def main(experiment_name, phenotypes, data_directory, anchor_genes,
num_replicates=1, percent=0.4, num_anchors=50, min_dangle_size=3,
max_dangle_size=10, test_ratio=0.5):
assert isinstance(phenotypes, list)
alphas = random.choices(range(min_dangle_size, max_dangle_size),
k=int(num_anchors * test_ratio))
assert len(alphas) < len(anchor_genes)
anchor_train_groups = []
anchor_test_groups = []
backbones = []
# Create all backbones
for rep_id in range(num_replicates):
random.shuffle(anchor_genes)
candidates = anchor_genes[:int(num_anchors)]
genes_of_interest_train, genes_of_interest_test = train_test_split(
candidates,
shuffle=True,
test_size=test_ratio)
anchor_train_groups.append(genes_of_interest_train)
anchor_test_groups.append(genes_of_interest_test)
backbones.append(
build_backbone(anchors=anchor_train_groups[rep_id], alphas=alphas,
weight=1, edge_percentage=percent))
# Write train anchors to file
with open(os.path.join(experiment_name, 'train_anchors.csv'), 'w') as fout:
for gene_group in anchor_train_groups:
fout.write(','.join(gene_group))
fout.write("\n")
# Write test anchors to file
with open(os.path.join(experiment_name, 'test_anchors.csv'), 'w') as fout:
for gene_group in anchor_test_groups:
fout.write(','.join(gene_group))
fout.write("\n")
# Adding the backbones and create the similarity object
for pheno in phenotypes:
file_name = os.path.join(data_directory, "{}.csv".format(pheno))
for rep_id in range(num_replicates):
sim_file_name = "anchored_{}_{}.csv".format(pheno, str(rep_id))
out_address = os.path.join(experiment_name, sim_file_name)
similarity = Similarity(file_name,
anchors=anchor_train_groups[rep_id],
alphas=alphas, string_id=True)
similarity.transform()
similarity.apply_threshold(lower_cor=0.2, upper_cor=0.8,
value=0)
similarity.augment(backbones[rep_id])
similarity.to_csv(out_address)
