import numpy as np from scbean.tools import utils as tl import scanpy as sc import pandas as pd import scanorama import argparse base_path = '/Users/zhongyuanke/data/' file1 = 'dropviz/mouse_brain_dropviz_filtered.h5ad' file2 = 'nuclei/adata_nuclei_filtered.h5ad' scan_path = 'results/scan_mouse.h5ad' # -------------train--------------------- adata1 = tl.read_sc_data(file1, fmt='h5ad') adata2 = tl.read_sc_data(file2, fmt='h5ad') # orig_label =adata_orig.obs['label'] print(adata1) print(adata2) datas = [adata1, adata2] corrected = scanorama.correct_scanpy(datas, return_dimred=True, dimred=16) adata_corrected = corrected[0].concatenate(corrected[1]) print(adata_corrected) sc.pp.neighbors(adata_corrected, use_rep='X_scanorama') sc.tl.umap(adata_corrected) adata_corrected.write_h5ad(scan_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')
import matplotlib
from numpy.random import seed
seed(2021)
matplotlib.use('TkAgg')
base_path = '/Users/zhongyuanke/data/'
out_path = 'dann_vae/spatial/davae_save02.h5ad'
file1 = base_path + 'spatial/mouse_brain/10x_mouse_brain_Anterior/V1_Mouse_Brain_Sagittal_Anterior_filtered_feature_bc_matrix.h5'
file2 = base_path + 'spatial/mouse_brain/10x_mouse_brain_Posterior/V1_Mouse_Brain_Sagittal_Posterior_filtered_feature_bc_matrix.h5'
file1_p = base_path + 'spatial/10x_mouse_brain_Anterior/anterior.h5ad'
file2_p = base_path + 'spatial/10x_mouse_brain_Posterior/posterior.h5ad'
batch_size = 256
epochs = 25
# adata1 = sc.read_10x_h5(file1)
adata1 = tl.read_sc_data(file1, fmt='10x_h5', batch_name='Anterior')
adata2 = tl.read_sc_data(file2, fmt='10x_h5', batch_name='Posterior')
print(adata1)
# print(adata1)
adata1.var_names_make_unique()
adata2.var_names_make_unique()
# len1 = adata1.shape[0]
# len2 = adata2.shape[0]
# sc.pp.filter_genes(adata1, min_cells=30)
# sc.pp.filter_genes(adata2, min_cells=30)
# sc.pp.log1p(adata1)
# sc.pp.log1p(adata2)
# print(adata1)
# print(adata2)
#
from scbean.model import davae as davae
import anndata
import scanpy as sc
import pandas as pd
import matplotlib
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']
import scbean.model.vipcca as vip
import scbean.tools.utils as tl
import scbean.tools.plotting as pl
# Please choose an appropiate matplotlib backend.
import matplotlib
# matplotlib.use('TkAgg')
# read single-cell data.
adata_b1 = tl.read_sc_data("./data/mixed_cell_lines/293t.h5ad", batch_name="293t")
adata_b2 = tl.read_sc_data("./data/mixed_cell_lines/jurkat.h5ad", batch_name="jurkat")
adata_b3 = tl.read_sc_data("./data/mixed_cell_lines/mixed.h5ad", batch_name="mixed")
# tl.preprocessing include filteration, log-TPM normalization, selection of highly variable genes.
adata_all= tl.preprocessing([adata_b1, adata_b2, adata_b3])
# Construct VIPCCA with specific setting.
handle = vip.VIPCCA(
adata_all,
res_path='./results/CVAE_5/',
split_by="_batch",
epochs=100,
lambda_regulizer=5,
)
# Training and integrating multiple single-cell datasets. The VIPCCA's output include cell representation in reduced dimensional space and recovered gene expression.
adata_integrate=handle.fit_integrate()
# Visualization
pl.run_embedding(adata_integrate, path='./results/CVAE_5/',method="umap")
pl.plotEmbedding(adata_integrate, path='./results/CVAE_5/', method='umap', group_by="_batch",legend_loc="right margin")
matplotlib.use('TkAgg')
parser = argparse.ArgumentParser()
parser.add_argument("--base_path",
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')
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')
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
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)