accs = np.zeros((2, len(num_cluster)))
for i in range(len(num_cluster)):
k = num_cluster[i]
print('Iteration {0}, num-cluster={1}'.format(i, k))
# --------------------------------------------------
# 3.1. SETUP SOURCE DATA NMF CLUSTERING
# --------------------------------------------------
if labels is None:
# No source labels are provided, generate them via NMF clustering
nmf_labels = None
nmf_labels = NmfClustering(data, gene_ids, num_cluster=k, labels=[])
nmf_labels.add_cell_filter(cell_filter_fun)
nmf_labels.add_gene_filter(gene_filter_fun)
nmf_labels.set_data_transformation(data_transf_fun)
nmf_labels.apply(k=k, alpha=arguments.nmf_alpha, l1=arguments.nmf_l1, max_iter=arguments.nmf_max_iter, rel_err=arguments.nmf_rel_err)
labels = nmf_labels.cluster_labels
# Use perfect number of latent states for nmf and sc3
src_labels = np.array(labels, dtype=np.int)
src_lbl_set = np.unique(src_labels)
k_now = src_lbl_set.size
nmf = None
nmf = NmfClustering_initW(data, gene_ids, labels=labels, num_cluster=k_now)
nmf.add_cell_filter(cell_filter_fun)
nmf.add_gene_filter(gene_filter_fun)
nmf.set_data_transformation(data_transf_fun)
nmf.apply(k=k_now, alpha=arguments.nmf_alpha, l1=arguments.nmf_l1, max_iter=arguments.nmf_max_iter, rel_err=arguments.nmf_rel_err)
# --------------------------------------------------
perc_consensus_genes=perc_consensus_genes,
non_zero_threshold=non_zero_threshold)
data_transf_fun = sc.data_transformation_log2
# Generating labels from complete dataset
print "Train complete data"
complete_nmf = None
complete_nmf = NmfClustering(data,
np.arange(data.shape[0]),
num_cluster=num_cluster)
complete_nmf.add_cell_filter(cell_filter_fun)
complete_nmf.add_gene_filter(gene_filter_fun)
complete_nmf.set_data_transformation(data_transf_fun)
complete_nmf.apply(k=num_cluster,
alpha=nmf_alpha,
l1=nmf_l1,
max_iter=nmf_max_iter,
rel_err=nmf_rel_err)
# Get labels
desc, target_nmf, trg_lbls_pred, mixed_data = method_sc3_filter(
complete_nmf,
data, [],
cell_filter=cell_filter_fun,
gene_filter=gene_filter_fun,
transformation=data_transf_fun,
mix=0.0,
metric='euclidean',
use_da_dists=False,
n_trg_cluster=num_cluster)
labels = trg_lbls_pred
label_names, label_counts = np.unique(labels, return_counts=True)
data_src = data_transformation_log2(data_src)
# Load Target data
data_trg = np.loadtxt(path_trg)
gene_ids_trg = np.loadtxt(path_geneids_trg, dtype=np.str)
# Delete non-unique genes
data_trg, gene_ids_trg = delete_nonunique_genes(data_trg, gene_ids_trg)
# Apply cell filter
valid_cells = cell_filter(data_trg)
# Apply gene filter
valid_genes = gene_filter(data_trg)
# Create filtered data
data_trg = data_trg[:, valid_cells]
data_trg = data_trg[valid_genes, :]
gene_ids_trg = gene_ids_trg[valid_genes]
# Log transform data
data_trg = data_transformation_log2(data_trg)
# train source and test performance
source_nmf = NmfClustering(data_src, gene_ids_src, num_cluster=n_source_cluster)
source_nmf.apply(k=n_source_cluster, max_iter=100, rel_err=1e-3)
# Number of repetitions can be changed in line 153 of utils.py
target_nmf = DaNmfClustering(source_nmf, data_trg.copy(), gene_ids_trg, num_cluster=n_target_cluster)
target_nmf.apply(k=n_target_cluster, calc_transferability=True)
# target_nmf.transferability_pvalue
# np.savez(fname, source_ari=source_ari, target_ari=target_ari, n_mix=n_mix, n_source=n_source, n_target=n_target, n_source_cluster=n_source_cluster,
# n_target_cluster=n_target_cluster)
def method_nmf(src, src_labels, trg, trg_labels, n_src_cluster, n_trg_cluster):
ids = np.arange(trg.shape[0])
cp = NmfClustering(trg, ids, num_cluster=n_trg_cluster)
cp.apply()
return 'NMF', cp.cluster_labels, None
