{"id":60913,"date":"2024-09-12T16:57:20","date_gmt":"2024-09-12T08:57:20","guid":{"rendered":"http:\/\/www.biocloudservice.com\/wordpress\/?p=60913"},"modified":"2024-09-12T16:57:20","modified_gmt":"2024-09-12T08:57:20","slug":"%e5%a4%a7%e4%bd%ac%e7%9c%bc%e4%b8%ad%e7%9a%84%e8%b6%85%e7%ba%a7%e6%b0%b4%e5%88%8anc%e7%85%a7%e6%a0%b7%e5%87%ba%e4%bd%b3%e4%bd%9c%ef%bc%81%e5%9f%ba%e4%ba%8e%e6%a0%b8%e6%8a%95%e5%bd%b1%e7%9a%84%e8%bf%87","status":"publish","type":"post","link":"http:\/\/www.biocloudservice.com\/wordpress\/?p=60913","title":{"rendered":"\u5927\u4f6c\u773c\u4e2d\u7684\u8d85\u7ea7\u6c34\u520aNC\u7167\u6837\u51fa\u4f73\u4f5c\uff01\u57fa\u4e8e\u6838\u6295\u5f71\u7684\u8fc7\u6ee4\u7b97\u6cd5 SiFT\u6765\u63ed\u793a\u5355\u7ec6\u80de\u6570\u636e\u9690\u85cf\u7684\u751f\u7269\u5c5e\u6027"},"content":{"rendered":"\n

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

\u5929\u7a7a\u4e00\u58f0\u5de8\u54cd\uff0c\u5927\u6d77\u54e5\u95ea\u4eae\u767b\u573a\uff01\u5f00\u59cb\u4eca\u5929\u7684\u5206\u4eab\u4e4b\u524d\uff0c\u5c0f\u4f19\u4f34\u4eec\u7ad6\u8d77\u8033\u6735\u542c\u542c\u5927\u6d77\u54e5\u7684\u95ee\u9898\uff01\u5355\u7ec6\u80de\u57fa\u56e0\u8868\u8fbe\u8c31\u7684\u90e8\u5206\u7a81\u51fa\u4fe1\u606f\u5bf9\u4e8e\u6211\u4eec\u7684\u5206\u6790\u771f\u7684\u90fd\u662f\u6709\u76ca\u7684\u5417\uff1f\u6709\u6ca1\u6709\u5c0f\u4f19\u4f34\u4eec\u601d\u8003\u8fc7\u8fd9\u4e2a\u95ee\u9898\u5462\uff1f\u505a\u8fc7\u5355\u7ec6\u80de\u7684\u5c0f\u4f19\u4f34\u4eec\u90fd\u77e5\u9053\u7ec6\u80de\u7fa4\u4f53\u4e0d\u4ec5\u5177\u6709\u7a7a\u95f4\u914d\u7f6e\u3001\u65f6\u95f4\u8f68\u8ff9\u548c\u7ec6\u80de\u95f4\u4e92\u52a8\u7b49\u591a\u79cd\u751f\u7269\u5c5e\u6027\uff0c\u800c\u4e14\u8fd9\u4e9b\u5c5e\u6027\u5728\u6570\u636e\u4e2d\u4ea4\u7ec7\u5728\u4e00\u8d77\uff0c\u5f62\u6210\u4e86\u590d\u6742\u7684\u751f\u7269\u4fe1\u53f7\u7f51\u7edc\u3002\u4f46\u662f\uff0c\u5728\u5b9e\u9645\u7684\u7814\u7a76\u4e2d\uff0c\u90e8\u5206\u7a81\u51fa\u7684\u4fe1\u606f\u53ef\u80fd\u4f1a\u4f7f\u6211\u4eec\u5ffd\u7565\u5173\u952e\u7684\u751f\u7269\u5b66\u9690\u85cf\u5c5e\u6027\u3002\u6bd4\u5982\uff0c\u5728\u4e00\u5f20\u5178\u578b\u7684 UMAP \u964d\u7ef4\u56fe\u4e2d\uff0c\u7ec6\u80de\u7c7b\u578b\u5f80\u5f80\u4f1a\u5728\u964d\u7ef4\u540e\u7684\u4e3b\u6210\u5206\u4e2d\u8868\u73b0\u7684\u5dee\u5f02\u6700\u5927\uff0c\u5373\u53ef\u4ee5\u5728\u56fe\u4e2d\u5c06\u4e0d\u540c\u7684\u7ec6\u80de\u5206\u5f00\uff0c\u4f46\u6b64\u65f6\u53ef\u80fd\u4f1a\u4f7f\u6211\u4eec\u5ffd\u7565\u6389\u4e00\u4e9b\u9690\u85cf\u7684\u751f\u7269\u5b66\u5c5e\u6027\u3002\u4e3a\u4e86\u66f4\u597d\u7684\u4f7f\u5c0f\u4f19\u4f34\u4eec\u4e0d\u6f0f\u6389\u91cd\u8981\u7684\u4fe1\u606f\uff0c\u6240\u4ee5\u5927\u6d77\u54e5\u8981\u4ea4\u4e2a\u5927\u5bb6\u4e00\u4e2a\u65b0\u7684python\u5305SiFT\u3002SiFT\u662f\u4e00\u79cd\u57fa\u4e8e\u6838\u5fc3\u7684\u6295\u5f71\u65b9\u6cd5\uff0c\u4e13\u95e8\u7528\u4e8e\u8fc7\u6ee4\u5355\u7ec6\u80de\u6570\u636e\u4e2d\u7684\u751f\u7269\u4fe1\u53f7\uff0c\u4ee5\u63ed\u9732\u6f5c\u5728\u7684\u3001\u9690\u85cf\u5728\u6570\u636e\u80cc\u540e\u7684\u751f\u7269\u8fc7\u7a0b\u3002SiFT\u7684\u8bbe\u8ba1\u76ee\u6807\u662f\u5e7f\u6cdb\u4e14\u5177\u6709\u9002\u5e94\u6027\uff0c\u4e0d\u4ec5\u80fd\u591f\u4ece\u6570\u636e\u4e2d\u79fb\u9664\u4e0d\u9700\u8981\u7684\u53d8\u5f02\uff0c\u8fd8\u80fd\u63ed\u793a\u9690\u85cf\u7684\u751f\u7269\u7ed3\u6784\u3002<\/p>\n\n\n\n

SiFT\u7b97\u6cd5\u7684\u6982\u89c8<\/strong><\/strong><\/p>\n\n\n\n

1a\u7684\u6982\u5ff5\u6027\u63d2\u56fe\u8bf4\u660e\u4e86SiFT\u7b97\u6cd5\u5e94\u7528\u4e8e\u6bcf\u4e2a\u7ec6\u80de\u5177\u6709\u4e24\u4e2a\u5c5e\u6027\uff08\u5f62\u72b6\u548c\u989c\u8272\uff09\u7684\u60c5\u51b5\u3002\u5e94\u7528SiFT\u5c06\u66b4\u9732\u5f62\u72b6\u5c5e\u6027\uff0c\u57fa\u4e8e\u6211\u4eec\u5bf9\u989c\u8272\u7ed3\u6784\u7684\u73b0\u6709\u77e5\u8bc6\u3002\u56fe\u50cf\u7531BioRender.com\u521b\u5efa\u30021b\u662f\u8f93\u5165<\/strong>\uff1bSiFT\u63a5\u53d7\u4e00\u4e2a\u8ba1\u6570\u77e9\u9635\u548c\u9884\u5148\u8ba1\u7b97\u597d\u7684\u7ec6\u80de\u6620\u5c04\u4f5c\u4e3a\u8f93\u5165\u3002\u6620\u5c04\u53ef\u4ee5\u662f\u8fde\u7eed\u7684\u6216\u79bb\u6563\u7684\uff0c\u4e5f\u53ef\u4ee5\u662f\u5355\u53d8\u91cf\u7684\u6216\u591a\u7ef4\u7684\u3002\u56fe\u50cf\u7531BioRender.com\u521b\u5efa\u30021c\u662f\u7ec6\u80de-\u7ec6\u80de\u76f8\u4f3c\u6027\u6838\u5fc3\u8ba1\u7b97<\/strong>\uff1b\u6839\u636e\u7ed9\u5b9a\u7684\u4fe1\u53f7\u6620\u5c04\u8ba1\u7b97\u7ec6\u80de-\u7ec6\u80de\u76f8\u4f3c\u6027\u6838\u5fc3\u3002\u5217\u5bf9\u5e94\u4e0d\u540c\u7684\u6838\u5fc3\uff0c\u6620\u5c04\u6838\u5fc3\uff08\u5de6\uff09\uff0cknn\u6838\u5fc3\uff08\u4e2d\uff09\uff0c\u4ee5\u53ca\u8ddd\u79bb\u6838\u5fc3\uff08\u53f3\uff09\u3002\u9876\u90e8\u884c\u5c55\u793a\u4e86\u6838\u5fc3\u6355\u83b7\u7684\u7ec6\u80de\u76f8\u4f3c\u6027\u7ed3\u6784\uff0c\u5e95\u90e8\u884c\u5c55\u793a\u4e86\u7ec6\u80de-\u7ec6\u80de\u76f8\u4f3c\u6027\u6838\u5fc3\u30021d\u662f\u6295\u5f71\u8fc7\u6ee4<\/strong>\uff1b\u901a\u8fc7\u5c06\u6838\u5fc3\u6295\u5f71\u5230\u8ba1\u6570\u77e9\u9635\u4e0a\u5e76\u4ece\u539f\u59cb\u8ba1\u6570\u77e9\u9635\u4e2d\u63a8\u5bfc\u51fa\u6295\u5f71\u6765\u6267\u884c\u8fc7\u6ee4<\/strong>\u30021e\u662f\u540e\u7eed\u5206\u6790<\/strong>\uff1b\u8fc7\u6ee4\u540e\uff0c\u9690\u85cf\u7ed3\u6784\u88ab\u66b4\u9732\u5e76\u4e14\u53ef\u4ee5\u5728\u540e\u7eed\u5206\u6790\u4e2d\u8f7b\u677e\u6062\u590d\u3002SiFT\u5141\u8bb8\u6839\u636e\u9690\u85cf\u4fe1\u53f7\u6807\u8bb0\uff08\u5de6\uff09\uff0c\u589e\u5f3a\u57fa\u56e0\u8d8b\u52bf\uff08\u4e2d\uff09\uff0c\u5e76\u4f7f\u7528\u53c2\u8003\u5bf9\u7167\u7fa4\u4f53\u6765\u8bc6\u522b\u5bf9\u6848\u4f8b\u53cd\u5e94\u7684\u7ec6\u80de\uff0c\u4ece\u800c\u7ea0\u6b63\u5929\u771f\u7684\u4e30\u5ea6\u6d4b\u8bd5\uff0c\u5e76\u8bc6\u522b\u7c7b\u578bB\u7684\u7ec6\u80de\u5305\u542b\u66f4\u591a\u75be\u75c5\u72b6\u6001\u7684\u4fe1\u606f\u6027\u7ec6\u80de\u7fa4\u4f53\uff08\u53f3\uff09\u3002<\/strong><\/p>\n\n\n\n

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

\u5bf9\u4e86\uff0c\u6709\u4ec0\u4e48\u751f\u4fe1\u5206\u6790\u4e0a\u7684\u95ee\u9898\u5927\u5bb6\u5c3d\u7ba1\u54a8\u8be2\u5927\u6d77\u54e5\uff01\u6ca1\u6709\u65f6\u95f4\u5b66\u4e60\u7684\u5c0f\u4f19\u4f34\u4eec\u4e5f\u4e0d\u8981\u7740\u6025\u54e6\uff01\u6709\u9700\u8981\u751f\u4fe1\u5206\u6790\u7684\u5c0f\u4f19\u4f34\u4eec\u4e5f\u53ef\u4ee5\u627e\u5927\u6d77\u54e5\u54e6\uff01\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\u4ece\u5206\u6790\u5230\u53ef\u89c6\u5316\u76f4\u5230\u4f60\u6ee1\u610f\u4e3a\u6b62\uff01<\/p>\n\n\n\n

\u751f\u4fe1\u6570\u636e\u5904\u7406\u8d77\u6765\u5360\u7528\u5185\u5b58\u5b9e\u5728\u592a\u5927\u4e86\uff0c\u653e\u8fc7\u81ea\u5df1\u7684\u7535\u8111\u5427\uff01\u5927\u6d77\u54e5\u5728\u8fd9\u91cc\u7ed9\u5927\u5bb6\u9001\u4e0a\u798f\u5229\u4e86\uff0c\u6709\u9700\u8981\u670d\u52a1\u5668\u7684\u5c0f\u4f19\u4f34\u4eec\uff0c\u6b22\u8fce\u5927\u5bb6\u8054\u7cfb\u5927\u6d77\u54e5\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

SiFT \u7684\u5b89\u88c5<\/strong><\/strong><\/p>\n\n\n\n

SiFT \u57fa\u4e8e python \u8bed\u8a00\u73af\u5883\uff0c\u5728\u914d\u7f6e\u597d Python \u73af\u5883\u7684\u524d\u63d0\u4e0b\uff0c\u53ef\u4ee5\u5728\u547d\u4ee4\u884c\u4e2d\u8f93\u5165\u4ee5\u4e0b\u4ee3\u7801\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n\n\n\n

pip install sift-sc<\/p>\n\n\n\n

\u8bfb\u5165\u6570\u636e\u5e76\u521d\u6b65\u53ef\u89c6\u5316<\/strong><\/strong><\/p>\n\n\n\n

import numpy as np<\/p>\n\n\n\n

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

import sift<\/p>\n\n\n\n

\u8bfb\u5165\u793a\u4f8b\u6570\u636e\uff0c\u5927\u6982700M\uff0c\u793a\u4f8b\u6570\u636e\u7684\u4e0b\u8f7d\u94fe\u63a5\u5982\u4e0b\uff1a<\/p>\n\n\n\n

\nhttps:\/\/drive.google.com\/file\/d\/1onaka32WOxtUzk9fuRGO0E-Fb60KEoU5\/view?usp=sharing\n<\/div><\/figure>\n\n\n\n

DATA_DIR = “…\/drosophila.annotated.h5ad”  # set path to anndata<\/p>\n\n\n\n

adata = sc.read(DATA_DIR)<\/p>\n\n\n\n

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

adata<\/p>\n\n\n\n

# \u6b64\u65f6\u7684adata\u4e3aAnnData\u5bf9\u8c61<\/p>\n\n\n\n

#AnnData object with n_obs \u00d7 n_vars = 19885 \u00d7 3387<\/p>\n\n\n\n

#    obs: ‘batch’, ‘lncRNA:roX1_cutoff’, ‘lncRNA:roX2_cutoff’, ‘sex’, ‘S_#score’, ‘G2M_score’, ‘phase’, ‘phase_sex’<\/p>\n\n\n\n

#    uns: ‘batch_colors’, ‘cell_cycle_genes’, ‘log1p’, ‘phase_colors’, ‘ph#ase_sex_colors’, ‘sex_colors’, ‘sex_genes’<\/p>\n\n\n\n

#    layers: ‘counts’<\/p>\n\n\n\n

\u968f\u540e\u6211\u4eec\u6267\u884cPCA\u5206\u6790\u3001\u6784\u5efa\u7ec6\u80de\u4e34\u8fd1\u56fe\u5e76\u6267\u884cUMAP\u5206\u6790\uff0c\u6700\u540e\u8fdb\u884c\u53ef\u89c6\u5316<\/p>\n\n\n\n

sc.tl.pca(adata_ref)<\/p>\n\n\n\n

sc.pp.neighbors(adata_ref)<\/p>\n\n\n\n

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

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

sc.pl.umap(<\/p>\n\n\n\n

    adata_ref,<\/p>\n\n\n\n

    color=[“phase”, “sex”, “phase_sex”, “PCNA”, “lncRNA:roX1”, “Nrt”],<\/p>\n\n\n\n

    title=[<\/p>\n\n\n\n

        “cell cycle phase”,<\/p>\n\n\n\n

        “sex”,<\/p>\n\n\n\n

        “cc phase & sex”,<\/p>\n\n\n\n

        “PCNA\\n(cc marker)”,<\/p>\n\n\n\n

        “lncRNA:roX1\\n(sex marker)”,<\/p>\n\n\n\n

        “Nrt\\n(biological marker)”,<\/p>\n\n\n\n

    ],<\/p>\n\n\n\n

    frameon=False,<\/p>\n\n\n\n

    wspace=0.15,<\/p>\n\n\n\n

    ncols=3,<\/p>\n\n\n\n

)<\/p>\n\n\n\n

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

UMAP \u5d4c\u5165\u9075\u5faa\u4e0d\u540c\u7684\u6570\u636e\u6821\u6b63\u7a0b\u5e8f\uff08\u884c\uff09\u5e76\u7531\u4e0d\u540c\u7684\u534f\u53d8\u91cf\u7740\u8272\uff0c\u4ee3\u8868\u4e0d\u9700\u8981\u7684\u53d8\u5f02\u6e90\u548c\u6240\u9700\u7684\u751f\u7269\u4fe1\u53f7\uff08\u5217\uff09\u3002\u884c\uff08\u4ece\u4e0a\u5230\u4e0b\uff09\u663e\u793a\u672a\u6821\u6b63\u7684\u6570\u636e\uff08\u539f\u59cb\u6570\u636e\uff09\u3001\u4f7f\u7528 knn \u6838 \uff08SiFT\uff09 \u7684 SiFT \u6ee4\u6ce2\u3001Sampy \u7684 scanpy.pp.regress_out\uff08\uff09 \uff08regress_out\uff09 \u548c\u5177\u6709\u8fde\u7eed\u534f\u53d8\u91cf \uff08scVI\uff09 \u7684 scVI \u6f5c\u5728\u7a7a\u95f4\u3002\u5217\uff08\u4ece\u5de6\u5230\u53f3\uff09\u663e\u793a\u4e86\u6309\u6279\u6b21\u6807\u8bb0\u3001\u6027\u522b\u6807\u8bb0\u3001\u7ec6\u80de\u5468\u671f\u9636\u6bb5\u548c Nrt\uff08\u53c2\u8003\u6587\u732e\u4e2d\u9274\u5b9a\u7684\u4e00\u79cd\u65b0\u578b Hedgehog \u9776\u57fa\u56e0\uff09\u7740\u8272\u7684\u7ec6\u80de\u3002\u53ef\u4ee5\u770b\u5230\u6b64\u65f6\u7684\u964d\u7ef4\u660e\u663e\u662f\u5177\u6709\u7ec6\u80de\u5468\u671f\u3001\u6027\u522b\u7279\u5f02\u6027\u7684\u3002\u540c\u65f6\uff0c\u4e0a\u56fe\u8fd8\u5c55\u793a\u4e86\u7ec6\u80de\u5468\u671f\u3001\u6027\u522b\u76f8\u5173\u7684\u4e00\u4e9b marker \u7684\u5206\u5e03\uff0c\u4e5f\u540c\u6837\u9a8c\u8bc1\u4e86\u8fd9\u4e2a\u7ed3\u8bba\uff1a<\/p>\n\n\n\n

    \n
  • cell cycle marker: PCNA<\/li>\n\n\n\n
  • sex marker: lncRNA:roX1<\/li>\n\n\n\n
  • biological marker: Nrt<\/li>\n<\/ul>\n\n\n\n

    \u6267\u884c SiFT \u5206\u6790<\/strong><\/strong><\/p>\n\n\n\n

    \u57fa\u4e8e\u7ec6\u80de\u5468\u671f\u3001\u6027\u522b\u76f8\u5173\u7684\u5e72\u6270\u57fa\u56e0\u8bbe\u7f6e SiFT \u8fc7\u6ee4\u7684 adata\uff0c\u968f\u540e\u5c06\u5e72\u6270\u57fa\u56e0\uff08\u6027\u522b\u57fa\u56e0\u548c\u7ec6\u80de\u5468\u671f\u57fa\u56e0\uff09\u7684\u8868\u8fbe\u590d\u5236\u5230 adata.obsm \u4e2d\uff0c\u5e76\u4ece\u8868\u8fbe\u77e9\u9635\u4e2d\u79fb\u9664\u8fd9\u4e9b\u57fa\u56e0\u3002<\/p>\n\n\n\n

    nuisance_genes = np.concatenate((adata.uns[“sex_genes”], adata.uns[“cell_cycle_genes”]))<\/p>\n\n\n\n

    adata.obsm[“nuisance_genes”] = adata[:, nuisance_genes].X<\/p>\n\n\n\n

    adata.uns[“nuisance_genes”] = nuisance_genes<\/p>\n\n\n\n

    gene_subset = [g for g in adata.var_names if g not in nuisance_genes]<\/p>\n\n\n\n

    adata = adata[:, gene_subset].copy()<\/p>\n\n\n\n

    \u8bbe\u7f6e\u53c2\u6570<\/p>\n\n\n\n

    metric\uff1a\u7528\u4e8e SiFT \u5185\u6838\u7684\u6307\u6807\u3002\u8fd9\u91cc\u6211\u4eec\u8003\u8651 k-NN \u5185\u6838\u3002<\/p>\n\n\n\n

    n_neighbors\uff1a\u5bf9\u4e8e k-NN \u5185\u6838\uff0c\u6211\u4eec\u53ef\u4ee5\u6307\u5b9a\u4f7f\u7528\u7684\u8fd1\u90bb\u6570\u91cf\u3002<\/p>\n\n\n\n

    kernel_key\uff1a\u7528\u4e8e\u5b9a\u4e49\u6838\u7684anndata\u4e2d\u7684\u952e<\/p>\n\n\n\n

    metric_ = “knn”<\/p>\n\n\n\n

    n_neighbors_ = 5<\/p>\n\n\n\n

    kernel_key_ = “nuisance_genes”<\/p>\n\n\n\n

    ##\u6267\u884cSIFT\u5206\u6790<\/p>\n\n\n\n

    sft = sift.SiFT(<\/p>\n\n\n\n

        adata=adata,<\/p>\n\n\n\n

        kernel_key=kernel_key_,<\/p>\n\n\n\n

        n_neighbors=n_neighbors_,<\/p>\n\n\n\n

        metric=metric_,<\/p>\n\n\n\n

        copy=True,<\/p>\n\n\n\n

    )<\/p>\n\n\n\n

    \u6211\u4eec\u53ef\u4ee5\u4f7f\u7528 plot_kernel()\u53ef\u89c6\u5316\u7ec6\u80de\u76f8\u4f3c\u6027\u77e9\u9635\uff1a<\/p>\n\n\n\n

    \u53c2\u6570\uff1a<\/p>\n\n\n\n

      \n
    • groupby\uff1a\u6211\u4eec\u53ef\u4ee5\u5bf9\u7ec6\u80de\u8fdb\u884c\u5206\u7ec4\u3002<\/li>\n\n\n\n
    • color_palette\uff1a\u7ec4\u7684\u989c\u8272\u3002<\/li>\n<\/ul>\n\n\n\n

      sft.plot_kernel(<\/p>\n\n\n\n

          groupby=”phase_sex”, color_palette=adata.uns[“phase_sex_colors”], ncol=3<\/p>\n\n\n\n

      )<\/p>\n\n\n\n

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

      \u5b9e\u9a8c\u6570\u636e\u901a\u5e38\u5305\u542b\u4e0d\u9700\u8981\u7684\u53d8\u5f02\u6e90\uff0c\u8fd9\u4e9b\u53d8\u5f02\u6e90\u63a9\u76d6\u4e86\u611f\u5174\u8da3\u7684\u751f\u7269\u4fe1\u53f7\u3002\u8fd9\u4e9b\u4fe1\u53f7\u53ef\u4ee5\u662f\u79bb\u6563\u7684\uff08\u4f8b\u5982\uff0c\u6027\u522b\u6807\u7b7e\uff09\u6216\u8fde\u7eed\u7684\uff08\u4f8b\u5982\uff0c\u7ec6\u80de\u5468\u671f\u9636\u6bb5\uff09\u4fe1\u53f7\u3002\u6240\u9700\u7684\u9884\u5904\u7406\u6b65\u9aa4\u662f\u53bb\u9664\u6b64\u7c7b\u53d8\u5f02\u6e90\u3002\u6700\u4f73\u53bb\u9664\u7a0b\u5e8f\u5e94\uff1a\u5728\u4fdd\u7559\u751f\u7269\u5c5e\u6027\u7684\u540c\u65f6\u6709\u6548\u53bb\u9664\u4e0d\u9700\u8981\u7684\u4fe1\u53f7\uff0c\u5177\u6709\u901a\u7528\u6027\u548c\u9002\u5e94\u6027\uff0c\u5e76\u4e14\u6613\u4e8e\u5305\u542b\u5728\u5206\u6790\u7ba1\u9053\u4e2d\u3002\u6211\u4eec\u5e94\u7528SiFT\u6765\u8fc7\u6ee4\u7ec6\u80de\u5468\u671f\u548c\u6027\u522b\u76f8\u5173\u7684\u53d8\u5f02\u3002<\/p>\n\n\n\n

      \u6267\u884c SiFT \u7684\u8fc7\u6ee4\u6b65\u9aa4\uff0c\u83b7\u5f97\u66f4\u65b0\u7684\u8868\u8fbe\u77e9\u9635\uff1a\u6211\u4eec\u4f7f\u7528filter()\u51fd\u6570\u3002<\/p>\n\n\n\n

      \u53c2\u6570\uff1a
      embedding_key\uff1a\u6211\u4eec\u8981\u4f7f\u7528\u7684 for \u6570\u636e\u5bf9\u8c61\u3002<\/p>\n\n\n\n

      pseudocount\uff1a\u5c06 A \u6dfb\u52a0\u5230\u8fc7\u6ee4\u7684\u5bf9\u8c61\u4e2d\uff0c\u4ee5\u786e\u4fddpseudocount\u7684\u975e\u8d1f\u6027\u3002<\/p>\n\n\n\n

      adata = sft.filter(embedding_key=”X”, pseudocount=False)<\/p>\n\n\n\n

      \u53ef\u89c6\u5316\u6700\u7ec8\u7684\u7ed3\u679c<\/strong><\/strong><\/p>\n\n\n\n

      \u6211\u4eec\u89c2\u5bdf\u5bf9\u6807\u8bb0\u57fa\u56e0(\u7ec6\u80de\u5468\u671f\u6807\u8bb0)\u548c(\u6027\u522b\u6807\u8bb0)\u7684\u5e72\u6270\u6548\u5e94\u7684\u53bb\u9664\u3002<\/p>\n\n\n\n

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

      sc.pp.neighbors(adata)<\/p>\n\n\n\n

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

      sc.pl.umap(<\/p>\n\n\n\n

          adata,<\/p>\n\n\n\n

          color=[“phase”, “sex”, “phase_sex”, “PCNA”, “lncRNA:roX1”, “Nrt”],<\/p>\n\n\n\n

          title=[<\/p>\n\n\n\n

              “cell cycle phase”,<\/p>\n\n\n\n

              “sex”,<\/p>\n\n\n\n

              “cc phase & sex”,<\/p>\n\n\n\n

              “PCNA\\n(cc marker)”,<\/p>\n\n\n\n

              “lncRNA:roX1\\n(sex marker)”,<\/p>\n\n\n\n

              “Nrt\\n(biological marker)”,<\/p>\n\n\n\n

          ],<\/p>\n\n\n\n

          frameon=False,<\/p>\n\n\n\n

          wspace=0.15,<\/p>\n\n\n\n

          ncols=3,<\/p>\n\n\n\n

      )<\/p>\n\n\n\n

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

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

      SiFT\uff08Signal FilTering\uff09\u7684\u7814\u7a76\u63ed\u793a\u4e86\u4e00\u4e2a\u5f3a\u5927\u7684\u6846\u67b6\uff0c\u7528\u4e8e\u5728\u5355\u7ec6\u80de\u6570\u636e\u4e2d\u6709\u6548\u5730\u8fc7\u6ee4\u548c\u63ed\u9732\u751f\u7269\u8fc7\u7a0b\u3002\u901a\u8fc7\u8ba1\u7b97\u6982\u7387\u7ec6\u80de-\u7ec6\u80de\u76f8\u4f3c\u6027\u6838\u5fc3\uff0cSiFT\u80fd\u591f\u7cbe\u786e\u5730\u6355\u6349\u548c\u8fc7\u6ee4\u51fa\u7279\u5b9a\u7684\u751f\u7269\u4fe1\u53f7\uff0c\u4ece\u800c\u63ed\u793a\u90a3\u4e9b\u53ef\u80fd\u88ab\u5176\u4ed6\u4fe1\u53f7\u63a9\u76d6\u7684\u7ec6\u80de\u5c5e\u6027\u3002\u8fd9\u79cd\u65b9\u6cd5\u7684\u4f18\u52bf\u5728\u4e8e\u5176\u5e7f\u6cdb\u7684\u9002\u7528\u6027\u548c\u7075\u6d3b\u6027\uff0c\u4e0d\u4ec5\u80fd\u591f\u4ece\u6570\u636e\u4e2d\u79fb\u9664\u4e0d\u9700\u8981\u7684\u53d8\u5f02\uff0c\u8fd8\u80fd\u63ed\u793a\u9690\u85cf\u7684\u751f\u7269\u7ed3\u6784\u3002SiFT\u5728\u591a\u4e2a\u6848\u4f8b\u4e2d\u5c55\u793a\u4e86\u5176\u80fd\u529b\uff0c\u5305\u62ec\u589e\u5f3a\u809d\u810f\u663c\u591c\u8282\u5f8b\u4fe1\u53f7\u3001\u6062\u590d\u7a7a\u95f4\u5206\u8fa8\u809d\u810f\u6570\u636e\u4e2d\u7684\u518d\u751f\u7ec6\u80de\u4e9a\u7fa4\uff0c\u4ee5\u53ca\u8bc6\u522b\u4e0eCOVID-19\u75be\u75c5\u76f8\u5173\u7684\u7ec6\u80de\u3001\u9014\u5f84\u548c\u52a8\u6001\u3002SiFT\u53ca\u7c7b\u4f3c\u5de5\u5177\u7684\u51fa\u73b0\u9884\u793a\u7740\u5355\u7ec6\u80de\u6570\u636e\u5206\u6790\u9886\u57df\u7684\u65b0\u7bc7\u7ae0\u3002\u5b83\u4eec\u4e0d\u4ec5\u4e3a\u751f\u7269\u5b66\u7814\u7a76\u63d0\u4f9b\u4e86\u66f4\u6df1\u5c42\u6b21\u7684\u6d1e\u5bdf\uff0c\u800c\u4e14\u4e3a\u5904\u7406\u548c\u5206\u6790\u65e5\u76ca\u589e\u957f\u7684\u590d\u6742\u751f\u7269\u6570\u636e\u96c6\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684\u5de5\u5177\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","protected":false},"excerpt":{"rendered":"

      \u524d\u8a00 \u5929\u7a7a\u4e00\u58f0\u5de8\u54cd\uff0c\u5927\u6d77\u54e5\u95ea\u4eae\u767b\u573a\uff01\u5f00\u59cb\u4eca\u5929\u7684\u5206\u4eab\u4e4b\u524d\uff0c\u5c0f\u4f19\u4f34\u4eec\u7ad6\u8d77\u8033\u6735\u542c\u542c\u5927\u6d77\u54e5\u7684\u95ee\u9898\uff01\u5355\u7ec6\u80de\u57fa\u56e0\u8868\u8fbe\u8c31\u7684\u90e8 […]<\/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\/60913"}],"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=60913"}],"version-history":[{"count":1,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/60913\/revisions"}],"predecessor-version":[{"id":60918,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/60913\/revisions\/60918"}],"wp:attachment":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=60913"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=60913"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=60913"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}