def main(args):
paralog = [args.paralog1, args.paralog2]
num_boot = args.bootnum
Force = None
clock = False
alignment_file = './BootStrapSamples/' + '_'.join(paralog) + '/' + '_'.join(paralog) + '_Boot' + str(num_boot) + '.fasta'
save_name = './BootStrapSave/' + '_'.join(paralog) + '/' + '_'.join(paralog) + '_Boot' + str(num_boot) + '_save.txt'
newicktree = './YeastTree.newick'
test = ReCodonGeneconv( newicktree, alignment_file, paralog, Model = 'MG94', Force = None, clock = False, save_name = save_name)
test.get_mle(False, True, 0, 'BFGS')
test.get_individual_summary(summary_path = './BootStrapSummary/' + '_'.join(paralog) + '/', file_name = './BootStrapSummary/' + '_'.join(paralog) + '/' + '_'.join(paralog) + '_Boot' + str(num_boot) + '_summary.txt')
def main(args):
paralog = [args.paralog1, args.paralog2]
Force = None
if args.case == 'Two':
alignment_file = './SwapParalogAlignment/' + '_'.join(paralog) + '/two_ingroup/' + '_'.join(paralog) + '_' + args.spe + '_two_ingroup_input.fasta'
save_name = './save/' + '_'.join(paralog) + '_' + args.spe + '_two_ingroup' + args.model+ '_nonclock_save.txt'
summary_file = './Summary/'+ '_'.join(paralog) + '_' + args.spe + '_two_ingroup' + args.model+ '_nonclock_summary.txt'
elif args.case == 'Six':
alignment_file = './SwapParalogAlignment/' + '_'.join(paralog) + '/six_ingroup/' + '_'.join(paralog) + '_' + args.spe + '_six_ingroup_input.fasta'
save_name = './save/' + '_'.join(paralog) + '_' + args.spe + '_six_ingroup' + args.model+ '_nonclock_save.txt'
summary_file = './Summary/'+ '_'.join(paralog) + '_' + args.spe + '_six_ingroup' + args.model+ '_nonclock_summary.txt'
newicktree = './YeastTree.newick'
if args.force:
if args.model == 'MG94':
Force = {5:0.0}
elif args.model == 'HKY':
Force = {4:0.0}
save_name = save_name.replace('./save/', './save/Force_')
summary_file = summary_file.replace('./Summary/', './Summary/Force_')
else:
Force = None
sitewise_summary_file = summary_file.replace('_summary.txt', '_sitewise_summary.txt')
test = ReCodonGeneconv( newicktree, alignment_file, paralog, Model = args.model, Force = Force, clock = args.clock, save_name = save_name)
test.get_mle(True, True, 0, 'BFGS')
test.get_individual_summary(summary_path = './Summary/', file_name = summary_file)
test.get_SitewisePosteriorSummary(summary_path = './Summary/', file_name = sitewise_summary_file)
def run_mle(test):
mle_paralog = [str(test.paralog.paralog1), str(test.paralog.paralog2)]
mle_model = test.model.model
mle_force = test.model.force
mle_clock = test.model.clock
mle_newicktree = test.tree.tree_file
if mle_force:
if mle_model == 'MG94':
Force = {5: 0.0}
elif mle_model == 'HKY':
Force = {4: 0.0}
else:
Force = None
mle_alignment_file = test.alignment.alignment_file
mle_save_name = test.save.save_file
mle_summary_folder = test.summary.summary_folder
summary_name_appendix = '_summary.txt'
if mle_clock:
summary_name_appendix = '_clock' + summary_name_appendix
else:
summary_name_appendix = '_nonclock' + summary_name_appendix
if mle_force:
summary_name_appendix = '_force' + summary_name_appendix
else:
summary_name_appendix = '_noforce' + summary_name_appendix
mle_summary_file = mle_summary_folder + '/' + mle_model + '_' + '_'.join(
mle_paralog) + summary_name_appendix
mle_sitewise_summary_file = mle_summary_folder + '/' + mle_model + '_' + '_'.join(
mle_paralog) + summary_name_appendix.replace('_summary.txt',
'_sitewise_summary.txt')
mle_test = ReCodonGeneconv(mle_newicktree,
mle_alignment_file,
mle_paralog,
Model=mle_model,
Force=Force,
clock=mle_clock,
save_name=mle_save_name)
mle_test.get_mle(True, True, 0, 'BFGS')
mle_test.get_individual_summary(summary_path=mle_summary_folder,
file_name=mle_summary_file)
mle_test.get_SitewisePosteriorSummary(summary_path=mle_summary_folder,
file_name=mle_sitewise_summary_file)
return mle_test
def main(args):
paralog = [args.paralog1, args.paralog2]
sim_num = args.simnum
Force = None
clock = False
alignment_file = './Simulation/' + '_'.join(paralog) + '/' + '_'.join(paralog) + '_MG94_nonclock_Sim_' + str(sim_num) + '.fasta'
save_name = './SimulationSave/' + '_'.join(paralog) + '/' + '_'.join(paralog) + '_MG94_nonclock_Sim_' + str(sim_num) + '_save.txt'
newicktree = './YeastTree.newick'
test = ReCodonGeneconv( newicktree, alignment_file, paralog, Model = 'MG94', Force = None, clock = False, save_name = save_name)
test.get_mle(True, True, 0, 'BFGS')
test.get_individual_summary(summary_path = './SimulationSummary/' + '_'.join(paralog) + '/', file_name = './SimulationSummary/' + '_'.join(paralog) + '/' + '_'.join(paralog) + '_MG94_nonclock_Sim_' + str(num_boot) + '_summary.txt')
def main(args):
paralog = [args.paralog1, args.paralog2]
Force = None
alignment_file = '../MafftAlignment/' + '_'.join(paralog) + '/' + '_'.join(paralog) + '_input.fasta'
newicktree = './YeastTree.newick'
if args.force:
if args.model == 'MG94':
Force = {5:0.0}
elif args.model == 'HKY':
Force = {4:0.0}
else:
Force = None
test = ReCodonGeneconv( newicktree, alignment_file, paralog, Model = args.model, Force = Force, clock = args.clock)
test.get_mle(True, True, 0, 'BFGS')
test.get_individual_summary(summary_path = './Summary/')
test.get_SitewisePosteriorSummary(summary_path = './Summary/')
def main(args):
paralog = [args.paralog1, args.paralog2]
Force = None
alignment_file = '../MafftAlignment/' + '_'.join(paralog) + '/' + '_'.join(
paralog) + '_input.fasta'
newicktree = './YeastTree.newick'
if args.force:
if args.model == 'MG94':
Force = {5: 0.0}
elif args.model == 'HKY':
Force = {4: 0.0}
else:
Force = None
test = ReCodonGeneconv(newicktree,
alignment_file,
paralog,
Model=args.model,
Force=Force,
clock=args.clock)
test.get_mle(True, True, 0, 'BFGS')
test.get_individual_summary(summary_path='./Summary/')
test.get_SitewisePosteriorSummary(summary_path='./Summary/')
def run(self):
mle_paralog = [str(self.paralog.paralog1), str(self.paralog.paralog2)]
mle_model = self.model.model
mle_force = self.model.force
mle_clock = self.model.clock
mle_newicktree = self.tree.tree_file
if mle_force:
if mle_model == 'MG94':
Force = {5: 0.0}
elif mle_model == 'HKY':
Force = {4: 0.0}
else:
Force = None
mle_alignment_file = self.alignment.alignment_file
mle_save_name = self.save.save_file
mle_summary_folder = self.summary.summary_folder
summary_name_appendix = '_summary.txt'
if mle_clock:
summary_name_appendix = '_clock' + summary_name_appendix
else:
summary_name_appendix = '_nonclock' + summary_name_appendix
if mle_force:
summary_name_appendix = '_force' + summary_name_appendix
else:
summary_name_appendix = '_noforce' + summary_name_appendix
mle_summary_file = mle_summary_folder + '/' + '_'.join(
mle_paralog) + '_' + mle_model + summary_name_appendix
mle_sitewise_summary_file = mle_summary_folder + '/' + '_'.join(
mle_paralog) + '_' + mle_model + summary_name_appendix.replace(
'_summary.txt', '_sitewise_summary.txt')
self.test = ReCodonGeneconv(mle_newicktree,
mle_alignment_file,
mle_paralog,
Model=mle_model,
Force=Force,
clock=mle_clock,
save_name=mle_save_name)
def main(args):
paralog = [args.paralog1, args.paralog2]
num_boot = args.bootnum
Force = None
clock = False
alignment_file = './BootStrapSamples/' + '_'.join(
paralog) + '/' + '_'.join(paralog) + '_Boot' + str(num_boot) + '.fasta'
save_name = './BootStrapSave/' + '_'.join(paralog) + '/' + '_'.join(
paralog) + '_Boot' + str(num_boot) + '_save.txt'
newicktree = './YeastTree.newick'
test = ReCodonGeneconv(newicktree,
alignment_file,
paralog,
Model='MG94',
Force=None,
clock=False,
save_name=save_name)
test.get_mle(False, True, 0, 'BFGS')
test.get_individual_summary(
summary_path='./BootStrapSummary/' + '_'.join(paralog) + '/',
file_name='./BootStrapSummary/' + '_'.join(paralog) + '/' +
'_'.join(paralog) + '_Boot' + str(num_boot) + '_summary.txt')
if __name__ == '__main__':
paralog = ['EDN', 'ECP']
Force = None
alignment_file = './EDN_ECP_Cleaned.fasta'
newicktree = './EDN_ECP_tree.newick'
Force = None
model = 'HKY' # choose from 'HKY' and 'MG94'
save_folder = './save/'
check_folder(save_folder)
save_name = save_folder + model + '_EDN_ECP_nonclock_save_change.txt'
summary_folder = './summary/'
check_folder(summary_folder)
test = ReCodonGeneconv(newicktree,
alignment_file,
paralog,
Model=model,
Force=Force,
clock=None,
save_path='./save/',
save_name=save_name,
tau=1,
omega=0.9,
kappa=0.1,
inibl=0.2)
test.get_mle()
test.get_ExpectedNumGeneconv()
test.get_individual_summary(summary_path='./save/')
from Pdiff import read_txt
from IGCexpansion.CodonGeneconv import ReCodonGeneconv
if __name__ == '__main__':
pairs = []
all_pairs = './Filtered_pairs.txt'
summary_path = '/Users/xji3/MixedFromCluster/NewPackageNewRun/'
with open(all_pairs, 'r') as f:
for line in f.readlines():
pairs.append(line.replace('\n', '').split('_'))
for paralog in pairs:
model = 'MG94'
alignment_file = '../MafftAlignment/' + '_'.join(
paralog) + '/' + '_'.join(paralog) + '_input.fasta'
newicktree = './YeastTree.newick'
clock = False
Force = None
test = ReCodonGeneconv(newicktree,
alignment_file,
paralog,
Model=model,
Force=Force,
clock=clock)
x = read_txt(summary_path, paralog, model, Force, clock, False, False)
test.update_by_x(x)
test.save_x()
# this function creats it by assuming the outer folder exists (potential bug...)
if not os.path.isdir(folder_name):
os.mkdir(folder_name)
if __name__ == '__main__':
paralog = ['EDN', 'ECP']
Force = None
alignment_file = './EDN_ECP_Cleaned.fasta'
newicktree = './EDN_ECP_tree.newick'
Force = None
model = 'MG94' # choose from 'HKY' and 'MG94'
save_folder = './save/'
check_folder(save_folder)
save_name = save_folder + model + '_EDN_ECP_nonclock_save.txt'
summary_folder = './summary/'
check_folder(summary_folder)
test = ReCodonGeneconv(newicktree,
alignment_file,
paralog,
Model=model,
Force=Force,
clock=None,
save_path='../test/save/',
save_name=save_name)
test.get_mle()
test.get_ExpectedNumGeneconv()
test.get_summary(True)
from IGCexpansion.CodonGeneconv import ReCodonGeneconv
if __name__ == '__main__':
paralog = ['YLR406C', 'YDL075W']
Force = None
alignment_file = './YLR406C_YDL075W_input.fasta'
newicktree = './YeastTree.newick'
# if args.force:
# if args.model == 'MG94':
# Force = {5:0.0}
# elif args.model == 'HKY':
# Force = {4:0.0}
# else:
# Force = None
Force = None
test = ReCodonGeneconv(newicktree,
alignment_file,
paralog,
Model='HKY',
Force=Force,
clock=None)
test.get_mle(True, True, 0, 'BFGS')
#test.get_individual_summary(summary_path = './Summary/')
#test.get_SitewisePosteriorSummary(summary_path = './Summary/')
def main(args):
model = args.model
paralog = [args.paralog1, args.paralog2]
alignment_file = '../MafftAlignment/' + '_'.join(paralog) + '/' + '_'.join(
paralog) + '_input.fasta'
switched_alignment_file = './TestTau/' + '_'.join(
paralog) + '/' + '_'.join(paralog) + '_switched.fasta'
if args.switch:
newicktree = './TestTau/YeastTestTree.newick'
path = './TestTau/'
summary_path = './TestTau/'
else:
newicktree = '../PairsAlignemt/YeastTree.newick'
path = './NewPackageNewRun/'
summary_path = './NewPackageNewRun/'
omega_guess = 0.1
print('Now calculate MLE for pair', paralog)
if args.force:
if model == 'MG94':
Force = {5: 0.0}
elif model == 'HKY':
Force = {4: 0.0}
else:
Force = None
if args.gBGC:
if args.dir:
test = gBGCDirGeneconv(newicktree,
alignment_file,
paralog,
Model=model,
Force=Force,
clock=args.clock)
else:
test = gBGCCodonGeneconv(newicktree,
alignment_file,
paralog,
Model=model,
Force=Force,
clock=args.clock)
else:
if args.dir:
test = DirGeneconv(newicktree,
alignment_file,
paralog,
Model=model,
Force=Force,
clock=args.clock)
else:
test = ReCodonGeneconv(newicktree,
alignment_file,
paralog,
Model=model,
Force=Force,
clock=args.clock)
if model == 'MG94':
method = 'BFGS'
else:
method = 'BFGS'
result = test.get_mle(display=False, em_iterations=0, method=method)
test.get_ExpectedNumGeneconv()
test.get_ExpectedHetDwellTime()
if model == 'MG94':
test.get_individual_summary(summary_path=summary_path)
if args.switch:
if args.gBGC:
if args.dir:
test2 = gBGCDirGeneconv(newicktree,
switched_alignment_file,
paralog,
Model=model,
Force=Force,
clock=args.clock)
else:
test2 = gBGCCodonGeneconv(newicktree,
switched_alignment_file,
paralog,
Model=model,
Force=Force,
clock=args.clock)
else:
if args.dir:
test2 = DirGeneconv(newicktree,
switched_alignment_file,
paralog,
Model=model,
Force=Force,
clock=args.clock)
else:
test2 = ReCodonGeneconv(newicktree,
switched_alignment_file,
paralog,
Model=model,
Force=Force,
clock=args.clock)
result = test2.get_mle(display=False, em_iterations=0, method=method)
test2.get_ExpectedNumGeneconv()
test2.get_ExpectedHetDwellTime()
test2.get_individual_summary(summary_path=summary_path + 'switched_')