{}'.format(i)]['start'] > 0:
plasmid.add_gene(name="protein{}".format(i), start=genome_tracker_new['gene_{}'.format(i)]['start'], stop=genome_tracker_new['gene_{}'.format(i)]['stop'],
rbs_start=(genome_tracker_new['gene_{}'.format(i)]['start']-30), rbs_stop=genome_tracker_new['gene_{}'.format(i)]['start']-1, rbs_strength=1e7)
#Run pinetree simulation
sim.register_genome(plasmid)
supress = SupressOutput()
with supress:
sim.simulate(time_limit=max_time+1, time_step=1, output=output_dir+'expression_pattern.tsv')
return
def execute(output):
sim = pt.Model(cell_volume=8e-16)
sim.seed(34)
sim.add_polymerase(name="rnapol", copy_number=10, speed=30, footprint=10)
sim.add_ribosome(copy_number=100,
speed=20, footprint=10)
plasmid = pt.Genome(name="T7", length=305,
transcript_degradation_rate=1e-2,
transcript_degradation_rate_ext=1e-2,
rnase_footprint=9,
rnase_speed=20)
# plasmid = pt.Genome(name="T7", length=305)
plasmid.add_promoter(name="phi1", start=1, stop=10,
interactions={"rnapol": 2e8})
plasmid.add_terminator(name="t1", start=304, stop=305,
efficiency={"rnapol": 1.0})
plasmid.add_gene(name="proteinX", start=30, stop=99,
rbs_start=(30 - 10), rbs_stop=30, rbs_strength=1e7)
# plasmid.add_promoter(name="phi2", start=100, stop=109,
# interactions={"rnapol": 2e8})
# plasmid.add_terminator(name="t1", start=98, stop=99,
# efficiency={"rnapol": 1.0})
# plasmid.add_rnase_site(100, 110)
plasmid.add_gene(name="proteinY", start=120, stop=199,
rbs_start=(120 - 10), rbs_stop=120, rbs_strength=1e7)
# plasmid.add_promoter(name="phi3", start=200, stop=209,
# interactions={"rnapol": 2e8})
plasmid.add_gene(name="proteinZ", start=220, stop=300,
rbs_start=(220 - 10), rbs_stop=220, rbs_strength=1e7)
sim.register_genome(plasmid)
sim.simulate(time_limit=500, time_step=1, output=output + "counts.tsv")
def phage_model(input,
output=None,
time=1500,
verbose=True,
seed=None,
multiplicity=1,
use_rnases=False):
if (seed != None) and (0 > seed > 2147483647):
raise ValueError(
f"Seed must be between 0 and 2147483647. You used '{seed}'.")
sim = pt.Model(cell_volume=CELL_VOLUME)
if not output:
output = ".".join(input.split(".")[:-1])
# Make the directory for output if it doesnt exist
output_dir = output.replace("\\", "/")
output_dir = "/".join(output_dir.split("/")[:-1])
if output_dir != '' and not os.path.exists(output_dir):
os.makedirs(output_dir)
# Log relevant information
if output[-1] == "/" or output[-1] == ".":
log_output = f"{output}pinetree.log"
else:
log_output = f"{output}.log"
logger = Logger(log_output=f"{log_output}", verbose=verbose)
# Use just the first record
all_records = list(SeqIO.parse(input, "genbank"))
if len(all_records) > 1:
logger.normal("Ignored extra sequence records in input file.")
record = all_records[0]
genome_length = len(record.seq)
start_time = datetime.datetime.utcnow()
logger.normal("[Pinetree] Pinetree T7 Genome Simulation")
logger.normal("barricklab/igem2020 Fork")
# Try and find a git repo and log its last commit
if os.path.exists(".git/refs/heads/master"):
git_master_path = ".git/refs/heads/master"
elif os.path.exists("../.git/refs/heads/master"):
git_master_path = "../.git/refs/heads/master"
else:
git_master_path = ""
if git_master_path:
with open(git_master_path, 'r') as file:
commit_hash = file.readline().strip()
logger.normal(f"Last commit: {commit_hash}")
logger.normal(f"Script and simulation started at {start_time} UTC")
# --- Feature Acquisition and validation VVV
promoters = Promoters()
feature_dict = {}
for i, feature in enumerate(record.features): # Accuasition
start = feature.location.start.position + 1
stop = feature.location.end.position
name = ''
feature_type = ''
interactions = None
skip = False
source_feature = feature
rate = 0
if 'name' in feature.qualifiers:
name = feature.qualifiers["name"][0]
elif "note" in feature.qualifiers:
name = feature.qualifiers["note"][0]
if feature.type == "regulatory":
if "promoter" in feature.qualifiers["regulatory_class"]:
length = stop - start
if length < 35:
start = start - 35
interactions = promoters.get_interaction(name)
feature_type = "promoter"
if "terminator" in feature.qualifiers["regulatory_class"]:
interactions = get_terminator_interactions(name)
feature_type = "terminator"
elif feature.type == "CDS":
feature_type = "cds"
elif feature.type == "misc_structure":
feature_type = "misc"
if "rnase" in name.lower():
feature_type = "rnase_site"
for site_name in RNAse_Table.keys():
if site_name == name.split(" ")[-1] or site_name == name:
rate = RNAse_Table[site_name]
if rate == 0:
skip = True
else:
feature_type = None
if feature_type:
feature_dict[i] = {
"start": start,
"stop": stop,
"name": name,
"type": feature_type,
"interactions": interactions,
"skip": skip,
"source_feature": source_feature,
"rate": rate
}
# TODO: Add more feature validation
if use_rnases == False:
logger.normal(
"Not considering RNase activity (use flag -r to consider)")
else:
logger.normal(f"Considering RNase activity.")
for feature in feature_dict.items(): # Validation
feature = feature[1]
if feature['skip']:
continue
if feature['name'] in IGNORE_REGULATORY or feature[
'name'] in IGNORE_CDS:
feature['skip'] = True
logger.log(
f"Ignored feature {feature['name']} ({feature['start']} - {feature['stop']})"
)
continue
if 'pseudo' in feature['source_feature'].qualifiers.keys():
logger.warn(
f"Found {feature['name']} with flag 'pseudo'. Ignoring.")
feature['skip'] = True
continue
if feature['stop'] - feature['start'] < 50 and feature['type'] in [
'gene', 'cds'
]:
logger.warn(
f"Found {feature['type'], feature['name']} that is tiny! ({feature['start']} - {feature['stop']})"
)
if feature['type'] == "rnase_site" and use_rnases == False:
feature['skip'] = True
continue
if feature['type'] == "rnase_site" and feature['rate'] == 0:
logger.log(
f"{feature['name']} has no explicit binding rate. Defaulting.")
feature['rate'] = RNase_III["rate"]
# -- Feature Acquisition Validation ^^^
# -- Set up masks
mask_interactions = [
"gp1", "gp1+gp3.5", "ecolipol", "ecolipol-p", "ecolipol-2",
"ecolipol-2-p"
]
logger.normal("Implemented masks and weighting")
# -- Set up masks
# -- Add Features to Sim VVV
phage_genomes = {}
for infection in range(0, multiplicity):
weights = [0.0] * len(record.seq)
if use_rnases:
phage_genomes[infection] = pt.Genome(
name=f"phage_{infection}",
length=genome_length,
transcript_degradation_rate_ext=RNase_E['rate'],
rnase_speed=RNase_E['speed'],
rnase_footprint=RNase_E['footprint'])
else:
phage_genomes[infection] = pt.Genome(name=f"phage_{infection}",
length=genome_length)
output_feature_dict = dict()
for feature in feature_dict.items():
feature_contents = feature[1]
if feature_contents['skip']:
continue
elif feature_contents['type'] == "promoter":
phage_genomes[infection].add_promoter(
feature_contents['name'], feature_contents['start'],
feature_contents['stop'], feature_contents['interactions'])
logger.log(
f"Added promoter feature: {feature_contents['name']}, Start: {feature_contents['start']}, Stop: {feature_contents['stop']}"
)
output_feature_dict[copy.copy(feature[0])] = copy.deepcopy(
feature[1])
elif feature_contents['type'] == "terminator":
phage_genomes[infection].add_terminator(
feature_contents['name'], feature_contents['start'],
feature_contents['stop'], feature_contents['interactions'])
logger.log(
f"Added terminator feature: {feature_contents['name']}, Start: {feature_contents['start']}, Stop: {feature_contents['stop']}"
)
output_feature_dict[copy.copy(feature[0])] = copy.deepcopy(
feature[1])
elif feature_contents['type'] == "cds":
phage_genomes[infection].add_gene(
name=feature_contents['name'],
start=feature_contents['start'],
stop=feature_contents['stop'],
rbs_start=feature_contents['start'] - 30,
rbs_stop=feature_contents['start'],
rbs_strength=1e7)
weights = compute_cds_weights(
record, feature_contents['source_feature'], 1.0, weights)
logger.log(
f"Added CDS feature: {feature_contents['name']}, Start: {feature_contents['start']}, Stop: {feature_contents['stop']}"
)
output_feature_dict[copy.copy(feature[0])] = copy.deepcopy(
feature[1])
elif feature_contents['type'] == "rnase_site":
phage_genomes[infection].add_rnase_site(
name=feature_contents['name'],
start=feature_contents['start'],
stop=feature_contents['stop'] + 10,
rate=feature_contents['rate'])
logger.log(
f"Added RNase site: {feature_contents['name']}, Start: {feature_contents['start']}, Stop: {feature_contents['stop']}"
)
output_feature_dict[copy.copy(feature[0])] = copy.deepcopy(
feature[1])
else:
continue
phage_genomes[infection].add_mask(500, mask_interactions)
norm_weights = normalize_weights(weights)
phage_genomes[infection].add_weights(norm_weights)
sim.register_genome(phage_genomes[infection])
logger.log(f"Registered phage genome #{infection+1}")
# -- Add Featues to Sim ^^^
# -- Output Features to CSV VVVVV
out_columns = ['name', 'type', 'start', 'end', 'strength']
out_data = []
for feature in feature_dict.items():
feature_contents = feature[1]
if feature_contents['skip'] == True:
continue
feature_contents['strength'] = None
if feature_contents['type'] == "promoter":
promoter_interaction_result = promoters.get_interaction(
feature_contents['name'])
if 'ecolipol' in promoter_interaction_result.keys():
feature_contents['strength'] = promoter_interaction_result[
'ecolipol']
elif 'gp1' in promoter_interaction_result.keys():
feature_contents['strength'] = promoter_interaction_result[
'gp1']
else:
feature_contents['strength'] = 0
elif feature_contents['type'] == "rnase_site":
feature_contents['strength'] = feature_contents['rate']
out_data.append({
'name': feature_contents['name'],
'type': feature_contents['type'],
'start': feature_contents['start'],
'end': feature_contents['stop'],
'strength': feature_contents['strength']
})
if output[-1] == "/" or output[-1] == ".":
out_features_filename = f"{output}features.csv"
else:
out_features_filename = f"{output}.features.csv"
with open(out_features_filename, 'w') as csv_file_object:
writer = csv.DictWriter(csv_file_object, fieldnames=out_columns)
writer.writeheader()
for contents in out_data:
writer.writerow(contents)
# -- Output Features to CSV ^^^^^
logger.normal("Registered genome features")
mask_interactions = [
"gp1", "gp1+gp3.5", "ecolipol", "ecolipol-p", "ecolipol-2",
"ecolipol-2-p"
]
sim.add_polymerase("gp1", 35, 230, 0)
sim.add_polymerase("gp1+gp3.5", 35, 230, 0)
sim.add_polymerase("ecolipol", 35, 45, 0)
sim.add_polymerase("ecolipol-p", 35, 45, 0)
sim.add_polymerase("ecolipol-2", 35, 45, 0)
sim.add_polymerase("ecolipol-2-p", 35, 45, 0)
sim.add_ribosome(30, 30, 0)
sim.add_species("bound_ribosome", 10000)
sim.add_species("bound_ecolipol", 1800)
sim.add_species("bound_ecolipol_p", 0)
sim.add_species("ecoli_genome", 0)
sim.add_species("ecoli_transcript", 0)
sim.add_reaction(1e6, ["ecoli_transcript", "__ribosome"],
["bound_ribosome"])
sim.add_reaction(0.04, ["bound_ribosome"],
["__ribosome", "ecoli_transcript"])
sim.add_reaction(0.001925, ["ecoli_transcript"], ["degraded_transcript"])
sim.add_reaction(1e7, ["ecolipol", "ecoli_genome"], ["bound_ecolipol"])
sim.add_reaction(0.3e7, ["ecolipol-p", "ecoli_genome"],
["bound_ecolipol_p"])
sim.add_reaction(0.04, ["bound_ecolipol"],
["ecolipol", "ecoli_genome", "ecoli_transcript"])
sim.add_reaction(0.04, ["bound_ecolipol_p"],
["ecolipol-p", "ecoli_genome", "ecoli_transcript"])
sim.add_reaction(3.8e7, ["gp0.7", "ecolipol"], ["ecolipol-p", "gp0.7"])
sim.add_reaction(3.8e7, ["gp0.7", "ecolipol+gp2"],
["ecolipol+gp2-p", "gp0.7"])
sim.add_reaction(3.8e7, ["gp2", "ecolipol"], ["ecolipol+gp2"])
sim.add_reaction(3.8e7, ["gp2", "ecolipol-p"], ["ecolipol+gp2-p"])
sim.add_reaction(1.1, ["ecolipol+gp2-p"], ["gp2", "ecolipol-p"])
sim.add_reaction(1.1, ["ecolipol+gp2"], ["gp2", "ecolipol"])
logger.normal("Registered reactions")
logger.normal("Running simulation")
if not seed:
seed = random.randint(0, 2147483647)
sim.seed(seed)
logger.normal(f"Random seed was set to {seed}")
if output[-1] == "/" or output[-1] == ".":
sim_output = f"{output}phage.counts.tsv"
else:
sim_output = f"{output}.counts.tsv"
# -- Running the actual sim. VVVV
# Note: Multiprocessing necessary for working keyboard interrupts.
try:
sim_process = multiprocessing.Process(target=sim.simulate,
kwargs={
'time_limit': time,
'time_step': 5,
'output': sim_output
})
sim_process.start()
sim_process.join()
except KeyboardInterrupt:
sim_process.terminate()
with open(sim_output, 'r') as outfile:
for line in outfile:
pass
last_file_line = line
interrupt_time = str(last_file_line).split("\t")[0]
logger.warn(
f'Received keyboard interruption. Simulation reached time {interrupt_time}'
)
finish_time = datetime.datetime.utcnow()
run_time = (finish_time - start_time).total_seconds()
logger.normal(f"Simulation interrupted after {run_time / 60} minutes.")
exit(0)
except TypeError:
logger.warn(
"There was a problem with multiprocessing. Keyboard Interrupts won't work, but the simulation should still run."
)
sim.simulate(time_limit=time, time_step=5, output=sim_output)
finish_time = datetime.datetime.utcnow()
run_time = (finish_time - start_time).total_seconds()
logger.normal(f"Simulation completed in {run_time/60} minutes.")
def main():
sim = pt.Model(cell_volume=CELL_VOLUME)
# Download T7 wild-type genbank records
Entrez.email = "*****@*****.**"
handle = Entrez.efetch(db="nuccore",
id=["NC_001604"],
rettype="gb",
retmode="text")
record = SeqIO.read(handle, "genbank")
genome_length = len(record.seq)
phage = pt.Genome(name="phage", length=genome_length)
for feature in record.features:
weights = [1.0] * len(record.seq)
# Convert to inclusive genomic coordinates
start = feature.location.start.position + 1
stop = feature.location.end.position
name = ''
if "note" in feature.qualifiers:
name = feature.qualifiers["note"][0]
# Grab promoters and terminators
if feature.type == "regulatory":
if name in IGNORE_REGULATORY:
continue
# Construct promoter
if "promoter" in feature.qualifiers["regulatory_class"]:
length = stop - start
if length < 35:
start = start - 35
interactions = get_promoter_interactions(name)
phage.add_promoter(name, start, stop, interactions)
# Construct terminator params
if "terminator" in feature.qualifiers["regulatory_class"]:
interactions = get_terminator_interactions(name)
phage.add_terminator(name, start, stop, interactions)
# Grab genes/CDSes
if feature.type == "gene":
if name in IGNORE_GENES:
continue
if name in RELABEL_GENES:
name = RELABEL_GENES[name]
# Construct CDS parameters for this gene
# print(name)
phage.add_gene(name=name,
start=start,
stop=stop,
rbs_start=start - 30,
rbs_stop=start,
rbs_strength=1e7)
# Recode gene 10A
if name == "gene 10A":
gene10_start = start
gene10_stop = stop
weights[gene10_start:gene10_stop] = [0.2] * (gene10_stop - gene10_start)
mask_interactions = [
"rnapol-1", "rnapol-3.5", "ecolipol", "ecolipol-p", "ecolipol-2",
"ecolipol-2-p"
]
phage.add_mask(500, mask_interactions)
phage.add_weights(weights)
sim.register_genome(phage)
sim.add_polymerase("rnapol-1", 35, 230, 0)
sim.add_polymerase("rnapol-3.5", 35, 230, 0)
sim.add_polymerase("ecolipol", 35, 45, 0)
sim.add_polymerase("ecolipol-p", 35, 45, 0)
sim.add_polymerase("ecolipol-2", 35, 45, 0)
sim.add_polymerase("ecolipol-2-p", 35, 45, 0)
sim.add_ribosome(30, 30, 0)
sim.add_species("bound_ribosome", 10000)
sim.add_species("bound_ecolipol", 1800)
sim.add_species("bound_ecolipol_p", 0)
sim.add_species("ecoli_genome", 0)
sim.add_species("ecoli_transcript", 0)
sim.add_reaction(1e6, ["ecoli_transcript", "__ribosome"],
["bound_ribosome"])
sim.add_reaction(0.04, ["bound_ribosome"],
["__ribosome", "ecoli_transcript"])
sim.add_reaction(0.001925, ["ecoli_transcript"], ["degraded_transcript"])
sim.add_reaction(1e7, ["ecolipol", "ecoli_genome"], ["bound_ecolipol"])
sim.add_reaction(0.3e7, ["ecolipol-p", "ecoli_genome"],
["bound_ecolipol_p"])
sim.add_reaction(0.04, ["bound_ecolipol"],
["ecolipol", "ecoli_genome", "ecoli_transcript"])
sim.add_reaction(0.04, ["bound_ecolipol_p"],
["ecolipol-p", "ecoli_genome", "ecoli_transcript"])
sim.add_reaction(3.8e7, ["protein_kinase-0.7", "ecolipol"],
["ecolipol-p", "protein_kinase-0.7"])
sim.add_reaction(3.8e7, ["protein_kinase-0.7", "ecolipol-2"],
["ecolipol-2-p", "protein_kinase-0.7"])
sim.add_reaction(3.8e7, ["gp-2", "ecolipol"], ["ecolipol-2"])
sim.add_reaction(3.8e7, ["gp-2", "ecolipol-p"], ["ecolipol-2-p"])
sim.add_reaction(1.1, ["ecolipol-2-p"], ["gp-2", "ecolipol-p"])
sim.add_reaction(1.1, ["ecolipol-2"], ["gp-2", "ecolipol"])
sim.add_reaction(3.8e9, ["lysozyme-3.5", "rnapol-1"], ["rnapol-3.5"])
sim.add_reaction(3.5, ["rnapol-3.5"], ["lysozyme-3.5", "rnapol-1"])
sim.seed(54)
sim.simulate(time_limit=1200,
time_step=5,
output="phage_model_knockout_recoded.tsv")
# Copy of Ben's three genes simulation setup, for reference
import pinetree as pt
sim = pt.Model(cell_volume=8e-16)
sim.seed(34)
sim.add_polymerase(name="rnapol", copy_number=4, speed=40, footprint=10)
sim.add_ribosome(copy_number=100, speed=30, footprint=10)
plasmid = pt.Genome(name="plasmid", length=450,
# transcript_degradation_rate=1e-2,
transcript_degradation_rate_ext=1e-3,
rnase_speed=20,
rnase_footprint=10)
plasmid.add_promoter(name="p1", start=1, stop=10, interactions={"rnapol": 2e10})
plasmid.add_terminator(name="t1", start=449, stop=450, efficiency={"rnapol": 1.0})
plasmid.add_gene(name="proteinX", start=26, stop=148, rbs_start=(26 - 15), rbs_stop=26, rbs_strength=1e7)
plasmid.add_gene(name="proteinY", start=26 + 150, stop=148 + 150, rbs_start=(26 - 15 + 150), rbs_stop=26 + 150, rbs_strength=1e7)
plasmid.add_promoter(name="p2", start=141 + 150, stop=150 + 150, interactions={"rnapol": 2e10})
plasmid.add_rnase_site(name="r1", start=150 + 150, stop=160 + 150, rate=1e-2)
plasmid.add_gene(name="proteinZ", start=165 + 150, stop=298 + 150, rbs_start=(165 - 15 + 150), rbs_stop=165 + 150, rbs_strength=1e7)
sim.register_genome(plasmid)
sim.simulate(time_limit=240, time_step=1, output="three_genes_rnase.tsv")
def main():
sim = pt.Model(cell_volume=CELL_VOLUME)
record = SeqIO.read("T7_genome.gb", "genbank")
genome_length = len(record.seq)
phage = pt.Genome(name="phage", length=genome_length)
for feature in record.features:
weights = [0.0] * len(record.seq)
# Convert to inclusive genomic coordinates
start = feature.location.start.position + 1
stop = feature.location.end.position
name = ''
if "note" in feature.qualifiers:
name = feature.qualifiers["note"][0]
# Grab promoters and terminators
if feature.type == "regulatory":
if name in IGNORE_REGULATORY:
continue
# Construct promoter
if "promoter" in feature.qualifiers["regulatory_class"]:
length = stop - start
if length < 35:
start = start - 35
interactions = get_promoter_interactions(name)
phage.add_promoter(name, start, stop, interactions)
# Construct terminator params
if "terminator" in feature.qualifiers["regulatory_class"]:
interactions = get_terminator_interactions(name)
phage.add_terminator(name, start, stop, interactions)
# Grab genes/CDSes
if feature.type == "gene":
if name in IGNORE_GENES:
continue
if name in RELABEL_GENES:
name = RELABEL_GENES[name]
# Construct CDS parameters for this gene
phage.add_gene(name=name, start=start, stop=stop,
rbs_start=start - 30, rbs_stop=start, rbs_strength=1e7)
if feature.type == "CDS":
weights = compute_cds_weights(record, feature, 1.0, weights)
mask_interactions = ["rnapol-1", "rnapol-3.5",
"ecolipol", "ecolipol-p", "ecolipol-2", "ecolipol-2-p"]
phage.add_mask(500, mask_interactions)
norm_weights = normalize_weights(weights)
phage.add_weights(norm_weights)
sim.register_genome(phage)
sim.add_polymerase("rnapol-1", 35, 230, 0)
sim.add_polymerase("rnapol-3.5", 35, 230, 0)
sim.add_polymerase("ecolipol", 35, 45, 0)
sim.add_polymerase("ecolipol-p", 35, 45, 0)
sim.add_polymerase("ecolipol-2", 35, 45, 0)
sim.add_polymerase("ecolipol-2-p", 35, 45, 0)
sim.add_ribosome(30, 30, 0)
sim.add_species("bound_ribosome", 10000)
sim.add_species("bound_ecolipol", 1800)
sim.add_species("bound_ecolipol_p", 0)
sim.add_species("ecoli_genome", 0)
sim.add_species("ecoli_transcript", 0)
sim.add_reaction(1e6, ["ecoli_transcript", "__ribosome"], [
"bound_ribosome"])
sim.add_reaction(0.04, ["bound_ribosome"], [
"__ribosome", "ecoli_transcript"])
sim.add_reaction(0.001925, ["ecoli_transcript"], ["degraded_transcript"])
sim.add_reaction(1e7, ["ecolipol", "ecoli_genome"], ["bound_ecolipol"])
sim.add_reaction(
0.3e7, ["ecolipol-p", "ecoli_genome"], ["bound_ecolipol_p"])
sim.add_reaction(0.04, ["bound_ecolipol"], [
"ecolipol", "ecoli_genome", "ecoli_transcript"])
sim.add_reaction(0.04, ["bound_ecolipol_p"], [
"ecolipol-p", "ecoli_genome", "ecoli_transcript"])
sim.add_reaction(3.8e7, ["protein_kinase-0.7", "ecolipol"],
["ecolipol-p", "protein_kinase-0.7"])
sim.add_reaction(3.8e7, ["protein_kinase-0.7", "ecolipol-2"],
["ecolipol-2-p", "protein_kinase-0.7"])
sim.add_reaction(3.8e7, ["gp-2", "ecolipol"], ["ecolipol-2"])
sim.add_reaction(3.8e7, ["gp-2", "ecolipol-p"], ["ecolipol-2-p"])
sim.add_reaction(1.1, ["ecolipol-2-p"], ["gp-2", "ecolipol-p"])
sim.add_reaction(1.1, ["ecolipol-2"], ["gp-2", "ecolipol"])
sim.add_reaction(3.8e9, ["lysozyme-3.5", "rnapol-1"], ["rnapol-3.5"])
sim.add_reaction(3.5, ["rnapol-3.5"], ["lysozyme-3.5", "rnapol-1"])
sim.seed(34)
sim.simulate(time_limit=1500, time_step=5, output="phage_counts.tsv")
def construct_genome(config_file):
"""
Initialize a Genome object from a yaml config file.
"""
data = _load_conf(config_file)
constructor_args = data["genome"]
genomes = []
# if the simulation contains more than one phage, we'll create them all now
for i in range(constructor_args["copy_number"]):
if "transcript_degradation_rate_ext" in constructor_args:
genome = pt.Genome(
name=constructor_args["name"],
length=constructor_args["length"],
transcript_degradation_rate_ext=float(
constructor_args["transcript_degradation_rate_ext"]),
rnase_speed=constructor_args["rnase_speed"],
rnase_footprint=constructor_args["rnase_footprint"])
else:
genome = pt.Genome(name=constructor_args["name"],
length=constructor_args["length"])
## add elements to the genome
if "promoters" in data:
promoters = data["promoters"]
for promoter in promoters:
start = promoter["start"]
stop = promoter["stop"]
length = stop - start
if length < 35:
start = start - 35
genome.add_promoter(name=promoter["name"],
start=start,
stop=stop,
interactions=promoter["interactions"])
if "genes" in data:
genes = data["genes"]
for gene in genes:
start = gene["start"]
genome.add_gene(name=gene["name"],
start=start,
stop=gene["stop"],
rbs_start=start + gene["rbs"],
rbs_stop=start,
rbs_strength=float(gene["rbs_strength"]))
if "terminators" in data:
terminators = data["terminators"]
for terminator in terminators:
genome.add_terminator(name=terminator["name"],
start=terminator["start"],
stop=terminator["stop"],
efficiency=terminator["interactions"])
if "rnase_sites" in data:
rnase_sites = data["rnase_sites"]
for rnase_site in rnase_sites:
genome.add_rnase_site(name=rnase_site["name"],
start=rnase_site["start"],
stop=rnase_site["start"] + 10,
rate=float(rnase_site["rnase_strength"]))
if "mask" in data:
mask = data["mask"]
genome.add_mask(start=mask["start"],
interactions=mask["interactions"])
if "opt_codon_factor" in data:
codon_weights = weights.t7_weights(data["opt_codon_factor"])
genome.add_weights(codon_weights)
genomes.append(genome)
return genomes
