{"id":16078,"date":"2023-10-20T15:57:07","date_gmt":"2023-10-20T07:57:07","guid":{"rendered":"http:\/\/www.biocloudservice.com\/wordpress\/?p=16078"},"modified":"2023-10-20T15:57:08","modified_gmt":"2023-10-20T07:57:08","slug":"ncbi-datasets-%e4%b8%8b%e8%bd%bd%e5%ba%8f%e5%88%97%e7%9a%84%e5%88%a9%e5%99%a8","status":"publish","type":"post","link":"http:\/\/www.biocloudservice.com\/wordpress\/?p=16078","title":{"rendered":"NCBI Datasets \u4e0b\u8f7d\u5e8f\u5217\u7684\u5229\u5668"},"content":{"rendered":"

<\/h1>\n

NCBI Datasets\u662f\u4e00\u79cd\u65b0\u7684\u8d44\u6e90\uff0c\u53ef\u4ee5\u8ba9\u60a8\u8f7b\u677e\u5730\u4ece\u8de8NCBI\u6570\u636e\u5e93\u6536\u96c6\u6570\u636e\u3002\u60a8\u53ef\u4ee5\u4f7f\u7528\u5b83\u6765\u67e5\u627e\u548c\u4e0b\u8f7d\u57fa\u56e0\u548c\u57fa\u56e0\u7ec4\u7684\u5e8f\u5217\u3001\u6ce8\u91ca\u548c\u5143\u6570\u636e\uff0c\u4f7f\u7528\u6211\u4eec\u7684\u547d\u4ee4\u884c\u754c\u9762(CLI)\u5de5\u5177\u6216NCBI Datasets web\u754c\u9762\u3002<\/p>\n

\u4e0b\u8f7d\u5e76\u5b89\u88c5<\/h2>\n

\u4e0b\u8f7d\u7684\u94fe\u63a5\u5728\u8fd9\u91cc\uff0c\u6839\u636e\u81ea\u5df1\u7684\u7535\u8111\u7248\u672c\u627e\u5230\u76f8\u5e94\u7684\u5b89\u88c5\u5305<\/p>\n

https:\/\/www.ncbi.nlm.nih.gov\/datasets\/docs\/v2\/download-and-install\/<\/a><\/p>\n

\u5c55\u793alinux\u7cfb\u7edf\u5b89\u88c5\u7684\u6d41\u7a0b\uff1a<\/p>\n

1\u3001\u901a\u8fc7curl\u5b89\u88c5<\/p>\n

\u4e0b\u8f7d datasets:\u00a0curl -o datasets ‘https:\/\/ftp.ncbi.nlm.nih.gov\/pub\/datasets\/command-line\/v1\/linux-amd64\/datasets<\/a>‘<\/p>\n

\u4e0b\u8f7d dataformat:\u00a0curl -o dataformat ‘https:\/\/ftp.ncbi.nlm.nih.gov\/pub\/datasets\/command-line\/v1\/linux-amd64\/dataformat<\/a>‘<\/p>\n

\u4fee\u6539\u4e00\u4e0b\u6743\u9650\uff1achmod +x datasets dataformat<\/p>\n

\u672a\u4fee\u6539\u6743\u9650\u524d\u662f\u4e00\u4e2a\u4e0d\u80fd\u6267\u884c\u7684\u6587\u4ef6\uff08\u8fd9\u91cc\u6211\u7528\u7eff\u8272\u6765\u533a\u5206\u53ef\u4ee5\u6267\u884c\u7684\u547d\u4ee4\uff0c\u5373\u5728\u4ea4\u4e92\u5f0f\u9875\u9762\u53ef\u4ee5\u76f4\u63a5\u952e\u5165\u4f7f\u7528\uff0c\u4f8b\u5982linux\u81ea\u5e26\u7684\u201cls\u201d\u547d\u4ee4\u4e00\u6837\uff09<\/p>\n

\"\/private\/var\/folders\/xd\/jn2f48nj2k52zzgd8wm1j4yr0000gn\/T\/com.kingsoft.wpsoffice.mac\/photoedit2\/20230920203929\/temp.pngtemp\"<\/p>\n

\u4fee\u6539\u6743\u9650\u540e\uff1a<\/p>\n

\"\/private\/var\/folders\/xd\/jn2f48nj2k52zzgd8wm1j4yr0000gn\/T\/com.kingsoft.wpsoffice.mac\/photoedit2\/20230920203954\/temp.pngtemp\"<\/p>\n

datasets -h #\u6d4b\u8bd5\u4f60\u662f\u5426\u5b89\u88c5\u6210\u529f<\/p>\n

2\u3001\u901a\u8fc7conda \u8fdb\u884c\u5b89\u88c5<\/p>\n

\u9996\u5148\u521b\u5efa\u4e00\u4e2aconda\u73af\u5883:\u00a0conda create -n ncbi_datasets<\/p>\n

\u7136\u540e\u6fc0\u6d3b\u8fd9\u4e2a\u73af\u5883:\u00a0conda activate ncbi_datasets<\/p>\n

\u6700\u540e\u901a\u8fc7\u8fd9\u6761\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5:\u00a0conda install -c conda-forge ncbi-datasets-cli”<14″<\/p>\n

\u7528\u6cd5<\/p>\n

\u901a\u8fc7\u4e0a\u8ff0\u7684\u4e0b\u8f7d\uff0c\u5c0f\u82b1\u76f8\u4fe1\u4f60\u5df2\u7ecf\u4e0b\u8f7d\u4e86\u597d\u4e86datasets\uff0c\u4e0b\u9762\u6765\u770b\u770bdatasets\u600e\u4e48\u7528\u53ed\uff5e<\/p>\n

\u7f51\u9875\u7c98\u8d34\u4ee3\u7801<\/h3>\n

\"\/private\/var\/folders\/xd\/jn2f48nj2k52zzgd8wm1j4yr0000gn\/T\/com.kingsoft.wpsoffice.mac\/photoedit2\/20230920234302\/temp.pngtemp\"<\/p>\n

\u6211\u4eec\u53ef\u4ee5\u4ece\u7f51\u4e0a\u770b\u5230\u76f8\u5173\u7684\u4e0b\u8f7d\u4ee3\u7801\uff0c\u590d\u5236\u4e0b\u6765\u5728\u547d\u4ee4\u884c\u8f93\u5165\u76f8\u5173\u4ee3\u7801\u3002<\/p>\n

\"\u622a\u5c4f2023-09-20<\/p>\n

\u590d\u5236\u8fd9\u6bb5\u4ee3\u7801\uff1a<\/p>\n

datasets download genome accession GCF_000002655.1 –include gff3,rna,cds,protein,genome,seq-report –filename GCF_000002655.1.zip<\/p>\n

\u8fd9\u79cd\u65b9\u6cd5\u7ed9\u5c0f\u767d\u5e26\u6765\u7684\u798f\u5229\u54e6\uff5e<\/p>\n

\"\/private\/var\/folders\/xd\/jn2f48nj2k52zzgd8wm1j4yr0000gn\/T\/com.kingsoft.wpsoffice.mac\/photoedit2\/20230922160953\/temp.pngtemp\"<\/p>\n

\"IMG_258\"<\/p>\n

\u5728\u8bb2\u7528\u6cd5\u4e4b\u524d\u6211\u4eec\u5148\u5bf9\u7167\u4e0a\u56fe\u4e86\u89e3\u8fd9\u4e2a\u5c0f\u8f6f\u4ef6\u7684\u6240\u6709\u7528\u6cd5\u3002<\/p>\n

\u57fa\u56e0\u7ec4\u7684\u4e0b\u8f7d<\/h3>\n

#\u5355\u72ec\u4e0b\u8f7d\u67d0\u4e00\u4e2a\u57fa\u56e0\u7ec4\u4fe1\u606f<\/p>\n

datasets download genome accession GCF_000001405.40<\/p>\n

#\u4e0b\u8f7d\u67d0\u4e00\u4e2a\u7269\u79cd\u4e0b\u7684\u6240\u6709\u7684\u57fa\u56e0\u7ec4\u4fe1\u606f<\/p>\n

datasets download genome taxon \u201cCandida lusitaniae\u201d<\/p>\n

#\u4e0b\u8f7d\u4eba\u7c7b\u7684\u57fa\u56e0\u7ec4\u4fe1\u606f<\/p>\n

datasets download genome taxon \u201chuman\u201d –filename human_dataset.zip<\/p>\n

datasets download genome accession GCF_000001405.40 –filename human_GRCh38_dataset.zip<\/p>\n

\u4e0b\u8f7d\u7684\u8fc7\u7a0b\u4e2d\u4f1a\u663e\u793a\uff1a \"\u622a\u5c4f2023-10-08<\/p>\n

\u4e0b\u8f7d\u5b8c\u6210\u540e\u7684\u4fe1\u606f\u4f1a\u663e\u793a\uff1a<\/p>\n

\"\u622a\u5c4f2023-09-20<\/p>\n

\u9664\u6b64\u4e4b\u5916\uff0c\u4ee5BioProject \u65b9\u5f0f\u4e0b\u8f7d<\/p>\n

datasets download genome accession PRJEB33226 –filename sanger_bioproject_dataset.zip<\/p>\n

\u4e0b\u9762\u5c0f\u82b1\u5217\u51fa\u5e38\u7528\u547d\u4ee4\uff0c\u8bfb\u8005\u53ef\u4ee5\u6839\u636e\u81ea\u5df1\u7684\u9700\u6c42\u8fdb\u884c\u9009\u62e9<\/p>\n

#\u4e0b\u8f7d\u4eba\u7c7b\u53c2\u8003\u57fa\u56e0\u7ec4<\/p>\n

datasets download genome taxon human –reference<\/p>\n

\"\u622a\u5c4f2023-10-08<\/p>\n

#\u83b7\u53d6\u6ce8\u91ca\u4eba\u7c7b\u57fa\u56e0\u7ec4\u7684\u6570\u636e<\/p>\n

datasets download genome taxon human –annotated<\/p>\n

\"\u622a\u5c4f2023-10-08<\/p>\n

#\u4ee5\u201c\u5b8c\u6574\u57fa\u56e0\u7ec4\u201d\u7684\u88c5\u914d\u6c34\u5e73\u83b7\u53d6\u4eba\u7c7b\u57fa\u56e0\u7ec4\u6570\u636e<\/p>\n

datasets download genome taxon human –assembly-level complete<\/p>\n

\"\u622a\u5c4f2023-10-08<\/p>\n

#\u83b7\u53d62020\u5e741\u67081\u65e5\u4e4b\u540e\u53d1\u5e03\u7684\u4eba\u7c7b\u57fa\u56e0\u7ec4\u6570\u636e<\/p>\n

datasets download genome taxon human –released-after 01\/01\/2020<\/p>\n

\"\u622a\u5c4f2023-10-08<\/p>\n

#\u83b7\u53d6T2T\u8054\u76df\u63d0\u4ea4\u7684\u4eba\u7c7b\u57fa\u56e0\u7ec4\u6570\u636e<\/p>\n

datasets download genome taxon human –search ‘T2T Consortium’<\/p>\n

\"\u622a\u5c4f2023-10-08<\/p>\n

\u57fa\u56e0\u7684\u4e0b\u8f7d<\/h3>\n

\u9664\u4e86\u57fa\u56e0\u7ec4\u7684\u4e0b\u8f7d\uff0c\u57fa\u56e0\u7684\u4e0b\u8f7d\u4e5f\u662f\u53ef\u4ee5\u89e3\u51b3\u7684\u3002<\/p>\n

#\u57fa\u56e0\u7684\u4e0b\u8f7d<\/p>\n

datasets gene accession<\/p>\n

datasets gene gene-id<\/p>\n

\u901a\u8fc7\u63d0\u4f9b\u5355\u4e2a\u6216\u591a\u4e2a\u57fa\u56e0id(\u7a7a\u683c\u5206\u9694)\u4e0b\u8f7d\u57fa\u56e0\u6570\u636e\u5305\u3002\u5982\u679c\u4f7f\u7528\u2014\u2014inputfile\u9009\u9879\uff0c\u6bcf\u4e2agene-id\u5e94\u8be5\u5728\u5355\u72ec\u7684\u4e00\u884c\u4e2d\u3002<\/p>\n

datasets download gene gene-id 1 2 3 9 10 11 12 13 14 15 16 17<\/p>\n

\"\u622a\u5c4f2023-10-08<\/p>\n

\u6267\u884c\u5982\u4e0b\u547d\u4ee4\uff0c\u6309\u57fa\u56e0\u7b26\u53f7\u4e0b\u8f7d\u57fa\u56e0\u6570\u636e\u5305\u3002<\/p>\n

datasets download gene symbol ACRV1 A2M –taxon human<\/p>\n

\"\u622a\u5c4f2023-10-08<\/p>\n

\u901a\u8fc7RefSeq\u6838\u82f7\u9178\u6216\u86cb\u767d\u8d28\u52a0\u5165\u4e0b\u8f7d\u57fa\u56e0\u6570\u636e\u5305\u3002<\/p>\n

datasets download gene accession NM_020107.5 NP_001334352.2<\/p>\n

\"\u622a\u5c4f2023-10-08<\/p>\n

\u6309\u7269\u79cd\u540d\u79f0\u6216\u5206\u7c7b\u53f7\u4e0b\u8f7d\u57fa\u56e0\u8d44\u6599\u5305\u3002\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4\u4e0b\u8f7d\u6240\u6709\u4eba\u7c7b\u57fa\u56e0\u7684\u57fa\u56e0\u6570\u636e\u5305\u3002<\/p>\n

datasets download gene taxon human<\/p>\n

\"\u622a\u5c4f2023-10-08<\/p>\n

\u771f\u6838\u57fa\u56e0\u6570\u636e\u5305\u9ed8\u8ba4\u5305\u542b\u8f6c\u5f55\u7269\u3001\u86cb\u767d\u8d28\u5e8f\u5217\u548c\u5143\u6570\u636e\uff0c\u800c\u539f\u6838\u6570\u636e\u5305\u542b\u57fa\u56e0\u548c\u86cb\u767d\u8d28\u5e8f\u5217\uff0c\u5916\u52a0\u5143\u6570\u636e\u3002\u53ef\u4ee5\u9009\u62e9\u6dfb\u52a0\u989d\u5916\u7684\u6570\u636e\u6587\u4ef6\uff0c\u6216\u8005\u53ea\u5728\u6570\u636e\u5305\u4e2d\u5305\u542b\u5143\u6570\u636e\uff0c\u4f7f\u7528\u2014\u2014include\u4e00\u4e2a\u6216\u591a\u4e2a\u672f\u8bed\u3002\u4e0b\u9762\u662f\u4e00\u4e9b\u4f7f\u7528\u2014\u2014include\u6807\u5fd7\u6765\u9009\u62e9\u5728\u6570\u636e\u5305\u4e2d\u5305\u542b\u54ea\u4e9b\u6570\u636e\u6587\u4ef6\u7684\u793a\u4f8b\u3002<\/p>\n

\u83b7\u53d6\u4eba\u7c7bBRCA1\u57fa\u56e0(gene-id: 672)\u7684\u57fa\u56e0\u548c\u86cb\u767d\u8d28\u5e8f\u5217:<\/p>\n

datasets download gene gene-id 672 –include gene,protein<\/p>\n

\"\u622a\u5c4f2023-09-22<\/p>\n

\u8fd9\u4e2a\u793a\u4f8b\u4e2d\u83b7\u53d6\u4e86gene-id\u4e3a672\u7684\u57fa\u56e0\u5e8f\u5217ncbi_dataset\/data\/gene.fna\u548c\u86cb\u767d\u8d28\u5e8f\u5217ncbi_dataset\/data\/protein.faa<\/p>\n

\u83b7\u53d6\u4eba\u7c7bBRCA1\u57fa\u56e0(gene-id: 672)\u7684\u57fa\u56e0\u3001\u8f6c\u5f55\u672c\u3001CDS\u548c\u86cb\u767d\u8d28\u5e8f\u5217:<\/p>\n

datasets download gene gene-id 672 –include gene,rna,cds,protein<\/p>\n

\"\u622a\u5c4f2023-09-22<\/p>\n

\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c<\/p>\n

\u83b7\u53d6\u4e00\u4e2a\u53ea\u6709\u57fa\u56e0\u6570\u636e\u62a5\u544a(\u5143\u6570\u636e)\u7684\u6570\u636e\u5305:<\/p>\n

datasets download gene gene-id 672 –include none<\/p>\n

\u5e9e\u5927\u7684\u57fa\u56e0\u7ec4\u7684\u4e0b\u8f7d\u65b9\u6cd5<\/h3>\n

#\u5927\u57fa\u56e0\u7ec4\u7684\u4e0b\u8f7d<\/p>\n

1\u3001\u4e0b\u8f7d\u7684\u547d\u4ee4datasets download genome taxon \u201chuman\u201d –dehydrated<\/p>\n

\u4e0b\u8f7d\u663e\u793a\uff1a<\/p>\n

\"\u622a\u5c4f2023-09-21<\/p>\n

2\u3001\u89e3\u538bunzip ncbi_dataset.zip<\/p>\n

\u8fd9\u6837\u4e0b\u8f7dncbi_dataset.zip\u89e3\u538b\u540e\uff0c\u4f60\u4f1a\u770b\u5230\u5982\u4e0b\u7684<\/p>\n

\"\u622a\u5c4f2023-09-22<\/p>\n

\u5728\u538b\u7f29\u5305\u4e2d\u6587\u4ef6\u4e2dfetch.txt\u5b58\u50a8\u4e86\u4e0b\u8f7d\u7684\u4fe1\u606f<\/p>\n

3\u3001nohup datasets rehydrate –directory .\/<\/p>\n

\u8fd0\u884c\u4e0a\u8ff0\u7684\u547d\u4ee4\u624d\u5f00\u59cb\u4e0b\u8f7d\u76f8\u5173\u7684\u57fa\u56e0\u7ec4\u7684\u4fe1\u606f\u3002\u8fd9\u91cc\u7684\u547d\u4ee4\u6302\u5728\u4e86\u540e\u53f0\uff0c\u5982\u679c\u4e2d\u65ad\u53ef\u4ee5\u518d\u6b21\u63d0\u4ea4\uff0c\u4f1a\u4ece\u4e2d\u65ad\u7684\u5730\u65b9\u518d\u4e0b\u8f7d\u7684\u3002\u8fd9\u4e00\u70b9\u5bf9\u4e8e\u4e0b\u8f7d\u5e9e\u5927\u7684\u57fa\u56e0\u7ec4\u6765\u8bb2\u662f\u975e\u5e38\u7684\u6709\u5229\u7684\u3002<\/p>\n

\u8fd9\u91cc\u5c0f\u82b1\u5f3a\u70c8\u5efa\u8bae\u8d85\u8fc7100\u4e2a\u57fa\u56e0\u7ec4\u4ee5\u4e0a\u91c7\u7528\u4e0a\u8ff0\u7684\u529e\u6cd5\uff0c\u8fdb\u884c\u4e0b\u8f7d\u3002<\/p>\n

\u5982\u679c\u9047\u5230\u4e0d\u61c2\u7684\u4e5f\u53ef\u4ee5\u501f\u52a9\u7ebf\u4e0a\u7684\u4e91\u5e73\u53f0\u54e6\uff5ehttp:\/\/www.biocloudservice.com\/home.html<\/p>\n

\u597d\u4e86\u4eca\u5929\u7684\u5e8f\u5217\u4e0b\u8f7d\u5de5\u5177\u5c31\u8bb2\u5230\u8fd9\u91cc\uff0c\u6b22\u8fce\u5927\u5bb6\u6709\u95ee\u9898\u4e0e\u5c0f\u82b1\u4e00\u8d77\u8ba8\u8bba\u54e6\uff5e<\/p>\n","protected":false},"excerpt":{"rendered":"

NCBI Datasets\u662f\u4e00\u79cd\u65b0\u7684\u8d44\u6e90\uff0c\u53ef\u4ee5\u8ba9\u60a8\u8f7b\u677e\u5730\u4ece\u8de8NCBI\u6570\u636e\u5e93\u6536\u96c6\u6570\u636e\u3002\u60a8\u53ef\u4ee5\u4f7f\u7528\u5b83\u6765\u67e5\u627e\u548c\u4e0b\u8f7d\u57fa […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","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\/16078"}],"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=16078"}],"version-history":[{"count":1,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/16078\/revisions"}],"predecessor-version":[{"id":16100,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/16078\/revisions\/16100"}],"wp:attachment":[{"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=16078"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=16078"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.biocloudservice.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=16078"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}