def hmdb_disease_analysis():
naming = NamingService('recon')
y, X = list(zip(*DataReader().read_hmdb_diseases().items()))
dyn_pre = DynamicPreprocessing(['fva'])
X_t = dyn_pre.fit_transform(X, y)
DataWriter('hmdb_disease_analysis').write_json(dict(zip(y, X_t)))
def healties_model():
X, y = DataReader().read_healthy('BC')
pre_model = DynamicPreprocessing(['naming', 'basic-fold-change-scaler'])
X = pre_model.fit_transform(list(X), y)
model = DynamicPreprocessing(['fva', 'flux-diff'])
model.fit(X, y)
with open('../outputs/api_model.p', 'wb') as f:
pickle.dump(model, f)
def hmdb_disease_analysis_pathway_level():
X, y = DataReader().read_solution('hmdb_disease_analysis')
with open('../models/api_model.p', 'rb') as f:
reaction_scaler = pickle.load(f)
dyn_pre = DynamicPreprocessing(
['pathway-scoring', 'transport-elimination'])
X_t = reaction_scaler._model.named_steps['flux-diff'].transform(X)
X_t = dyn_pre.fit_transform(X_t, y)
DataWriter('hmdb_disease_analysis_pathway_level').write_json(
dict(zip(y, X_t)))
def pathifier(disease_name):
model = DataReader().read_network_model()
X, y = DataReader().read_data(disease_name)
pre = DynamicPreprocessing(['metabolic-standard'])
X = pre.fit_transform(X, y)
import pdb
pdb.set_trace()
df = pd.DataFrame(X)
metabolite_fold_changes = robj.r.matrix(robj.FloatVector(
df.as_matrix().T.ravel().tolist()),
nrow=df.shape[1])
all_metabolite_ids = robj.StrVector(list(df))
subsystem_metabolite = defaultdict(set)
for r in model.reactions:
if r.subsystem and not (r.subsystem.startswith('Transport')
or r.subsystem.startswith('Exchange')):
subsystem_metabolite[r.subsystem] \
.update(m.id for m in r.metabolites if m.id in df)
pathway_names, pathway_metabolites = zip(
*filter(lambda x: x[1], subsystem_metabolite.items()))
pathway_metabolites = robj.r['list'](
*map(lambda x: robj.StrVector(list(x)), pathway_metabolites))
pathway_names = robj.StrVector(list(pathway_names))
is_healthy = robj.BoolVector(list(map(lambda x: x == 'h', y)))
pathifier = importr("pathifier")
result = pathifier.quantify_pathways_deregulation(metabolite_fold_changes,
all_metabolite_ids,
pathway_metabolites,
pathway_names,
is_healthy,
attempts=100,
min_exp=0,
min_std=0)
regScores = dict()
for pathway, scores in dict(result.items())['scores'].items():
regScores[pathway] = list(scores[:])
df = pd.DataFrame(regScores)
df.insert(0, 'stage', y)
df.to_csv('../dataset/disease/%s_regulization.csv' % disease_name,
index=False)