def integrate_spatial_rna(adata_spatial, adata_rna, type='anterior'):
adata_all = tl.spatial_rna_preprocessing(adata_spatial,
adata_rna,
n_top_genes=10000)
adata_integrate = davae.fit_integration(
adata_all,
epochs=100,
batch_size=2,
domain_lambda=5,
sparse=True,
hidden_layers=[128, 64, 32],
split_by='batch',
)
sc.pp.neighbors(adata_integrate, use_rep='X_davae')
sc.tl.umap(adata_integrate)
sc.pl.umap(adata_integrate, color='batch')
len_spatial = adata_spatial.shape[0]
len_rna = adata_rna.shape[0]
davae_emb = adata_integrate.obsm['X_davae']
adata_spatial.obsm["davae_embedding"] = davae_emb[0:len_spatial, :]
adata_rna.obsm['davae_embedding'] = davae_emb[len_spatial:len_rna +
len_spatial, :]
distances = 1 - cosine_distances(adata_rna.obsm["davae_embedding"],
adata_spatial.obsm['davae_embedding'])
class_prob_anterior = label_transfer(distances,
adata_rna.obs.cell_subclass)
cp_spatial_df = pd.DataFrame(class_prob_anterior,
columns=np.sort(
adata_rna.obs.cell_subclass.unique()))
label = cp_spatial_df.idxmax(axis='columns').values
cp_spatial_df.index = adata_spatial.obs.index
adata_transfer = adata_spatial.copy()
adata_transfer.obs = pd.concat([adata_spatial.obs, cp_spatial_df], axis=1)
sc.pl.spatial(
adata_transfer,
img_key="hires",
# color=["L2/3 IT", "L4", "L5 PT", "L6 CT"],
colot=['Hpca'],
size=1.5,
color_map='Blues',
ncols=2,
legend_fontsize='xx-small')
adata_spatial.obs['celltype'] = label
# sc.pl.spatial(
# adata_transfer,
# img_key="hires",
# color='celltype',
# size=1.5,
# color_map='Set2'
# )
label = list(label)
from collections import Counter
print(Counter(label))
adata_spatial.write_h5ad('/Users/zhongyuanke/data/dann_vae/spatial/' +
type + '_label_02.h5ad')
def deep_label_transfer(adata_spatial, adata_rna, type='anterior'):
adata_all = tl.spatial_rna_preprocessing(adata_spatial, adata_rna)
adata_integrate = davae.fit_integration(
adata_all,
epochs=45,
hidden_layers=[128, 64, 32, 5],
sparse=True,
domain_lambda=3.0,
)
sc.pp.neighbors(adata_integrate, use_rep='X_davae')
sc.tl.umap(adata_integrate)
sc.pl.umap(adata_integrate, color='batch')
rna_celltype = adata_rna.obs.cell_subclass
print(rna_celltype)
encoder = LabelEncoder()
orig_label = encoder.fit_transform(rna_celltype)
print(orig_label)
orig_label.dtype = 'int64'
davae_emb = adata_integrate.obsm['X_davae']
len_spatial = adata_spatial.shape[0]
len_rna = adata_rna.shape[0]
test_set = davae_emb[0:len_spatial]
train_set = davae_emb[len_spatial:len_spatial + len_rna]
label = to_categorical(orig_label)
print(label)
class_num = label.shape[1]
net_x = dc.CLASSIFIER(input_size=train_set.shape[1], class_num=class_num)
net_x.build()
net_x.compile()
net_x.train(x=train_set, label=label, epochs=25, batch_size=128)
pred_label = net_x.prediction(test_set)
pred_label.dtype = 'int64'
pred_type = encoder.inverse_transform(pred_label)
# df = pd.DataFrame(pred_type)
# df.to_csv('/Users/zhongyuanke/data/dann_vae/atac/pred_type_save03.csv')
# np.savetxt('/Users/zhongyuanke/data/dann_vae/atac/pred_label_save03.csv', pred_label, delimiter=',')
#
# all_label = np.concatenate([pred_label, orig_label])
# all_type = encoder.inverse_transform(all_label)
print(pred_type)
type_list = list(pred_type)
print(Counter(type_list))
adata_spatial.obs['celltype'] = pred_type
# adata_davae.obs['cell type'] = all_type
adata_spatial.write_h5ad(base_path + 'dann_vae/spatial/'+type+'_label_02.h5ad')
help="base path")
parser.add_argument("--epoch", type=int, default=15, help="epochs")
opt = parser.parse_args()
base_path = opt.base_path
epoch = opt.epoch
#
time_list = []
adata1 = sc.read_h5ad(base_path + 'blood_5w.h5ad')
adata2 = sc.read_h5ad(base_path + 'bone_5w.h5ad')
print(adata1)
print(adata2)
adata_all = tl.davae_preprocessing([adata1, adata2])
t0 = time.time()
adata_out = davae.fit_integration(adata_all,
batch_size=256,
epochs=epoch,
sparse=True)
t1 = time.time()
print("Total time running DAVAE 10w cells: %s seconds" % (str(t1 - t0)))
time_list.append(t1 - t0)
info = psutil.virtual_memory()
print('内存使用：',
psutil.Process(os.getpid()).memory_info().rss / 1024 / 1024 / 1024, 'GB')
print('总内存：', info.total / 1024 / 1024 / 1024, 'GB')
print('内存占比：', info.percent)
print('cpu个数：', psutil.cpu_count())
adata1 = sc.read_h5ad(base_path + 'blood_10w.h5ad')
adata2 = sc.read_h5ad(base_path + 'bone_10w.h5ad')
print(adata1)
print(adata2)
# sc.pp.highly_variable_genes(adata2, n_top_genes=6000)
# adata1 = adata1[:, adata1.var.highly_variable]
# adata2 = adata2[:, adata2.var.highly_variable]
#
# adata1.write_h5ad(file1_p)
# adata2.write_h5ad(file2_p)
# del adata1.var['highly_variable']
# del adata2.var['highly_variable']
# del adata1.var['means']
# del adata2.var['means']
# del adata1.var['dispersions']
# del adata2.var['dispersions']
# del adata1.var['dispersions_norm']
# del adata2.var['dispersions_norm']
print(adata1)
print(adata2)
adata_all = tl.davae_preprocessing([adata1, adata2], n_top_genes=4000)
adata_integrate = davae.fit_integration(
adata_all,
epochs=25,
hidden_layers=[128, 64, 32, 5],
sparse=True,
domain_lambda=0.5,
)
# import umap
# adata_integrate.obsm['X_umap']=umap.UMAP().fit_transform(adata_integrate.obsm['X_davae'])
sc.pp.neighbors(adata_integrate, use_rep='X_davae', n_neighbors=8)
sc.tl.umap(adata_integrate)
sc.pl.umap(adata_integrate, color=['_batch'], s=3)
adata_integrate.write_h5ad(base_path + out_path)
import scbean.model.davae as davae
import scbean.tools.utils as tl
import scanpy as sc
import matplotlib
from numpy.random import seed
seed(2021)
matplotlib.use('TkAgg')
adata = tl.read_sc_data('/Users/zhongyuanke/data/seurat_data/ifnb/ifnb.h5ad')
datasets = tl.split_object(adata, by="stim")
print(datasets[0])
print(datasets[1])
adata_all = tl.davae_preprocessing(datasets, n_top_genes=8000)
adata_intagrate = davae.fit_integration(
adata_all,
epochs=30,
hidden_layers=[128, 64, 32, 5],
domain_lambda=3.0,
)
print(adata_intagrate)
sc.pp.neighbors(adata_intagrate, use_rep='X_davae', n_neighbors=15)
sc.tl.louvain(adata_intagrate)
sc.tl.umap(adata_intagrate)
sc.pl.umap(adata_intagrate, color='louvain', cmap='tab20c')
matplotlib.use('TkAgg')
epochs = 40
base_path = '/Users/zhongyuanke/data/'
file1 = base_path + 'dann_vae/benchmark1/dc_batch1.h5ad'
file2 = base_path + 'dann_vae/benchmark1/dc_batch2.h5ad'
orig_path = base_path + 'dann_vae/benchmark1/orig.h5ad'
# -------------train---------------------
adata1 = tl.read_sc_data(file1, fmt='h5ad')
adata2 = tl.read_sc_data(file2, fmt='h5ad')
adata_orig = tl.read_sc_data(orig_path, fmt='h5ad')
# orig_label =adata_orig.obs['label']
print(adata1)
print(adata2)
adata_all = tl.davae_preprocessing([adata1, adata2],
n_top_genes=4000,
sparse=False)
adata_integrate = davae.fit_integration(adata_all,
split_by='batch',
epochs=1000,
hidden_layers=[128, 64, 32, 2],
sparse=False,
domain_lambda=6)
adata_integrate.obs['label'] = adata_orig.obs['label']
sc.pp.neighbors(adata_integrate, use_rep='X_davae')
sc.tl.umap(adata_integrate)
sc.pl.umap(adata_integrate, color=['batch', 'label'], s=10, cmap='Dark2')
# print(adata_integrate)
# adata_integrate.write_h5ad(base_path+'dann_vae/benchmark1/dc_davae_temp.h5ad')
type=str,
default='/Users/zhongyuanke/data/',
help="base path")
parser.add_argument("--epoch", type=int, default=10, help="epoch of training")
opt = parser.parse_args()
base_path = opt.base_path
out_path = 'dann_vae/hca/davae_01.h5ad'
file1 = base_path + 'HCA/ica_cord_blood_h5.h5'
file2 = base_path + 'HCA/ica_bone_marrow_h5.h5'
adata1 = tl.read_sc_data(file1, fmt='10x_h5')
adata2 = tl.read_sc_data(file2, fmt='10x_h5')
adata1.var_names_make_unique()
adata2.var_names_make_unique()
print(adata1)
adata_all = tl.davae_preprocessing([adata1, adata2], hvg=False, lognorm=False)
adata_integrate = davae.fit_integration(
adata_all,
split_by='batch',
domain_lambda=5,
epochs=1,
hidden_layers=[128, 64, 32, 5],
sparse=True,
)
sc.pp.neighbors(adata_integrate, use_rep='X_davae')
sc.tl.umap(adata_integrate)
sc.pl.umap(adata_integrate, color='batch')
print(adata_integrate)
matplotlib.use('TkAgg')
base_path = "/Users/zhongyuanke/data/vipcca/mixed_cell_lines/"
adata_b1 = tl.read_sc_data(base_path + "293t.h5ad", batch_name="293t")
adata_b2 = tl.read_sc_data(base_path + "jurkat.h5ad", batch_name="jurkat")
adata_b3 = tl.read_sc_data(base_path + "mixed.h5ad", batch_name="mixed")
adata = adata_b1.concatenate(adata_b2)
adata = adata.concatenate(adata_b3)
adata.write_h5ad('/Users/zhongyuanke/data/pbmc/zheng/mcl.h5ad')
adata_all = tl.davae_preprocessing([adata_b1, adata_b2, adata_b3],
n_top_genes=3000)
print(adata_all)
print(adata_all)
adata_integrate = davae.fit_integration(adata_all,
batch_num=3,
split_by='batch_label',
domain_lambda=3.0,
epochs=25,
sparse=True,
hidden_layers=[128, 64, 32, 5])
# sc.pp.neighbors(adata_integrate, use_rep='X_davae', n_neighbors=10)
# sc.tl.umap(adata_integrate)
import umap
adata_integrate.obsm['X_umap'] = umap.UMAP().fit_transform(
adata_integrate.obsm['X_davae'])
sc.pl.umap(adata_integrate, color=['_batch', 'celltype'], s=3)
# adata_integrate.write_h5ad('/Users/zhongyuanke/data/dann_vae/pbmc/davae_save02.h5ad')
# loss_weight = np.array(loss_weight)
# print(adata1.shape)
# print(adata2.shape)
# print(orig_data.shape)
# data, batches, batch_label, loss_weight = shuffle(orig_data, orig_batches, orig_batch_label, loss_weight,
# random_state=0)
# net_x = DACVAE(input_size=data.shape[1], batches=2, latent_size=10)
# net_x.build()
# net_x.compile()
# his = net_x.train(data, batches, loss_weight, epochs=epochs, batch_size=batch_size)
#
# mid = net_x.embedding(orig_data, orig_batches)
# adata_mid = anndata.AnnData(X=mid)
# adata_mid.obs['batch'] = orig_batch_label
# adata.obsm['davae'] = mid
adata_all = tl.davae_preprocessing(adata_list, sparse=False)
adata_out = davae.fit_integration(adata_all,
split_by='batch',
mode='DACVAE',
domain_lambda=5.0,
epochs=3,
hidden_layers=[128, 64, 32, 5],
sparse=False)
sc.pp.neighbors(adata_out, use_rep='X_davae')
sc.tl.umap(adata_out)
sc.pl.umap(adata_out, color='celltype')
print(adata_out)
# adata.write_h5ad(base_path+out_path)
import scbean.model.davae as davae
import scbean.tools.utils as tl
import scanpy as sc
import matplotlib
from numpy.random import seed
import umap
seed(2021)
matplotlib.use('TkAgg')
r1 = "./data/mixed_cell_lines/mixed.h5ad"
r2 = "./data/mixed_cell_lines/293t.h5ad"
r3 = "./data/mixed_cell_lines/jurkat.h5ad"
adata_b1 = tl.read_sc_data(r1, batch_name='mix')
adata_b2 = tl.read_sc_data(r2, batch_name='293t')
adata_b3 = tl.read_sc_data(r3, batch_name='jurkat')
adata_all = tl.davae_preprocessing([adata_b1, adata_b2, adata_b3],
n_top_genes=2000)
adata_integrate = davae.fit_integration(adata_all,
batch_num=3,
domain_lambda=3.0,
epochs=25,
sparse=True,
hidden_layers=[64, 32, 6])
adata_integrate.obsm['X_umap'] = umap.UMAP().fit_transform(
adata_integrate.obsm['X_davae'])
sc.pl.umap(adata_integrate, color=['_batch', 'celltype'], s=3)
# sc.pp.log1p(adata2)
# sc.pp.scale(adata2)
# adata2.obs['celltype'] = adata1.obs['celltype']
# adata2.write_h5ad(base_path + 'multimodal/atac_pbmc_10k/activaty_matrix_label.h5ad')
adata_all = tl.davae_preprocessing([adata1, adata2],
n_top_genes=2000,
hvg=False,
lognorm=False)
# sc.pp.scale(adata_all)
print(adata_all)
adata_integrate = davae.fit_integration(
adata_all,
# mode='DAVAE',
batch_num=2,
split_by='batch_label',
domain_lambda=6.0,
epochs=60,
sparse=True,
hidden_layers=[128, 64, 32, 16, 8])
print(adata_integrate)
# adata_integrate.obs['celltyp']=adata
import umap
sc.pp.neighbors(adata_integrate, use_rep='X_davae')
sc.tl.umap(adata_integrate)
# adata_integrate.obs['celltype']
adata_integrate.write_h5ad(
'/Users/zhongyuanke/data/dann_vae/multimodal/davae_multi_temp.h5ad')
#
#
# label=tool.get_label_by_txt(seurat_celltype_path)
# batch_categories=[
# k
# for d in [
# adata_spatial_anterior.uns["spatial"],
# adata_spatial_posterior.uns["spatial"],
# ]
# for k, v in d.items()
# ],
# )
print(adata_spatial)
import scbean.model.davae as davae
adata_integrate = davae.fit_integration(
adata_spatial,
epochs=25,
split_by='loss_weight',
hidden_layers=[128, 64, 32, 5],
sparse=True,
domain_lambda=0.5,
)
print(adata_spatial)
# embedding_adata = sc.read_h5ad(base_path+'dann_vae/spatial/davae_save02.h5ad')
adata_spatial.obsm["X_davae"] = adata_integrate.obsm['X_davae']
sc.pp.neighbors(adata_spatial, use_rep='X_davae', n_neighbors=10)
sc.tl.umap(adata_spatial)
sc.tl.leiden(adata_spatial, key_added="clusters")
sc.pl.umap(adata_spatial,
color=["library_id", "clusters"],
size=4,
color_map='Set2',
frameon=False)
# sc.pl.umap(
import scanpy as sc
import argparse
import scbean.model.davae as davae
import scbean.tools.utils as tl
parser = argparse.ArgumentParser()
parser.add_argument("--base_path",
type=str,
default='/Users/zhongyuanke/data/hca/',
help="base path")
parser.add_argument("--type", type=str, default='5w', help="cell counts")
parser.add_argument("--epoch", type=int, default=2, help="epochs")
opt = parser.parse_args()
base_path = opt.base_path
file1 = base_path + 'blood_' + opt.type + '.h5ad'
file2 = base_path + 'bone_' + opt.type + '.h5ad'
adata1 = sc.read_h5ad(file1)
adata2 = sc.read_h5ad(file2)
print(adata1)
print(adata2)
adata_all = tl.davae_preprocessing([adata1, adata2], lognorm=False, hvg=False)
adata_integrate = davae.fit_integration(adata_all,
batch_num=2,
split_by='batch_label',
domain_lambda=2.0,
epochs=opt.epoch,
sparse=True,
hidden_layers=[64, 32, 6])
