def create_sample_dropout(sample_id, num_vars: int,
bicluster_list: List[SimBicluster],
epi_data: np.ndarray, num_clusters: int,
epi_error: float, prob_drop_out: float):
chosen_clusters = random.sample(bicluster_list, num_clusters)
chosen_vars = set()
for cluster in chosen_clusters:
chosen_vars.update(cluster.vars)
cluster.samples.add(sample_id)
sample_clean = [
random.normalvariate(10, 1)
if i in chosen_vars else random.normalvariate(0, 1)
for i in range(num_vars)
]
sample = [
sample_var if random.random() < prob_drop_out else 0
for sample_var in sample_clean
]
epi_row = [
np.random.binomial(1, 1 - epi_error)
if i in chosen_vars else np.random.binomial(1, epi_error)
for i in range(num_vars)
]
epi_data.__iadd__(epi_row)
return sample
def create_sample_easy(sample_id, num_vars: int,
bicluster_list: List[SimBicluster],
epi_data: np.ndarray, num_tfs: int, epi_error: float,
error_type: str):
'''
:param sample_id: Sample unique id
:param num_vars: number of genes
:param bicluster_list: list of bicluster objects
:param epi_data: epigenetic gene vector
:param num_tfs: number of bicluters the sample belongs too
:param epi_error: error in epigentic measurements
:return: sample vector of gene measurements
'''
#randomly choose biclusters that the
chosen_clusters = random.sample(bicluster_list, num_tfs)
chosen_vars = set()
#union set of genes that are activated in sample
for cluster in chosen_clusters:
chosen_vars.update(cluster.vars)
cluster.samples.add(sample_id)
#sample = [random.normalvariate(5,1) if i in chosen_vars else random.normalvariate(0,1)
#for i in range(num_vars)]
if error_type == "mode":
state_row = [
np.random.binomial(1, 1 - epi_error)
if i in chosen_vars else np.random.binomial(1, epi_error)
for i in range(num_vars)
]
sample = [
random.normalvariate(3, 1)
if state_row[i] == 1 else random.normalvariate(0, 1)
for i in range(num_vars)
]
else:
sample = [
random.normalvariate(3, epi_error)
if i in chosen_vars else random.normalvariate(0, epi_error)
for i in range(num_vars)
]
#update the epigenetic vector with noise
epi_row = [1.0 if i in chosen_vars else 0.0 for i in range(num_vars)]
#epi_row = [np.random.binomial(1, 1 - epi_error) if i in chosen_vars else np.random.binomial(1, epi_error)
#for i in range(num_vars)]
#epi_row = [1 if i in chosen_vars else 0 for i in range(num_vars)]
epi_data.__iadd__(epi_row)
return sample
