try:
source_clusters = None
if args.splitting_mode == 6:
source_clusters = ast.literal_eval(args.source_clusters)
except SyntaxError:
sys.stderr.write("Error: Invalid source cluster specification.")
sys.exit()
# 1. GENERATE TOY DATA
print('\nGenerate artificial single-cell RNA-seq data.')
data, labels = generate_toy_data(
num_genes=args.num_genes,
num_cells=args.num_cells,
cluster_spec=cluster_spec,
dirichlet_parameter_cluster_size=args.dir_cluster_size,
gamma_shape=args.gamma_shape,
gamma_rate=args.gamma_rate,
nb_dispersion=args.nb_dispersion,
min_prop_genes_de=args.min_prop_genes_de,
max_prop_genes_de=args.max_prop_genes_de,
mean_de_logfc=args.mean_de_logfc,
sd_de_logfc=args.sd_de_logfc)
print 'Data dimension: ', data.shape
output_fmt = "%u"
#Perform FPKM and log2 normalisation if required
if args.normalise:
data = np.log2(data.astype(float) / (np.sum(data, 0) / 1e6) + 1)
output_fmt = "%f"
# 2. SPLIT TOY DATA IN TARGET AND SOURCE DATA
source_clusters = ast.literal_eval(args.source_clusters)
except SyntaxError:
sys.stderr.write("Error: Invalid source cluster specification.")
sys.exit()
# 1. GENERATE TOY DATA
print('\nGenerate artificial single-cell RNA-seq data.')
data, labels = generate_toy_data(
num_genes = args.num_genes,
num_cells = args.num_cells,
cluster_spec = cluster_spec,
dirichlet_parameter_cluster_size = args.dir_cluster_size,
gamma_shape = args.gamma_shape,
gamma_rate = args.gamma_rate,
nb_dispersion = args.nb_dispersion,
min_prop_genes_de = args.min_prop_genes_de,
max_prop_genes_de = args.max_prop_genes_de,
mean_de_logfc = args.mean_de_logfc,
sd_de_logfc = args.sd_de_logfc
)
print 'Data dimension: ', data.shape
output_fmt = "%u"
#Perform FPKM and log2 normalisation if required
if args.normalise:
data = np.log2(data.astype(float) / (np.sum(data, 0) / 1e6) + 1)
output_fmt = "%f"
def experiment_loop(fname, methods, acc_funcs, n_src=800, n_trg=800, n_genes=1000, mode=2, reps=10,
cluster_mode=False, cluster_spec=[1, 2, 3, [4, 5], [6, [7, 8]]], percs=[0.1, 0.4, 0.8]):
flatten = lambda l: flatten(l[0]) + (flatten(l[1:]) if len(l) > 1 else []) if type(l) is list else [l]
n_cluster = len(flatten(cluster_spec))
print 'Number of cluster is ', n_cluster
accs = np.zeros((len(acc_funcs), reps, len(percs), len(methods)))
accs_desc = [''] * len(acc_funcs)
num_strat = np.zeros((reps, len(percs), len(methods)))
res_desc = []
for r in range(reps):
# 1. Generate scRNA data
data, labels = generate_toy_data(num_genes=n_genes,
num_cells=2.*(n_trg + n_src), # generate more data
cluster_spec=cluster_spec)
# 2. Split source and target according to specified mode/setting
src, trg, src_labels, trg_labels = split_source_target(data, labels,
target_ncells=n_trg, source_ncells=n_src,
mode=mode, source_clusters=None,
noise_target=False, noise_sd=0.1)
trg_labels = np.array(trg_labels, dtype=np.int)
src_labels = np.array(src_labels, dtype=np.int)
# 3.a. Subsampling order for target
inds = np.random.permutation(trg_labels.size)
# 3.b. Use perfect number of latent states for nmf and sc3
src_lbl_set = np.unique(src_labels)
n_trg_cluster = np.unique(trg_labels).size
n_src_cluster = src_lbl_set.size
# 3.c. Target data subsampling loop
for i in range(len(percs)):
if cluster_mode:
n_trg_cluster = percs[i]
p_trg = trg[:, inds[:n_trg]].copy()
p_trg_labels = trg_labels[inds[:n_trg]].copy()
else:
n_trg_perc = np.int(n_trg * percs[i])
p_trg = trg[:, inds[:n_trg_perc]].copy()
p_trg_labels = trg_labels[inds[:n_trg_perc]].copy()
# 4. MTL/DA mixing parameter loop
res_desc = list()
for m in range(len(methods)):
desc, lbls, reject = methods[m](src.copy(), src_labels.copy(),
p_trg.copy(), p_trg_labels.copy(),
n_src_cluster=n_src_cluster, n_trg_cluster=n_trg_cluster)
res_desc.append(desc)
# evaluation
strat_lbl_inds = []
for n in range(p_trg_labels.size):
if p_trg_labels[n] in src_lbl_set:
strat_lbl_inds.append(n)
for f in range(len(acc_funcs)):
accs[f, r, i, m], desc = acc_funcs[f](p_trg.copy(), p_trg_labels.copy(),
lbls.copy(), reject, strat_lbl_inds)
accs_desc[f] = desc
# save the result and then plot
np.savez(fname, methods=methods, acc_funcs=acc_funcs, accs=accs, accs_desc=accs_desc,
percs=percs, reps=reps, n_genes=n_genes, n_src=n_src, n_trg=n_trg,
desc=res_desc, mode=mode, num_strat=num_strat, cluster_mode=cluster_mode)
print('Done.')
n_cluster = len(flatten(cluster_spec))
#print 'Number of cluster is ', n_cluster
accs = np.zeros((len(acc_funcs), reps, len(percs), len(methods)))
#accs_mixed = np.zeros((len(acc_funcs), reps, len(percs), len(methods)))
accs_desc = list()
opt_mix_ind = np.zeros((reps, len(percs)))
opt_mix_aris = np.zeros((reps, len(percs)))
num_strat = np.zeros((reps, len(percs), len(methods)))
res_desc = []
r = 0
while r < reps:
# 1. Generate scRNA data
data, labels = generate_toy_data(num_genes=genes[g],
num_cells=10. *
(n_trg + n_src[s]),
cluster_spec=cluster_spec)
# 2. Split source and target according to specified mode/setting
src, trg, src_labels, trg_labels = split_source_target(
data,
labels,
target_ncells=n_trg,
source_ncells=n_src[s],
mode=7,
source_clusters=None,
noise_target=False,
noise_sd=0.1,
common=common[c],
cluster_spec=cluster_spec)
trg_labels = np.array(trg_labels, dtype=np.int)
src_labels = np.array(src_labels, dtype=np.int)