def simulate(self, cterms=['intrinsic', 'environmental', 'interactions'], interactions_size=None):
# train gp with requested terms
model = Model1(self.Y, self.X, norm='quantile', oos_predictions=0.,
cov_terms=cterms, kin_from=self.kin_from)
model.reset_params()
model.train_gp(grid_size=10)
# simulate from gp after removing interactions term
k = model.covar_terms['intrinsic'].K() + \
model.covar_terms['environmental'].K() + \
model.covar_terms['noise'].K()
k *= covar_rescaling_factor_efficient(k)
# manually add a cross-talk term
if interactions_size is not None:
assert 0. < interactions_size < 1., 'interactions size must be between 0 and 1 '
tmp = model.covar_terms['interactions'].K()
tmp *= covar_rescaling_factor_efficient(tmp)
tmp *= (interactions_size / (1. - interactions_size))
k += tmp
res = np.random.multivariate_normal([0.]*k.shape[0], k)
return res
def run(data_dir,
protein_index,
output_dir,
normalisation='quantile',
permute=False):
# reading all data
####################################################################
expression_file = data_dir + '/expressions.txt'
position_file = data_dir + '/positions.txt'
protein_names, phenotypes, X = utils.read_data(expression_file,
position_file)
# import pdb; pdb.set_trace()
protein_name = protein_names[protein_index, :]
phenotype = phenotypes[:, protein_index]
sel = range(phenotypes.shape[1])
sel.remove(protein_index)
kin_from = phenotypes[:, sel]
N_samples = X.shape[0]
# permuting cells
if permute:
perm = np.random.permutation(X.shape[0])
X = X[perm, :]
# intrinsic term
####################################################################
cterms = ['intrinsic', 'environmental', 'interactions']
model = Model1(phenotype,
X,
norm=normalisation,
oos_predictions=0.,
cov_terms=cterms,
kin_from=kin_from,
cv_ix=0)
model.reset_params()
model.train_gp(grid_size=10)
file_prefix = protein_name[0] + '_' + str(0) + '_interactions'
write_variance_explained(model, output_dir, file_prefix)
write_LL_grid(model, output_dir, file_prefix)
def run_indiv(protein_names, phenotypes, X, protein_index, output_dir,
normalisation, permute):
protein_name = protein_names[protein_index, :]
print('-------------------------------------------')
print('running model for ', protein_name[0])
print('-------------------------------------------')
phenotype = phenotypes[:, protein_index]
#sel = range(phenotypes.shape[1])
sel = [i for i in range(phenotypes.shape[1]) if i != protein_index]
#sel.remove(protein_index)
kin_from = phenotypes[:, sel]
N_samples = X.shape[0]
# permuting cells
if permute:
perm = np.random.permutation(X.shape[0])
X = X[perm, :]
# intrinsic term
# ------------------------------------------------------------------------
cterms = ['intrinsic', 'environmental', 'interactions']
model = Model1(phenotype,
X,
norm=normalisation,
oos_predictions=0.,
cov_terms=cterms,
kin_from=kin_from,
cv_ix=0)
model.reset_params()
model.train_gp(grid_size=10)
file_prefix = protein_name[0] + '_' + str(0) + '_interactions'
write_variance_explained(model, output_dir, file_prefix)
def run(data_dir,
protein_index,
output_dir,
bootstrap_index,
normalisation='standard',
permute=False):
# reading all data
####################################################################
expression_file = data_dir + '/expressions.txt'
position_file = data_dir + '/positions.txt'
protein_names, phenotypes, X = utils.read_data(expression_file,
position_file)
# import pdb; pdb.set_trace()
protein_name = protein_names[protein_index, :]
phenotype = phenotypes[:, protein_index]
sel = range(phenotypes.shape[1])
sel.remove(protein_index)
kin_from = phenotypes[:, sel]
N_samples = X.shape[0]
# permuting cells
if permute:
perm = np.random.permutation(X.shape[0])
X = X[perm, :]
# do null simulation
####################################################################
sim = FromRealSimulation(X, phenotype, kin_from)
Y_sim = sim.simulate()
# run model on simulated data
####################################################################
# intrinsic and environmental term
####################################################################
cterms = ['intrinsic', 'environmental']
model = Model1(Y_sim,
X,
norm=normalisation,
oos_predictions=0.,
cov_terms=cterms,
kin_from=kin_from)
model.reset_params()
model.train_gp(grid_size=10)
file_prefix = protein_name[0] + '_' + str(bootstrap_index) + '_local'
write_variance_explained(model, output_dir, file_prefix)
write_LL(model, output_dir, file_prefix)
int_param = model.intrinsic_cov.getParams()
env_param = model.environmental_cov.getParams()
noise_param = model.noise_cov.getParams()
####################################################################
# add cell-cell interactions
####################################################################
model.add_cov(['interactions'])
LL = np.Inf
for i in range(5):
if i == 0:
int_bk = int_param
env_bk = env_param
noise_bk = noise_param
scale_interactions = True
else:
int_bk = int_param * s.random.uniform(0.8, 1.2, len(int_param))
local_bk = local_param * s.random.uniform(0.8, 1.2, len(env_param))
noise_bk = noise_param * s.random.uniform(0.8, 1.2,
len(noise_param))
scale_interactions = False
model.set_initCovs({
'intrinsic': dir_bk,
'noise': noise_bk,
'environmental': local_bk
})
if scale_interactions:
model.set_scale_down(['interactions'])
else:
model.use_scale_down = False
model.reset_params()
model.train_gp(grid_size=10)
if model.gp.LML() < LL:
LL = model.gp.LML()
saved_params = model.gp.getParams()
model.gp.setParams(saved_params)
file_prefix = protein_name[0] + '_' + str(
bootstrap_index) + '_interactions'
write_variance_explained(model, output_dir, file_prefix)
#write_r2(model, output_dir, file_prefix)
write_LL(model, output_dir, file_prefix)
def run(data_dir,
protein_index,
output_dir,
interactions_size,
normalisation='standard',
permute=False):
# reading all data
####################################################################
expression_file = data_dir + '/expressions.txt'
position_file = data_dir + '/positions.txt'
protein_names, phenotypes, X = utils.read_data(expression_file,
position_file)
protein_name = protein_names[protein_index, :]
phenotype = phenotypes[:, protein_index]
sel = range(phenotypes.shape[1])
sel.remove(protein_index)
kin_from = phenotypes[:, sel]
# N_samples = X.shape[0]
boot_ix = deepcopy(interactions_size)
interactions_size = float(int(interactions_size) % 10) / 10.
down_sampling = 1 - float(int(interactions_size) / 10) / 10.
# down sampling
n_sel = down_sampling * X.shape[0]
sel = np.sort(np.random.choice(range(X.shape[0]), n_sel, replace=False))
X = X[sel, :]
phenotype = phenotype[sel]
kin_from = kin_from[sel, :]
N_samples = X.shape[0]
# TODO select X, select phenotype, kin_from, N_samples
# permuting cells
if permute:
perm = np.random.permutation(X.shape[0])
X = X[perm, :]
# do null simulation
####################################################################
sim = FromRealSimulation(X, phenotype, kin_from)
Y_sim = sim.simulate(interactions_size=interactions_size)
# run model on simulated data
####################################################################
# all but interactions
####################################################################
cterms = ['intrinsic', 'environmental']
model = Model1(Y_sim,
X,
norm=normalisation,
oos_predictions=0.,
cov_terms=cterms,
kin_from=kin_from)
model.reset_params()
model.train_gp(grid_size=10)
file_prefix = protein_name[0] + '_' + str(boot_ix) + '_environmental'
write_variance_explained(model, output_dir, file_prefix)
write_LL(model, output_dir, file_prefix)
####################################################################
# adding interactions
####################################################################
model.add_cov(['interactions'])
model.reset_params()
model.train_gp(grid_size=10)
file_prefix = protein_name[0] + '_' + str(boot_ix) + '_interactions'
write_variance_explained(model, output_dir, file_prefix)
write_LL(model, output_dir, file_prefix)
def run(data_dir,
protein_index,
output_dir,
bootstrap_index,
normalisation='quantile',
N_fold=5,
permute=False):
# reading all data
####################################################################
expression_file = data_dir + '/expressions.txt'
position_file = data_dir + '/positions.txt'
protein_names, phenotypes, X = utils.read_data(expression_file,
position_file)
protein_name = protein_names[protein_index, :]
phenotype = phenotypes[:, protein_index]
sel = range(phenotypes.shape[1])
sel.remove(protein_index)
kin_from = phenotypes[:, sel]
N_samples = X.shape[0]
# permuting cells
if permute:
perm = np.random.permutation(X.shape[0])
X = X[perm, :]
# checking N_fold for cross validation
oos = 1. / N_fold
# intrinsic term
####################################################################
cterms = ['intrinsic']
model = Model1(phenotype,
X,
norm=normalisation,
oos_predictions=oos,
cov_terms=cterms,
kin_from=kin_from,
cv_ix=bootstrap_index)
model.reset_params()
model.train_gp(grid_size=10)
file_prefix = protein_name[0] + '_' + str(bootstrap_index) + '_intrinsic'
write_variance_explained(model, output_dir, file_prefix)
write_pred(model, output_dir, file_prefix)
write_LL(model, output_dir, file_prefix)
# add local term
####################################################################
model.add_cov(['environmental'])
model.reset_params()
model.train_gp(grid_size=10)
file_prefix = protein_name[0] + '_' + str(
bootstrap_index) + '_environmental'
write_variance_explained(model, output_dir, file_prefix)
write_pred(model, output_dir, file_prefix)
write_LL_grid(model, output_dir, file_prefix)
# add crowding term
####################################################################
model.add_cov(['interactions'])
model.reset_params()
model.train_gp(grid_size=10)
file_prefix = protein_name[0] + '_' + str(
bootstrap_index) + '_interactions'
write_variance_explained(model, output_dir, file_prefix)
write_pred(model, output_dir, file_prefix)
write_LL_grid(model, output_dir, file_prefix)