def MehRBS(seq,start):
#Read command line arguments
if start == 0:
start_range = [0, len(seq)]
else:
start_range = [int(start), int(start)+1]
name = "no name"
#Create instance of RBS Calculator
calcObj = RBS_Calculator(seq, start_range, name)
calcObj.calc_dG()
dG_total_list = calcObj.dG_total_list[:]
start_pos_list = calcObj.start_pos_list[:]
kinetic_score_list = calcObj.kinetic_score_list[:]
expr_list = []
for dG in dG_total_list:
expr_list.append(calcObj.K * math.exp(-dG/calcObj.RT_eff))
print len(expr_list)
for (expr,start_pos,ks) in zip(expr_list,start_pos_list,kinetic_score_list):
print start_pos, expr, ks
def MyRBS(sequence, subDNA_frame, subDNA_start, start=0):
""" Recieve sequences and return starting points and relative initiation
frequencies and a kinetic folding parameter. I don't know how to use the
kinetic folding parameter. """
# You can force the calculator to start at a specific start codon
if start == 0:
start_range = [0, len(sequence)]
else:
start_range = [int(start), int(start)+1]
name = "no name"
#Create instance of RBS Calculator
calcObj = RBS_Calculator(sequence, start_range, name)
calcObj.calc_dG()
dG_total_list = calcObj.dG_total_list[:]
start_pos_list = calcObj.start_pos_list[:]
kinetic_score_list = calcObj.kinetic_score_list[:]
expr_list = []
for dG in dG_total_list:
expr_list.append(calcObj.K * math.exp(-dG/calcObj.RT_eff))
returnlist = []
for (expr, RBSstart_pos, ks) in zip(expr_list, start_pos_list, kinetic_score_list):
result_object = Result(RBSstart_pos, expr, ks, subDNA_frame, subDNA_start)
returnlist.append(result_object)
# Return the number of start sites, and a list of start positions, relative
# initiation rates, and the kinetic parameter.
return returnlist
def rbs_calc(self, seq):
os.putenv('NUPACKHOME', '/opt/nupack')
start_range = [0, len(seq)]
name = "no name"
calcObj = RBS_Calculator(seq, start_range, name)
calcObj.calc_dG()
dG_total_list = calcObj.dG_total_list[:]
start_pos_list = calcObj.start_pos_list[:]
kinetic_score_list = calcObj.kinetic_score_list[:]
txt = ""
expr_list = []
for dG in dG_total_list:
expr_list.append(calcObj.K * math.exp(-dG / calcObj.RT_eff))
txt += str(len(expr_list)) + "\n"
for (expr, start_pos, ks) in zip(expr_list, start_pos_list,
kinetic_score_list):
txt += str(start_pos) + " " + str(expr) + " " + str(ks) + "\n"
return txt
def rbs_calc(self, seq):
os.putenv("NUPACKHOME", "/opt/nupack")
start_range = [0, len(seq)]
name = "no name"
calcObj = RBS_Calculator(seq, start_range, name)
calcObj.calc_dG()
dG_total_list = calcObj.dG_total_list[:]
start_pos_list = calcObj.start_pos_list[:]
kinetic_score_list = calcObj.kinetic_score_list[:]
txt = ""
expr_list = []
for dG in dG_total_list:
expr_list.append(calcObj.K * math.exp(-dG / calcObj.RT_eff))
txt += str(len(expr_list)) + "\n"
for (expr, start_pos, ks) in zip(expr_list, start_pos_list, kinetic_score_list):
txt += str(start_pos) + " " + str(expr) + " " + str(ks) + "\n"
return txt
def MyRBS(sequence, start=0):
""" Recieve sequences and return starting points and relative initiation
frequencies and a kinetic folding parameter """
if start == 0:
start_range = [0, len(seq)]
else:
start_range = [int(start), int(start)+1]
name = "no name"
#Create instance of RBS Calculator
calcObj = RBS_Calculator(sequence, start_range, name)
calcObj.calc_dG()
dG_total_list = calcObj.dG_total_list[:]
start_pos_list = calcObj.start_pos_list[:]
kinetic_score_list = calcObj.kinetic_score_list[:]
expr_list = []
for dG in dG_total_list:
expr_list.append(calcObj.K * math.exp(-dG/calcObj.RT_eff))
startsitenr = len(expr_list))
returnlist = []
for (expr,start_pos,ks) in zip(expr_list,start_pos_list,kinetic_score_list):
returnlist.append([start_pos, expr, ks])
return startsitenr, returnlist
def Run_RBS_Calculator(pre_seq,post_seq,RBS,verbose=True):
"""Short cut function to run the RBS Calculator on a pre_sequence, CDS, and RBS."""
if vars().has_key('estimator'): del(estimator)
start_range = [len(pre_seq) + len(RBS) - 2, len(pre_seq) + len(RBS) + 2]
mRNA = pre_seq.upper() + RBS + post_seq.upper()
estimator = RBS_Calculator(mRNA, start_range, "")
estimator.calc_dG()
if verbose: estimator.print_dG()
global num_rbs_calculations
num_rbs_calculations+=1
return estimator
def Run_RBS_Calculator(pre_seq, post_seq, RBS, verbose=True):
"""Short cut function to run the RBS Calculator on a pre_sequence, CDS, and RBS."""
if vars().has_key('estimator'): del (estimator)
start_range = [len(pre_seq) + len(RBS) - 2, len(pre_seq) + len(RBS) + 2]
mRNA = pre_seq.upper() + RBS + post_seq.upper()
estimator = RBS_Calculator(mRNA, start_range, "")
estimator.calc_dG()
if verbose: estimator.print_dG()
global num_rbs_calculations
num_rbs_calculations += 1
return estimator
if len(input_args) == 3:
seq = input_args[1]
start = input_args[2]
elif len(input_args) == 2:
seq = input_args[1]
else:
output = "Usage: " + input_args[0] + " [RNA/DNA Sequence] (start position)" + "\n"
print output
if start == 0:
start_range = [0, len(seq)]
else:
start_range = [int(start), int(start)+1]
name = "no name"
#Create instance of RBS Calculator
calcObj = RBS_Calculator(seq, start_range, name)
calcObj.calc_dG()
dG_total_list = calcObj.dG_total_list[:]
start_pos_list = calcObj.start_pos_list[:]
kinetic_score_list = calcObj.kinetic_score_list[:]
expr_list = []
for dG in dG_total_list:
expr_list.append(calcObj.K * math.exp(-dG/calcObj.RT_eff))
print len(expr_list)
for (expr,start_pos,ks) in zip(expr_list,start_pos_list,kinetic_score_list):
print start_pos, expr, ks
def calc_dG_pre_post_RBS(pre_list,post_list,RBS_list,name_list,output,verbose = True, parameters = {}):
from RBS_Calculator import RBS_Calculator
First = True
for (pre,post,RBS,name) in zip(pre_list,post_list,RBS_list,name_list):
mRNA = pre + RBS + post
start_range = [0, len(mRNA)]
#Create instance of RBS Calculator
test = RBS_Calculator(mRNA, start_range, name)
#Examine kvars dictionary and pull out any options. Assign them to instanced class.
for (key,value) in parameters.items():
if key == "cutoff":
test.cutoff = value
elif key == "start_range":
test.start_range = value
elif key == "rRNA":
test.rRNA = value
elif key == "energy_cutoff":
test.energy_cutoff = value
elif key == "standby_site_length":
test.standby_sitRBSe_length = value
elif key == "dangles":
test.dangles = value
elif key == "export_PDF":
export_PDF = value
test.calc_dG()
if verbose: test.print_dG(test.infinity)
test.save_data(output, First)
if First:
First = False
output.close()
def calc_dG_from_file(handle, output, verbose = True, parameters = {}):
from Bio import SeqIO
from RBS_Calculator import RBS_Calculator
records = SeqIO.parse(handle,"fasta")
First = True
export_PDF = True
#for i in range(30):
# records.next()
for record in records:
mRNA = record.seq.tostring().upper()
#Set any defaults
start_range = [0, len(mRNA)]
name = record.description.split(" ")[0]
#Create instance of RBS Calculator
test = RBS_Calculator(mRNA, start_range, name)
#Examine kvars dictionary and pull out any options. Assign them to instanced class.
for (key,value) in parameters.items():
if key == "cutoff":
test.cutoff = value
elif key == "start_range":
test.start_range = value
elif key == "rRNA":
test.rRNA = value
elif key == "energy_cutoff":
test.energy_cutoff = value
elif key == "standby_site_length":
test.standby_site_length = value
elif key == "dangles":
test.dangles = value
elif key == "export_PDF":
export_PDF = value
test.calc_dG()
test.print_dG(test.infinity,print_expression=verbose)
test.save_data(output, First)
if First:
First = False
if export_PDF:
num_structs = len(test.mRNA_rRNA_uncorrected_structure_list)
for (structure,counter) in zip(test.mRNA_rRNA_uncorrected_structure_list,range(num_structs)):
index = structure["MinStructureID"]
structure.export_PDF(index, name, filename = name + "_rRNA" + "_" + str(counter) + ".pdf", program = "subopt")
num_structs = len(test.mRNA_structure_list)
for (structure,counter) in zip(test.mRNA_structure_list,range(num_structs)):
structure.export_PDF(0, name, filename = name + "_mRNA" + "_" + str(counter) + ".pdf")
output.close()
def calc_dG_pre_post_RBS(pre_list,post_list,RBS_list,name_list,output,verbose = True, parameters = {}):
from RBS_Calculator import RBS_Calculator
First = True
for (pre,post,RBS,name) in zip(pre_list,post_list,RBS_list,name_list):
mRNA = pre + RBS + post
start_range = [0, len(mRNA)]
#Create instance of RBS Calculator
test = RBS_Calculator(mRNA, start_range, name)
#Examine kvars dictionary and pull out any options. Assign them to instanced class.
for (key,value) in parameters.items():
if key == "cutoff":
test.cutoff = value
elif key == "start_range":
test.start_range = value
elif key == "rRNA":
test.rRNA = value
elif key == "energy_cutoff":
test.energy_cutoff = value
elif key == "standby_site_length":
test.standby_sitRBSe_length = value
elif key == "dangles":
test.dangles = value
elif key == "export_PDF":
export_PDF = value
test.calc_dG()
if verbose: test.print_dG(test.infinity)
test.save_data(output, First)
if First:
First = False
output.close()
def calc_dG_from_file(handle, output, verbose = True, parameters = {}):
from Bio import SeqIO
from RBS_Calculator import RBS_Calculator
records = SeqIO.parse(handle,"fasta")
First = True
export_PDF = True
#for i in range(30):
# records.next()
for record in records:
mRNA = record.seq.tostring().upper()
#Set any defaults
start_range = [0, len(mRNA)]
name = record.description.split(" ")[0]
#Create instance of RBS Calculator
test = RBS_Calculator(mRNA, start_range, name)
#Examine kvars dictionary and pull out any options. Assign them to instanced class.
for (key,value) in parameters.items():
if key == "cutoff":
test.cutoff = value
elif key == "start_range":
test.start_range = value
elif key == "rRNA":
test.rRNA = value
elif key == "energy_cutoff":
test.energy_cutoff = value
elif key == "standby_site_length":
test.standby_site_length = value
elif key == "dangles":
test.dangles = value
elif key == "export_PDF":
export_PDF = value
test.calc_dG()
test.print_dG(test.infinity,print_expression=verbose)
test.save_data(output, First)
if First:
First = False
if export_PDF:
num_structs = len(test.mRNA_rRNA_uncorrected_structure_list)
for (structure,counter) in zip(test.mRNA_rRNA_uncorrected_structure_list,range(num_structs)):
index = structure["MinStructureID"]
structure.export_PDF(index, name, filename = name + "_rRNA" + "_" + str(counter) + ".pdf", program = "subopt")
num_structs = len(test.mRNA_structure_list)
for (structure,counter) in zip(test.mRNA_structure_list,range(num_structs)):
structure.export_PDF(0, name, filename = name + "_mRNA" + "_" + str(counter) + ".pdf")
output.close()
start = input_args[2]
elif len(input_args) == 2:
seq = input_args[1]
else:
output = "Usage: " + input_args[
0] + " [RNA/DNA Sequence] (start position)" + "\n"
print output
if start == 0:
start_range = [0, len(seq)]
else:
start_range = [int(start), int(start) + 1]
name = "no name"
#Create instance of RBS Calculator
calcObj = RBS_Calculator(seq, start_range, name)
calcObj.calc_dG()
dG_total_list = calcObj.dG_total_list[:]
start_pos_list = calcObj.start_pos_list[:]
kinetic_score_list = calcObj.kinetic_score_list[:]
expr_list = []
for dG in dG_total_list:
expr_list.append(calcObj.K * math.exp(-dG / calcObj.RT_eff))
print len(expr_list)
for (expr, start_pos, ks) in zip(expr_list, start_pos_list,
kinetic_score_list):
print start_pos, expr, ks
print "Usage: " + sys.argv[0] + " [input CSV]\n"
sys.exit(-1)
input_csv = csv.reader(open(sys.argv[1], "r"))
output_csv = csv.writer(open("result.csv", "w"))
output_csv.writerow(('name', 'sequence', 'start position', 'expression level', 'kinetic score'))
for row in input_csv:
(name, seq, start) = row
if (start == None):
start_range = [0, len(seq)]
else: # the new convension is to count the start position from the end of the sequence
start_range = [int(start)-1, int(start)]
#Create instance of RBS Calculator
calcObj = RBS_Calculator(seq, start_range, name)
calcObj.calc_dG()
dG_total_list = calcObj.dG_total_list[:]
start_pos_list = calcObj.start_pos_list[:]
kinetic_score_list = calcObj.kinetic_score_list[:]
if (len(dG_total_list) > 0):
expr_list = []
for dG in dG_total_list:
expr_list.append(calcObj.K * math.exp(-dG/calcObj.RT_eff))
for (start_pos, expr, ks) in zip(start_pos_list, expr_list, kinetic_score_list):
output_csv.writerow((name, seq, start_pos, expr, ks))
else:
output_csv.writerow((name, seq, "FAIL", "FAIL", "FAIL"))
