def main():
gdata = groups_data.GroupsData.FromGroupsFile(
open('../data/thermodynamics/groups_species.csv', 'r'))
decomposer = group_decomposition.GroupDecomposer(gdata)
pdata = pseudoisomers_data.PseudoisomersData.FromFile(
'../data/thermodynamics/dG0.csv')
dstats = DecompositionStats(gdata)
for pisomer in pdata:
if not pisomer.Train():
continue
mol = pisomer.Mol()
decomposition = None
if mol:
decomposition = decomposer.Decompose(pisomer.Mol())
dstats.AddDecomposition(pisomer, decomposition)
else:
logging.warning('Cannot get a Mol for pseudoisomer %s' % pisomer)
continue
map = dstats.GetGroupMap()
rare_groups = []
for i in range(21):
groups = map.GetGroupsByNumExamples(i)
l = [{'group': g, 'pseudoisomers': ps} for g, ps in groups]
rare_groups.append({'count': i, 'groups': l})
image_name = 'images/groups_histo.png'
map.PlotHistogram('../res/' + image_name)
most_common_groups = map.GetMostCommonGroups()
mcg_dicts = [{'count': c, 'group': g} for g, c in most_common_groups]
pairwise_map = dstats.GetPairwiseGroupMap()
frequent_pairs = pairwise_map.GetMostFrequentCooccurences()
freq_pairs_dicts = [{
'count': c,
'groups': [ga, gb]
} for ga, gb, c in frequent_pairs]
ld_pairs = pairwise_map.GetLinearlyDependentPairs()
ld_pairs_dicts = [{
'ratio': r,
'pisomers': p,
'count': len(p),
'groups': [ga, gb]
} for ga, gb, r, p in ld_pairs]
template_data = {
'rare_groups_by_count': rare_groups,
'most_common_groups': mcg_dicts,
'histo_image_name': image_name,
'frequent_pairs': freq_pairs_dicts,
'ld_pairs': ld_pairs_dicts,
'groups_data': gdata,
'group_map': map
}
templates.render_to_file('analyze_training_groups.html', template_data,
'../res/analyze_training_groups.html')
def Main():
options, _ = MakeOpts().parse_args(sys.argv)
estimators = thermodynamic_estimators.LoadAllEstimators()
input_filename = path.abspath(options.input_filename)
if not path.exists(input_filename):
logging.fatal('Input filename %s doesn\'t exist' % input_filename)
print 'Will read pathway definitions from %s' % input_filename
thermo = estimators[options.thermodynamics_source]
print "Using the thermodynamic estimations of: " + thermo.name
thermo_data = thermodynamic_data.WrapperThermoData(thermo)
# Create a bounds instance
kegg_instance = kegg.Kegg.getInstance()
# Create output directories
out_dir = options.output_dir
if not path.exists(out_dir):
util._mkdir(out_dir)
pathgraph_dir = path.join(out_dir, 'pathway_graphs/')
util._mkdir(pathgraph_dir)
print 'Executing MTDF analysis'
pathway_iterator = pathway.KeggPathwayIterator.FromFilename(input_filename)
results = []
for pathway_data in pathway_iterator:
if pathway_data.skip:
print 'Skipping pathway', pathway_data.name
continue
print 'Analyzing pathway', pathway_data.name
model = pathway_data.GetStoichiometricModel(kegg_instance)
model_bounds = pathway_data.GetBounds()
mtdf_opt = mtdf_optimizer.MTDFOptimizer(model, thermo_data)
result = mtdf_opt.FindMTDF(model_bounds)
print 'Optimization status', result.status
result.WriteAllGraphs(pathgraph_dir)
results.append(result)
mtdf = result.opt_val
print '\tMTDF for', pathway_data.name, '= %.2g' % mtdf
output_filename = path.join(out_dir, 'results.html')
print 'Writing output to', output_filename
template_data = {'analysis_type': 'MTDF',
'results':results}
templates.render_to_file('pathway_optimization_results.html',
template_data,
output_filename)
def Main():
options, _ = MakeOpts().parse_args(sys.argv)
estimators = thermodynamic_estimators.LoadAllEstimators()
input_filename = path.abspath(options.input_filename)
if not path.exists(input_filename):
logging.fatal('Input filename %s doesn\'t exist' % input_filename)
print 'Will read pathway definitions from %s' % input_filename
thermo = estimators[options.thermodynamics_source]
print "Using the thermodynamic estimations of: " + thermo.name
thermo_data = thermodynamic_data.WrapperThermoData(thermo)
# Create a bounds instance
kegg_instance = kegg.Kegg.getInstance()
# Create output directories
out_dir = options.output_dir
if not path.exists(out_dir):
util._mkdir(out_dir)
pathgraph_dir = path.join(out_dir, 'pathway_graphs/')
util._mkdir(pathgraph_dir)
print 'Executing MTDF analysis'
pathway_iterator = pathway.KeggPathwayIterator.FromFilename(input_filename)
results = []
for pathway_data in pathway_iterator:
if pathway_data.skip:
print 'Skipping pathway', pathway_data.name
continue
print 'Analyzing pathway', pathway_data.name
model = pathway_data.GetStoichiometricModel(kegg_instance)
model_bounds = pathway_data.GetBounds()
mtdf_opt = mtdf_optimizer.MTDFOptimizer(model, thermo_data)
result = mtdf_opt.FindMTDF(model_bounds)
print 'Optimization status', result.status
result.WriteAllGraphs(pathgraph_dir)
results.append(result)
mtdf = result.opt_val
print '\tMTDF for', pathway_data.name, '= %.2g' % mtdf
output_filename = path.join(out_dir, 'results.html')
print 'Writing output to', output_filename
template_data = {'analysis_type': 'MTDF', 'results': results}
templates.render_to_file('pathway_optimization_results.html',
template_data, output_filename)
def main():
gdata = groups_data.GroupsData.FromGroupsFile(
open('../data/thermodynamics/groups_species.csv', 'r'))
decomposer = group_decomposition.GroupDecomposer(gdata)
pdata = pseudoisomers_data.PseudoisomersData.FromFile(
'../data/thermodynamics/dG0.csv')
dstats = DecompositionStats(gdata)
for pisomer in pdata:
if not pisomer.Train():
continue
mol = pisomer.Mol()
decomposition = None
if mol:
decomposition = decomposer.Decompose(pisomer.Mol())
dstats.AddDecomposition(pisomer, decomposition)
else:
logging.warning('Cannot get a Mol for pseudoisomer %s' % pisomer)
continue
map = dstats.GetGroupMap()
rare_groups = []
for i in range(21):
groups = map.GetGroupsByNumExamples(i)
l = [{'group': g, 'pseudoisomers': ps} for g,ps in groups]
rare_groups.append({'count': i, 'groups': l})
image_name = 'images/groups_histo.png'
map.PlotHistogram('../res/' + image_name)
most_common_groups = map.GetMostCommonGroups()
mcg_dicts = [{'count': c, 'group': g} for g,c in most_common_groups]
pairwise_map = dstats.GetPairwiseGroupMap()
frequent_pairs = pairwise_map.GetMostFrequentCooccurences()
freq_pairs_dicts = [{'count': c, 'groups': [ga, gb]} for ga, gb, c in frequent_pairs]
ld_pairs = pairwise_map.GetLinearlyDependentPairs()
ld_pairs_dicts = [{'ratio': r, 'pisomers': p, 'count': len(p), 'groups': [ga, gb]}
for ga, gb, r, p in ld_pairs]
template_data = {'rare_groups_by_count': rare_groups,
'most_common_groups': mcg_dicts,
'histo_image_name': image_name,
'frequent_pairs': freq_pairs_dicts,
'ld_pairs': ld_pairs_dicts,
'groups_data': gdata,
'group_map': map}
templates.render_to_file('analyze_training_groups.html',
template_data,
'../res/analyze_training_groups.html')
def main():
pdata = pseudoisomers_data.PseudoisomersData.FromFile(
'../data/thermodynamics/dG0.csv')
decomposer = group_decomposition.GroupDecomposer.FromGroupsFile(
open('../data/thermodynamics/groups_species.csv', 'r'))
train_pseudoisomers = []
test_pseudoisomers = []
skip_pseudoisomers = []
for pisomer in pdata:
mol = pisomer.Mol()
decomposition = None
if mol:
decomposition = decomposer.Decompose(pisomer.Mol())
if decomposition.unassigned_nodes:
logging.warning('%s didn\'t decompose', pisomer)
pisomer_dict = {'data': pisomer, 'decomposition': decomposition}
if pisomer.Train():
train_pseudoisomers.append(pisomer_dict)
elif pisomer.Test():
test_pseudoisomers.append(pisomer_dict)
elif pisomer.Skip():
skip_pseudoisomers.append(pisomer_dict)
else:
logging.warning('Found a pseudoisomer that is not marked as'
' test, train, or skip.')
template_data = {
'pseudoisomer_collections': [{
'name': 'Train',
'pseudoisomers': train_pseudoisomers
}, {
'name': 'Test',
'pseudoisomers': test_pseudoisomers
}, {
'name': 'Skip',
'pseudoisomers': skip_pseudoisomers
}]
}
templates.render_to_file('pseudoisomers_ground_truth.html', template_data,
'../res/pseudoisomers_ground_truth.html')
def main():
pdata = pseudoisomers_data.PseudoisomersData.FromFile(
'../data/thermodynamics/dG0.csv')
decomposer = group_decomposition.GroupDecomposer.FromGroupsFile(
open('../data/thermodynamics/groups_species.csv', 'r'))
train_pseudoisomers = []
test_pseudoisomers = []
skip_pseudoisomers = []
for pisomer in pdata:
mol = pisomer.Mol()
decomposition = None
if mol:
decomposition = decomposer.Decompose(pisomer.Mol())
if decomposition.unassigned_nodes:
logging.warning('%s didn\'t decompose', pisomer)
pisomer_dict = {'data': pisomer,
'decomposition': decomposition}
if pisomer.Train():
train_pseudoisomers.append(pisomer_dict)
elif pisomer.Test():
test_pseudoisomers.append(pisomer_dict)
elif pisomer.Skip():
skip_pseudoisomers.append(pisomer_dict)
else:
logging.warning('Found a pseudoisomer that is not marked as'
' test, train, or skip.')
template_data = {'pseudoisomer_collections':
[{'name': 'Train',
'pseudoisomers': train_pseudoisomers},
{'name': 'Test',
'pseudoisomers': test_pseudoisomers},
{'name': 'Skip',
'pseudoisomers': skip_pseudoisomers}
]}
templates.render_to_file('pseudoisomers_ground_truth.html',
template_data,
'../res/pseudoisomers_ground_truth.html')
if cost is not None:
print '\t*Protein Cost for', pathway_data.name, '= %.2g' % cost
if optima:
print 'Found', len(optima), 'near-optima for', pathway_data.name
optima = np.array(optima)
mean_opt = np.mean(optima)
mean_diff = np.mean(np.abs(optima - mean_opt))
print 'Mean optimum', mean_opt
print 'Mean diff from mean', mean_diff
print 'Percent diff %s%%' % (100*mean_diff / mean_opt)
print 'StdDev opt', np.std(optima)
else:
# Use default conditions to show the failure
res = opt.FindOptimum(model_bounds)
result_dict['result'] = res
results.append(result_dict)
output_filename = path.join(out_dir, 'results.html')
print 'Writing output to', output_filename
template_data = {'analysis_type': 'Protein Cost',
'kinetic_data': kin_data,
'results':results}
templates.render_to_file('protein_optimization_results.html',
template_data,
output_filename)
if __name__ == "__main__":
Main()
