Tutorial 4: VisiumHD dataset

In this tutorial, we show how to apply scSTADE to identify spatial domains on VisiumHD dataset. As a example, we analyse the VisiumHD dataset.

---

The source code package is freely available at https://github.com/cuiyaxuan/scSTADE/tree/master. The datasets used in this study can be found at https://drive.google.com/drive/folders/1H-ymfCqlDR1wpMRX-bCewAjG5nOrIF51?usp=sharing.

---

import sys
sys.path.append("/.../scSTADE-master/scSTADE_Cluster_Functions")
# Input the path.
from scSTADE_HD import scSTADE
import os
import torch
import pandas as pd
import scanpy as sc
from sklearn import metrics
import multiprocessing as mp

def setup_seed(seed=41):
    import torch
    import os
    import numpy as np
    import random
    torch.manual_seed(seed)
    np.random.seed(seed)  # Numpy module.
    random.seed(seed)  # Python random module.
    if torch.cuda.is_available():
        # torch.backends.cudnn.benchmark = False
        torch.backends.cudnn.deterministic = True
        torch.cuda.manual_seed(seed)
        torch.cuda.manual_seed_all(seed)
        #os.environ['PYTHONHASHSEED'] = str(seed)

setup_seed(41)

device = torch.device('cpu')
# call 24 cpu cores
torch.set_num_threads(24)


n_clusters = 20  ###### the number of spatial domains.
file_fold = '/home/cuiyaxuan/spatialLIBD/square_016um/' #### to your path
adata = sc.read_visium(file_fold, count_file='filtered_feature_bc_matrix.h5', load_images=True) #### project name
adata.var_names_make_unique()
model = scSTADE(adata,device=device,n_top_genes=5000)
adata = model.train()
radius = 50
tool = 'mclust' # mclust, leiden, and louvain
from utils import clustering

if tool == 'mclust':
   clustering(adata, n_clusters, radius=radius, method=tool, refinement=False)
elif tool in ['leiden', 'louvain']:
   clustering(adata, n_clusters, radius=radius, method=tool, start=0.1, end=2.0, increment=0.01, refinement=False)

adata.obs['domain']
adata.obs['domain'].to_csv("label.csv")

/home/cuiyaxuan/anaconda3/envs/pytorch/lib/python3.8/site-packages/tqdm/auto.py:22: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm
/home/cuiyaxuan/anaconda3/envs/pytorch/lib/python3.8/site-packages/anndata/_core/anndata.py:1830: UserWarning: Variable names are not unique. To make them unique, call .var_names_make_unique.
  utils.warn_names_duplicates("var")
/home/cuiyaxuan/anaconda3/envs/pytorch/lib/python3.8/site-packages/scanpy/readwrite.py:413: DtypeWarning: Columns (1,2,3,4,5) have mixed types. Specify dtype option on import or set low_memory=False.
  positions = pd.read_csv(files['tissue_positions_file'], header=None)