{"id":60871,"date":"2024-09-12T15:44:37","date_gmt":"2024-09-12T07:44:37","guid":{"rendered":"http:\/\/www.biocloudservice.com\/wordpress\/?p=60871"},"modified":"2024-09-12T15:44:37","modified_gmt":"2024-09-12T07:44:37","slug":"nature-methods%e4%bd%b3%e4%bd%9c%ef%bc%81%e5%8f%8c%e6%b3%a8%e6%84%8f%e5%8a%9b%e6%9c%ba%e5%88%b6%e6%96%b0%e5%9e%8b%e5%9b%be%e7%a5%9e%e7%bb%8f%e7%bd%91%e7%bb%9cspatialglue%e7%a0%b4%e8%af%91%e7%a9%ba","status":"publish","type":"post","link":"http:\/\/www.biocloudservice.com\/wordpress\/?p=60871","title":{"rendered":"Nature Methods\u4f73\u4f5c\uff01\u53cc\u6ce8\u610f\u529b\u673a\u5236\u65b0\u578b\u56fe\u795e\u7ecf\u7f51\u7edcSpatialGlue\u7834\u8bd1\u7a7a\u95f4\u591a\u7ec4\u5b66\u7684\u7a7a\u95f4\u57df"},"content":{"rendered":"\n

\u524d\u8a00<\/strong><\/strong><\/p>\n\n\n\n

\u542c\u5230\u5f88\u591a\u5c0f\u4f19\u4f34\u4eec\u62b1\u6028\u751f\u4fe1\u5206\u6790\u53d1\u6587\u7ae0\u5b9e\u5728\u592a\u96be\u4e86\uff01\uff01\u5377\u5b8c\u5de5\u4f5c\u91cf\u5377\u65b0\u65b9\u6cd5\uff0c\u5377\u5b8c\u65b0\u65b9\u6cd5\u5377\u65b0\u7b97\u6cd5\uff01\u5b9e\u5728\u662f\u82e6\u4e0d\u582a\u8a00\u3002\u770b\u5230\u522b\u4eba\u5df2\u7ecf\u7ad9\u5728\u4e86\u98df\u7269\u94fe\u7684\u9876\u7aef\uff0c\u81ea\u5df1\u5374\u8fd8\u5728\u9f9f\u6b65\u524d\u884c\uff0c\u95f7\u95f7\u4e0d\u4e50\u3001\u6101\u7709\u82e6\u8138\uff01\u542c\u5230\u5927\u5bb6\u7684\u82e6\u607c\u5927\u6d77\u54e5\u6765\u5e2e\u52a9\u5927\u5bb6\u4e86\u3002\u4e0b\u9762\u770b\u770b\u53cc\u6ce8\u610f\u529b\u673a\u5236\u65b0\u578b\u56fe\u795e\u7ecf\u7f51\u7edc\u4e0e\u7a7a\u95f4\u591a\u7ec4\u5b66\u78b0\u649e\u4f1a\u64e6\u51fa\u4ec0\u4e48\u6837\u7684\u706b\u82b1\uff1f\u4e0d\u540c\u7684\u7ec4\u5b66\u6a21\u5f0f\u4e0e\u7a7a\u95f4\u4fe1\u606f\u76f8\u5982\u4f55\u8fdb\u884c\u7ed3\u5408\uff0c\u4ee5\u83b7\u5f97\u6240\u7814\u7a76\u7ec4\u7ec7\u7684\u5168\u9762\u5206\u5b50\u89c6\u56fe\uff1fSpatialGlue\u662f\u4e00\u79cd\u5177\u6709\u53cc\u6ce8\u610f\u529b\u673a\u5236\u7684\u56fe\u795e\u7ecf\u7f51\u7edc\u6a21\u578b\uff0c\u5b83\u901a\u8fc7\u7a7a\u95f4\u4f4d\u7f6e\u548c\u7ec4\u5b66\u6d4b\u91cf\u7684\u7ec4\u5185\u6574\u5408\u4ee5\u53ca\u8de8\u7ec4\u5b66\u6574\u5408\u6765\u7834\u8bd1\u7a7a\u95f4\u57df\u3002\u770b\u770bSpatialGlue\u80fd\u4e0d\u80fd\u8ba9\u4f60\u7075\u5149\u4e00\u73b0\u5462\uff1f<\/p>\n\n\n\n

\u7ec3\u4e86\u5341\u5e74\u751f\u4fe1\u5206\u6790\u7684\u5927\u6d77\u54e5\u5bf9\u4e8e\u751f\u4fe1\u5206\u6790\u77e5\u8bc6\u5df2\u7ecf\u5982\u9c7c\u5f97\u6c34\uff0c\u76f8\u4fe1\u6709\u5927\u6d77\u54e5\u7684\u52a0\u6301\u4e00\u5b9a\u80fd\u8ba9\u5927\u5bb6\u5b66\u4f1a\uff01\u6ca1\u6709\u65f6\u95f4\u5b66\u4e60\u4e14\u6709\u751f\u4fe1\u5206\u6790\u7684\u5c0f\u4f19\u4f34\u4eec\u5feb\u6765\u6ef4\u6ef4\u5927\u6d77\u54e5\u5662\uff01\u4ece\u5206\u6790\u5230\u53ef\u89c6\u5316\u76f4\u5230\u4f60\u6ee1\u610f\u4e3a\u6b62\uff01<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

\u5927\u6d77\u54e5\u5728\u8fd9\u91cc\u7ed9\u5927\u5bb6\u9001\u798f\u5229\u4e86\uff0c\u6709\u9700\u8981\u670d\u52a1\u5668\u7684\u5c0f\u4f19\u4f34\u4eec\uff0c\u6b22\u8fce\u5927\u5bb6\u540e\u53f0\u79c1\u4fe1\u5927\u6d77\u54e5\u54e6\uff0c\u4fdd\u8bc1\u670d\u52a1\u5668\u7684\u6027\u4ef7\u6bd4\u6700\u9ad8\u54e6\uff01<\/p>\n\n\n\n

\u4ee3\u7801\u6559\u7a0b<\/strong><\/strong><\/p>\n\n\n\n

\u5728\u672c\u6559\u7a0b\u4e2d\uff0c\u5927\u6d77\u54e5\u7ed9\u5927\u5bb6\u6f14\u793a\u4e86\u5982\u4f55\u5e94\u7528 SpatialGlue \u6765\u96c6\u6210 Stereo-CITE-seq\u6570\u636e\u4ee5\u83b7\u5f97\u7ec6\u7c92\u5ea6\u805a\u7c7b\u3002Stereo-CITE-seq\u53ef\u5171\u540c\u68c0\u6d4b\u514d\u75ab\u5668\u5b98\u4e2d\u7684mRNA\u548c\u86cb\u767d\u8d28\u6211\u4eec\u5206\u6790\u4e86\u5c0f\u9f20\u80f8\u817a\u6570\u636e\u96c6\u3002\u6211\u4eec\u4ece\u534e\u5927\u57fa\u56e0\u6536\u96c6\u4e86\u6570\u636e\u3002\u6839\u636e\u6807\u8bb0\u57fa\u56e0\u548c\u86cb\u767d\u8d28\uff0c\u6211\u4eec\u624b\u52a8\u5c06\u7ec4\u7ec7\u6ce8\u91ca\u4e3a 8 \u79cd\u7ec6\u80de\u7c7b\u578b\u3002\u6f14\u793a\u6570\u636e\u8bf7\u79c1\u4fe1\u5927\u6d77\u54e5\u83b7\u53d6\u54e6\uff01<\/p>\n\n\n\n

1..\u5b89\u88c5\u53ca\u52a0\u8f7d<\/strong>SpatialGlue<\/strong>\u5305<\/strong><\/strong><\/p>\n\n\n\n

conda create -n SpatialGlue python=3.8<\/p>\n\n\n\n

conda activate SpatialGlue<\/p>\n\n\n\n

pip install SpatialGlue<\/p>\n\n\n\n

##\u5bfc\u5165\u76f8\u5173\u7684\u5305<\/p>\n\n\n\n

import os<\/p>\n\n\n\n

import torch<\/p>\n\n\n\n

import pandas as pd<\/p>\n\n\n\n

import scanpy as sc<\/p>\n\n\n\n

import SpatialGlue<\/p>\n\n\n\n

# \u73af\u5883\u914d\u7f6e\u3002SpatialGlue\u5305\u53ef\u4ee5\u7528CPU\u6216GPU\u5b9e\u73b0\u3002\u5f3a\u70c8\u63a8\u8350GPU\u52a0\u901f\u4ee5\u63d0\u9ad8\u6548\u7387\u3002<\/p>\n\n\n\n

device = torch.device(‘cuda:2’ if torch.cuda.is_available() else ‘cpu’)<\/p>\n\n\n\n

# R\u7684\u4f4d\u7f6e\uff0c\u8fd9\u662f\u201cmclust\u201d\u805a\u7c7b\u7b97\u6cd5\u6240\u9700\u8981\u7684\u3002\u8bf7\u5c06\u4e0b\u9762\u7684\u8def\u5f84\u66ff\u6362\u4e3a\u672c\u5730R\u5b89\u88c5\u8def\u5f84<\/p>\n\n\n\n

os.environ[‘R_HOME’] = ‘\/scbio4\/tools\/R\/R-4.0.3_openblas\/R-4.0.3’<\/p>\n\n\n\n

2.\u52a0\u8f7d\u6570\u636e<\/strong><\/strong><\/p>\n\n\n\n

# \u8bfb\u53d6\u6570\u636e<\/p>\n\n\n\n

file_fold = ‘\/home\/yahui\/anaconda3\/work\/SpatialGlue_revision\/data\/Dataset3_Mouse_Thymus1\/’ #please replace ‘file_fold’ with the download path<\/p>\n\n\n\n

adata_omics1 = sc.read_h5ad(file_fold + ‘adata_RNA.h5ad’)<\/p>\n\n\n\n

adata_omics2 = sc.read_h5ad(file_fold + ‘adata_protein.h5ad’)<\/p>\n\n\n\n

adata_omics1.var_names_make_unique()<\/p>\n\n\n\n

adata_omics2.var_names_make_unique()<\/p>\n\n\n\n

#\u6307\u5b9a\u6570\u636e\u7c7b\u578b<\/p>\n\n\n\n

data_type = ‘Stereo-CITE-seq’<\/p>\n\n\n\n

#\u56fa\u5b9a\u968f\u673a\u79cd\u5b50<\/p>\n\n\n\n

from SpatialGlue.preprocess import fix_seed<\/p>\n\n\n\n

random_seed = 2022<\/p>\n\n\n\n

fix_seed(random_seed)<\/p>\n\n\n\n

3. \u9884\u5904\u7406\u6570\u636e<\/strong><\/strong><\/p>\n\n\n\n

SpatialGlue \u5bf9\u8f6c\u5f55\u7ec4\u5b66\u548c\u86cb\u767d\u8d28\u6570\u636e\u91c7\u7528\u6807\u51c6\u7684\u9884\u5904\u7406\u6b65\u9aa4\u3002\u5177\u4f53\u800c\u8a00\uff0c\u5bf9\u4e8e\u8f6c\u5f55\u7ec4\u5b66\u6570\u636e\uff0c\u901a\u8fc7SCANPY\u5305\u5bf9\u57fa\u56e0\u8868\u8fbe\u8ba1\u6570\u8fdb\u884c\u5bf9\u6570\u8f6c\u6362\u5e76\u6309\u6587\u5e93\u5927\u5c0f\u8fdb\u884c\u5f52\u4e00\u5316\u3002\u9009\u62e9\u524d 3,000 \u4e2a\u9ad8\u5ea6\u53ef\u53d8\u57fa\u56e0 \uff08HVG\uff09 \u4f5c\u4e3a PCA \u7684\u8f93\u5165\uff0c\u4ee5\u8fdb\u884c\u964d\u7ef4\u3002\u4e3a\u786e\u4fdd\u8f93\u5165\u7ef4\u5ea6\u4e0e\u86cb\u767d\u8d28\u6570\u636e\u4e00\u81f4\uff0c\u5c06\u4fdd\u7559\u524d k\uff08\u86cb\u767d\u8d28\u6570\uff09\u4e3b\u6210\u5206\u5e76\u7528\u4f5c\u6a21\u578b\u7684\u8f93\u5165\u3002\u8fd9 \u4f7f\u7528 CLR\uff08\u4e2d\u5fc3\u5bf9\u6570\u6bd4\uff09\u5bf9\u86cb\u767d\u8d28\u8868\u8fbe\u8ba1\u6570\u8fdb\u884c\u89c4\u8303\u5316\u3002PCA \u964d\u7ef4\u540e\u7684\u6240\u6709\u4e3b\u6210\u5206\u5747\u7528\u4f5c\u6a21\u578b\u7684\u8f93\u5165\u3002<\/p>\n\n\n\n

from SpatialGlue.preprocess import clr_normalize_each_cell, pca<\/p>\n\n\n\n

# RNA<\/p>\n\n\n\n

sc.pp.filter_genes(adata_omics1, min_cells=10)<\/p>\n\n\n\n

sc.pp.filter_cells(adata_omics1, min_genes=80)<\/p>\n\n\n\n

sc.pp.filter_genes(adata_omics2, min_cells=50)<\/p>\n\n\n\n

adata_omics2 = adata_omics2[adata_omics1.obs_names].copy()<\/p>\n\n\n\n

sc.pp.highly_variable_genes(adata_omics1, flavor=”seurat_v3″, n_top_genes=3000)<\/p>\n\n\n\n

sc.pp.normalize_total(adata_omics1, target_sum=1e4)<\/p>\n\n\n\n

sc.pp.log1p(adata_omics1)<\/p>\n\n\n\n

adata_omics1_high =  adata_omics1[:, adata_omics1.var[‘highly_variable’]]<\/p>\n\n\n\n

adata_omics1.obsm[‘feat’] = pca(adata_omics1_high, n_comps=adata_omics2.n_vars-1)<\/p>\n\n\n\n

# \u86cb\u767d\u8d28<\/p>\n\n\n\n

adata_omics2 = clr_normalize_each_cell(adata_omics2)<\/p>\n\n\n\n

adata_omics2.obsm[‘feat’] = pca(adata_omics2, n_comps=adata_omics2.n_vars-1)<\/p>\n\n\n\n

4. \u6784\u9020\u90bb\u57df\u56fe<\/strong><\/strong><\/p>\n\n\n\n

\u4e3a\u4e86\u4fdd\u6301\u5177\u6709\u76f8\u540c\u7ec6\u80de\u7c7b\u578b\u4f46\u5728\u7a7a\u95f4\u4e0a\u4e0d\u76f8\u90bb\u7684\u6591\u70b9\u4e4b\u95f4\u7684\u7269\u7406\u90bb\u8fd1\u6027\u548c\u8868\u578b\u90bb\u8fd1\u6027\uff0c\u6211\u4eec\u6784\u5efa\u4e86\u4e24\u4e2a\u76f8\u90bb\u56fe\uff0c\u5373\u7a7a\u95f4\u56fe\u548c\u7279\u5f81\u56fe\u3002\u7a7a\u95f4\u56fe\u57fa\u4e8e\u7a7a\u95f4\u4fe1\u606f\u6784\u5efa\uff0c\u7279\u5f81\u56fe\u57fa\u4e8e\u8868\u8fbe\u5f0f\u5256\u9762\u6784\u5efa\u3002<\/p>\n\n\n\n

from SpatialGlue.preprocess import construct_neighbor_graph<\/p>\n\n\n\n

data = construct_neighbor_graph(adata_omics1, adata_omics2, datatype=data_type)<\/p>\n\n\n\n

5. \u8bad\u7ec3\u6a21\u578b<\/strong><\/strong><\/p>\n\n\n\n

SpatialGlue \u6a21\u578b\u65e8\u5728\u901a\u8fc7\u4ee5\u7a7a\u95f4\u611f\u77e5\u65b9\u5f0f\u81ea\u9002\u5e94\u5730\u6574\u5408\u4e0d\u540c\u7ec4\u5b66\u6a21\u5f0f\u7684\u8868\u8fbe\u8c31\u6765\u5b66\u4e60\u96c6\u6210\u7684\u6f5c\u5728\u8868\u5f81\u3002<\/p>\n\n\n\n

SpatialGlue \u6a21\u578b\u65e8\u5728\u901a\u8fc7\u4ee5\u7a7a\u95f4\u611f\u77e5\u65b9\u5f0f\u81ea\u9002\u5e94\u5730\u6574\u5408\u4e0d\u540c\u7ec4\u5b66\u6a21\u5f0f\u7684\u8868\u8fbe\u8c31\u6765\u5b66\u4e60\u96c6\u6210\u7684\u6f5c\u5728\u8868\u5f81\u3002<\/p>\n\n\n\n

    \n
  1. \u6f5c\u5728\u8868\u5f81\uff1a<\/li>\n\n\n\n
  2. ’emb_latent_omics1’\uff1a\u7b2c\u4e00\u79cd\u7ec4\u5b66\u6a21\u5f0f\u7684\u6f5c\u5728\u8868\u793a\u3002<\/li>\n\n\n\n
  3. \u201cemb_latent_omics2\u201d\uff1a\u7b2c\u4e8c\u7ec4\u5b66\u6a21\u5f0f\u7684\u6f5c\u5728\u8868\u793a\u3002<\/li>\n\n\n\n
  4. \u201cSpatialGlue\u201d\uff1a\u901a\u8fc7\u7ed3\u5408\u8868\u8fbe\u5f0f\u6570\u636e\u548c\u7a7a\u95f4\u4f4d\u7f6e\u4fe1\u606f\u6765\u5b66\u4e60\u8054\u5408\u8868\u793a\u3002<\/li>\n<\/ol>\n\n\n\n

    \u8054\u5408\u8868\u793a\u53ef\u7528\u4e8e\u4e0b\u6e38\u5206\u6790\uff0c\u4f8b\u5982\u805a\u7c7b\u3001\u53ef\u89c6\u5316\u6216\u8bc6\u522b\u5dee\u5f02\u8868\u8fbe\u57fa\u56e0 \uff08DEG\uff09\u3002<\/p>\n\n\n\n

      \n
    • \u6ce8\u610f\u6743\u91cd\u503c\uff1a<\/li>\n\n\n\n
    • \u201calpha_omics1\u201d\uff1a\u7b2c\u4e00\u79cd\u7ec4\u5b66\u6a21\u6001\u7684\u6a21\u6001\u5185\u6ce8\u610f\u529b\u6743\u91cd\uff0c\u89e3\u91ca\u4e86\u6bcf\u4e2a\u56fe\u5bf9\u6bcf\u4e2a\u7c07\u7684\u8d21\u732e\u3002<\/li>\n\n\n\n
    • ‘alpha_omics2’\uff1a\u7b2c\u4e8c\u7ec4\u5b66\u6a21\u6001\u7684\u6a21\u6001\u5185\u6ce8\u610f\u529b\u6743\u91cd\uff0c\u89e3\u91ca\u6bcf\u4e2a\u56fe\u5bf9\u6bcf\u4e2a\u7c07\u7684\u8d21\u732e\u3002<\/li>\n\n\n\n
    • \u201calpha\u201d\uff1a\u6a21\u6001\u95f4\u6ce8\u610f\u529b\u6743\u91cd\uff0c\u89e3\u91ca\u6bcf\u79cd\u6a21\u6001\u5bf9\u6bcf\u4e2a\u96c6\u7fa4\u7684\u8d21\u732e\u3002<\/li>\n<\/ul>\n\n\n\n

      \u8fd9\u4e9b\u6a21\u6001\u5185\u548c\u6a21\u6001\u95f4\u6ce8\u610f\u529b\u6743\u91cd\u63d0\u4f9b\u4e86\u5bf9\u6bcf\u4e2a\u90bb\u57df\u56fe\u548c\u6a21\u6001\u5bf9\u6bcf\u4e2a\u805a\u7c7b\u7684\u91cd\u8981\u6027\u7684\u53ef\u89e3\u91ca\u89c1\u89e3\u3002<\/p>\n\n\n\n

      # \u5b9a\u4e49\u6a21\u578b<\/p>\n\n\n\n

      from SpatialGlue.SpatialGlue_pyG import Train_SpatialGlue<\/p>\n\n\n\n

      model = Train_SpatialGlue(data, datatype=data_type, device=device)<\/p>\n\n\n\n

      # \u8bad\u7ec3\u6a21\u578b<\/p>\n\n\n\n

      output = model.train()<\/p>\n\n\n\n

      adata = adata_omics1.copy()<\/p>\n\n\n\n

      adata.obsm[’emb_latent_omics1′] = output[’emb_latent_omics1′]<\/p>\n\n\n\n

      adata.obsm[’emb_latent_omics2′] = output[’emb_latent_omics2′]<\/p>\n\n\n\n

      adata.obsm[‘SpatialGlue’] = output[‘SpatialGlue’]<\/p>\n\n\n\n

      adata.obsm[‘alpha’] = output[‘alpha’]<\/p>\n\n\n\n

      adata.obsm[‘alpha_omics1’] = output[‘alpha_omics1’]<\/p>\n\n\n\n

      adata.obsm[‘alpha_omics2’] = output[‘alpha_omics2’]<\/p>\n\n\n\n

      6. \u8de8\u7ec4\u5b66\u6574\u5408\u5206\u6790<\/p>\n\n\n\n

      \u96c6\u6210\u540e\uff0c\u4f7f\u7528mclust\u8fdb\u884c\u805a\u7c7b\u5206\u6790\u3002\u5728\u8fd9\u91cc\uff0c\u6211\u4eec\u63d0\u4f9b\u4e86\u4e09\u79cd\u53ef\u9009\u7684\u805a\u7c7b\u5de5\u5177\uff0c\u5305\u62ec mclust\u3001leiden \u548c louvain\u3002\u5728\u6211\u4eec\u7684\u5b9e\u9a8c\u4e2d\uff0c\u5927\u6d77\u54e5\u53d1\u73b0\u5728\u5927\u591a\u6570\u60c5\u51b5\u4e0b\uff0c\u201cmclust\u201d\u7b97\u6cd5\u5728\u7a7a\u95f4\u6570\u636e\u4e0a\u7684\u8868\u73b0\u4f18\u4e8e\u201cleiden\u201d\u548c\u201clouvain\u201d\u3002\u56e0\u6b64\uff0c\u5927\u6d77\u54e5\u5efa\u8bae\u4f7f\u7528\u201cmclust\u201d\u7b97\u6cd5\u8fdb\u884c\u805a\u7c7b\u3002<\/p>\n\n\n\n

      # \u6211\u4eec\u5c06\u201cmclust\u201d\u9ed8\u8ba4\u8bbe\u7f6e\u4e3a\u805a\u7c7b\u5de5\u5177\u3002\u7528\u6237\u8fd8\u53ef\u4ee5\u9009\u62e9\u201cleiden\u201d\u548c\u201clouvain\u201d\u3002<\/p>\n\n\n\n

      tool = ‘mclust’ # mclust, leiden, and louvain<\/p>\n\n\n\n

      clustering(adata, key=’SpatialGlue’, add_key=’SpatialGlue’, n_clusters=8, method=tool, use_pca=True)<\/p>\n\n\n\n

      #\u53ef\u89c6\u5316<\/p>\n\n\n\n

      import matplotlib.pyplot as plt<\/p>\n\n\n\n

      adata.obsm[‘spatial’][:,1] = -1*adata.obsm[‘spatial’][:,1]<\/p>\n\n\n\n

      fig, ax_list = plt.subplots(1, 2, figsize=(7, 3))<\/p>\n\n\n\n

      sc.pp.neighbors(adata, use_rep=’SpatialGlue’, n_neighbors=30)<\/p>\n\n\n\n

      sc.tl.umap(adata)<\/p>\n\n\n\n

      sc.pl.umap(adata, color=’SpatialGlue’, ax=ax_list[0], title=’SpatialGlue’, s=20, show=False)<\/p>\n\n\n\n

      sc.pl.embedding(adata, basis=’spatial’, color=’SpatialGlue’, ax=ax_list[1], title=’SpatialGlue’, s=20, show=False)<\/p>\n\n\n\n

      plt.tight_layout(w_pad=0.3)<\/p>\n\n\n\n

      plt.show()<\/p>\n\n\n\n

      \"\"<\/figure>\n\n\n\n

      # \u6ce8\u91ca<\/p>\n\n\n\n

      adata.obs[‘SpatialGlue_number’] = adata.obs[‘SpatialGlue’].copy()<\/p>\n\n\n\n

      adata.obs[‘SpatialGlue’].cat.rename_categories({1: ‘5-Outer cortex region 3(DN T,DP T,cTEC)’,<\/p>\n\n\n\n

                                                      2: ‘7-Subcapsular zone(DN T)’,<\/p>\n\n\n\n

                                                      3: ‘4-Middle cortex region 2(DN T,DP T,cTEC)’,<\/p>\n\n\n\n

                                                      4: ‘2-Corticomedullary Junction(CMJ)’,<\/p>\n\n\n\n

                                                      5: ‘1-Medulla(SP T,mTEC,DC)’,<\/p>\n\n\n\n

                                                      6: ‘6-Connective tissue capsule(fibroblast)’,<\/p>\n\n\n\n

                                                      7: ‘8-Connective tissue capsule(fibroblast,RBC,myeloid)’,<\/p>\n\n\n\n

                                                      8: ‘3-Inner cortex region 1(DN T,DP T,cTEC)’<\/p>\n\n\n\n

                                                      }, inplace=True)<\/p>\n\n\n\n

      list_ = [‘3-Inner cortex region 1(DN T,DP T,cTEC)’,’2-Corticomedullary Junction(CMJ)’,’4-Middle cortex region 2(DN T,DP T,cTEC)’,<\/p>\n\n\n\n

               ‘7-Subcapsular zone(DN T)’, ‘5-Outer cortex region 3(DN T,DP T,cTEC)’, ‘8-Connective tissue capsule(fibroblast,RBC,myeloid)’,<\/p>\n\n\n\n

               ‘1-Medulla(SP T,mTEC,DC)’,’6-Connective tissue capsule(fibroblast)’]<\/p>\n\n\n\n

      adata.obs[‘SpatialGlue’]  = pd.Categorical(adata.obs[‘SpatialGlue’],<\/p>\n\n\n\n

                            categories=list_,<\/p>\n\n\n\n

                            ordered=True)<\/p>\n\n\n\n

      # \u7ed8\u56fe<\/p>\n\n\n\n

      fig, ax_list = plt.subplots(1, 2, figsize=(9.5, 3))<\/p>\n\n\n\n

      sc.pp.neighbors(adata, use_rep=’SpatialGlue’, n_neighbors=30)<\/p>\n\n\n\n

      sc.tl.umap(adata)<\/p>\n\n\n\n

      sc.pl.umap(adata, color=’SpatialGlue’, ax=ax_list[0], title=’SpatialGlue’, s=10, show=False)<\/p>\n\n\n\n

      sc.pl.embedding(adata, basis=’spatial’, color=’SpatialGlue’, ax=ax_list[1], title=’SpatialGlue’, s=20, show=False)<\/p>\n\n\n\n

      ax_list[0].get_legend().remove()<\/p>\n\n\n\n

      plt.tight_layout(w_pad=0.3)<\/p>\n\n\n\n

      plt.show()<\/p>\n\n\n\n

      \"\"<\/figure>\n\n\n\n

      #\u4ea4\u6362\u4e0e\u6ce8\u91ca\u5bf9\u5e94\u7684\u6ce8\u610f\u6743\u91cd<\/p>\n\n\n\n

      list_SpatialGlue = [5,4,8,3,1,6,2,7]<\/p>\n\n\n\n

      adata.obs[‘SpatialGlue_number’]  = pd.Categorical(adata.obs[‘SpatialGlue_number’],<\/p>\n\n\n\n

                            categories=list_SpatialGlue,<\/p>\n\n\n\n

                            ordered=True)<\/p>\n\n\n\n

      adata.obs[‘SpatialGlue_number’].cat.rename_categories({5:1,<\/p>\n\n\n\n

                                                             4:2,<\/p>\n\n\n\n

                                                             8:3,<\/p>\n\n\n\n

                                                             3:4,<\/p>\n\n\n\n

                                                             1:5,<\/p>\n\n\n\n

                                                             6:6,<\/p>\n\n\n\n

                                                             2:7,<\/p>\n\n\n\n

                                                             7:8<\/p>\n\n\n\n

                                                      }, inplace=True)<\/p>\n\n\n\n

      # \u7ed8\u5236\u6a21\u6001\u6743\u91cd\u503c<\/p>\n\n\n\n

      import pandas as pd<\/p>\n\n\n\n

      import seaborn as sns<\/p>\n\n\n\n

      plt.rcParams[‘figure.figsize’] = (5,3)<\/p>\n\n\n\n

      df = pd.DataFrame(columns=[‘RNA’, ‘protein’, ‘label’])<\/p>\n\n\n\n

      df[‘RNA’], df[‘protein’] = adata.obsm[‘alpha’][:, 0], adata.obsm[‘alpha’][:, 1]<\/p>\n\n\n\n

      df[‘label’] = adata.obs[‘SpatialGlue_number’].values<\/p>\n\n\n\n

      df = df.set_index(‘label’).stack().reset_index()<\/p>\n\n\n\n

      df.columns = [‘label_SpatialGlue’, ‘Modality’, ‘Weight value’]<\/p>\n\n\n\n

      ax = sns.violinplot(data=df, x=’label_SpatialGlue’, y=’Weight value’, hue=”Modality”,<\/p>\n\n\n\n

                      split=True, inner=”quart”, linewidth=1, show=False)<\/p>\n\n\n\n

      ax.set_title(‘RNA vs protein’)<\/p>\n\n\n\n

      ax.set_xlabel(‘SpatialGlue label’)<\/p>\n\n\n\n

      ax.legend(bbox_to_anchor=(1.4, 1.01), loc=’upper right’)<\/p>\n\n\n\n

      plt.tight_layout(w_pad=0.05)<\/p>\n\n\n\n

      #plt.show()<\/p>\n\n\n\n

      \"\"<\/figure>\n\n\n\n

      \u5c0f\u7ed3<\/strong><\/strong><\/p>\n\n\n\n

      \u5728\u8fd9\u91cc\uff0c\u5927\u6d77\u54e5\u7ed9\u5927\u5bb6\u4ecb\u7ecd\u4e86\u7528\u4e8e\u7a7a\u95f4\u591a\u7ec4\u5b66\u5206\u6790\u7684\u00a0SpatialGlue\u3002\u5177\u4f53\u6765\u8bf4\uff0cSpatialGlue \u662f\u4e00\u79cd\u7a7a\u95f4\u611f\u77e5\u65b9\u6cd5\uff0c\u5b83\u96c6\u6210\u4e86\u4ece\u540c\u4e00\u7ec4\u7ec7\u5207\u7247\u83b7\u53d6\u7684\u591a\u79cd\u7a7a\u95f4\u7ec4\u5b66\u6570\u636e\u6a21\u6001\uff0c\u4ee5\u66f4\u9ad8\u7684\u7a7a\u95f4\u5206\u8fa8\u7387\u7834\u8bd1\u7ec4\u7ec7\u6837\u672c\u7684\u7a7a\u95f4\u57df\u3002SpatialGlue \u4f7f\u7528\u56fe\u795e\u7ecf\u7f51\u7edc\u6765\u5b66\u4e60\u6bcf\u79cd\u6570\u636e\u6a21\u6001\u7684\u4f4e\u7ef4\u5d4c\u5165\uff0c\u7136\u540e\u8fdb\u884c\u8de8\u6a21\u6001\u7684\u6570\u636e\u96c6\u6210\u3002\u4e3a\u4e86\u5c06\u7a7a\u95f4\u4fe1\u606f\u4e0e\u5355\u4e2a\u7ec4\u5b66\u6570\u636e\u6574\u5408\u5e76\u8de8\u7ec4\u5b66\u6574\u5408\uff0c\u6211\u4eec\u91c7\u7528\u4e86\u53cc\u6ce8\u610f\u529b\u805a\u5408\u673a\u5236\u6765\u81ea\u9002\u5e94\u5730\u6355\u6349\u4e0d\u540c\u6a21\u6001\u7684\u91cd\u8981\u6027\uff0c\u4ece\u800c\u5b9e\u73b0\u66f4\u51c6\u786e\u7684\u6574\u5408\u3002\u6700\u540e\u5927\u6d77\u54e5\u7ed9\u5927\u5bb6\u4ecb\u7ecd\u4e00\u4e2a\u4e91\u5de5\u5177\uff01\u540c\u5b66\u4eec\u5982\u679c\u89c9\u5f97\u81ea\u5df1\u7684\u4ee3\u7801\u6c34\u5e73\u4e00\u822c\uff0c\u5bf9\u4e8e\u5f88\u591a\u7684\u53c2\u6570\u4e0d\u77e5\u9053\u600e\u4e48\u6539\uff0c\u53ef\u4ee5\u4f53\u9a8c\u4e00\u4e0b\u6211\u4eec\u7684\u4e91\u751f\u4fe1\u5c0f\u5de5\u5177\uff0c\u53ea\u9700\u8f93\u5165\u6570\u636e\uff0c\u5373\u53ef\u8f7b\u677e\u751f\u6210\u6240\u9700\u56fe\u8868\uff0c\u5b57\u4f53\u5927\u5c0f\u3001\u6807\u9898\u7b49\u4e5f\u53ef\u4e00\u952e\u66f4\u6539\u3002\u611f\u5174\u8da3\u7684\u5c0f\u4f19\u4f34\u53bb\u4e91\u751f\u4fe1\uff08http:\/\/www.biocloudservice.com\/home.html\uff09\u4f53\u9a8c\u4e00\u4e0b\u5427\uff01<\/p>\n\n\n\n

      \"\"<\/figure>\n","protected":false},"excerpt":{"rendered":"

      \u524d\u8a00 \u542c\u5230\u5f88\u591a\u5c0f\u4f19\u4f34\u4eec\u62b1\u6028\u751f\u4fe1\u5206\u6790\u53d1\u6587\u7ae0\u5b9e\u5728\u592a\u96be\u4e86\uff01\uff01\u5377\u5b8c\u5de5\u4f5c\u91cf\u5377\u65b0\u65b9\u6cd5\uff0c\u5377\u5b8c\u65b0\u65b9\u6cd5\u5377\u65b0\u7b97\u6cd5\uff01\u5b9e\u5728\u662f\u82e6\u4e0d\u582a\u8a00\u3002 […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":""},"categories":[1],"tags":[],"jetpack_featured_media_url":"","_links":{"self":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/60871"}],"collection":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=60871"}],"version-history":[{"count":1,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/60871\/revisions"}],"predecessor-version":[{"id":60877,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/60871\/revisions\/60877"}],"wp:attachment":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=60871"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=60871"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=60871"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}