def remove_reaction_duplicates(self, ignored_m_ids=None):
r_id2i = self.get_main_r_id2i()
m_id2i = self.get_main_m_id2i(ignored_m_ids=ignored_m_ids)
N = self.get_main_N(r_id2i=r_id2i, m_id2i=m_id2i)
r_id_groups = get_reaction_duplicates(N, r_id2i)
gr_i = 0
for r_ids in r_id_groups:
grouped_r_id, gr_i = get_unique_id(self.r_id2i, 'r_type', gr_i)
self.r_types.add(grouped_r_id)
self.r_id2gr_id.update({r_id: grouped_r_id for r_id in r_ids})
self.r_id2i[grouped_r_id] = self.V.shape[0]
sample_r_index = self.r_id2i[r_ids[0]]
sample_m_index = np.nonzero(self.N[:, sample_r_index])[0][0]
sample_m = self.N[sample_m_index, :]
st = sample_m[sample_r_index] * 1.0
indices = tuple((self.r_id2i[r_id] for r_id in r_ids))
self.gr_id2r_id2c[grouped_r_id] = {r_id: sample_m[self.r_id2i[r_id]] / st for r_id in r_ids}
self.N = np.concatenate((self.N, self.N[:, (sample_r_index, )]), axis=1)
v_new = np.dot(np.array([self.gr_id2r_id2c[grouped_r_id][r_id] for r_id in r_ids]), self.V[indices, :])
replace_zeros(v_new)
self.V = np.vstack((self.V, v_new))
self.r_ids -= set(r_ids)
self.r_ids.add(grouped_r_id)
def merge_efm_groups(self):
r_id2i = self.get_main_r_id2i()
m_id2i = self.get_main_m_id2i(boundary=True)
efm_id2i = self.get_main_efm_id2i()
V = self.get_main_V(r_id2i, efm_id2i)
N = self.get_main_N(r_id2i, m_id2i)
efm_id_groups = \
get_efm_groups_based_on_boundary_metabolites(N, V, efm_id2i)
gr_i = 0
for efm_ids in efm_id_groups:
grouped_efm_id, gr_i = get_unique_id(self.efm_id2i, 'pathway', gr_i)
self.pathways.add(grouped_efm_id)
self.efm_id2gr_id.update({efm_id: grouped_efm_id for efm_id in efm_ids})
self.gr_id2efm_ids[grouped_efm_id] = efm_ids
self.efm_id2i[grouped_efm_id] = self.V.shape[1]
indices = tuple((self.efm_id2i[efm_id] for efm_id in efm_ids))
lambdas = np.array([[1] for _ in efm_ids])
v_new = np.dot(self.V[:, indices], lambdas)
replace_zeros(v_new)
self.V = np.concatenate((self.V, v_new), axis=1)
self.efm_ids -= set(efm_ids)
self.efm_ids.add(grouped_efm_id)
def remove_efm_duplicates(self):
efm_id2i = self.get_main_efm_id2i()
V = self.get_main_V(efm_id2i=efm_id2i)
efm_id_groups = get_efm_duplicates(V, efm_id2i)
gr_i = 0
for efm_ids in efm_id_groups:
grouped_efm_id, gr_i = get_unique_id(self.efm_id2i, 'efm_type', gr_i)
self.folded_efms.add(grouped_efm_id)
self.efm_id2gr_id.update({efm_id: grouped_efm_id for efm_id in efm_ids})
self.gr_id2efm_ids[grouped_efm_id] = efm_ids
self.efm_id2i[grouped_efm_id] = self.V.shape[1]
sample_efm_index = self.efm_id2i[efm_ids[0]]
self.V = np.concatenate((self.V, self.V[:, (sample_efm_index, )]), axis=1)
self.efm_ids -= set(efm_ids)
self.efm_ids.add(grouped_efm_id)
def lump_coupled_reactions(self):
coupled_r_id_groups = get_coupled_reactions(self.V, self.r_id2i)
lr_i = 0
for r_ids in coupled_r_id_groups:
lumped_r_id, lr_i = get_unique_id(self.r_id2i, 'coupled_r', lr_i)
self.coupled_rs.add(lumped_r_id)
self.r_id2gr_id.update({r_id: lumped_r_id for r_id in r_ids})
self.r_id2i[lumped_r_id] = self.V.shape[0]
sample_r_index = self.r_id2i[r_ids[0]]
sample_efm_index = np.nonzero(self.V[sample_r_index, :])[0][0]
sample_efm = self.V[:, sample_efm_index]
c = abs(sample_efm[sample_r_index]) * 1.0
sign = coefficient_to_binary(sample_efm[sample_r_index])
self.gr_id2r_id2c[lumped_r_id] = {r_id: sample_efm[self.r_id2i[r_id]] / c for r_id in r_ids}
lambdas = np.array([[self.gr_id2r_id2c[lumped_r_id][r_id]] for r_id in r_ids])
r_new = np.dot(self.N[:, tuple((self.r_id2i[r_id] for r_id in r_ids))], lambdas)
replace_zeros(r_new)
self.N = np.concatenate((self.N, r_new), axis=1)
self.V = np.concatenate((self.V, [self.V[sample_r_index, :] * sign]), axis=0)
self.r_ids -= set(r_ids)
self.r_ids.add(lumped_r_id)