{"id":2759,"date":"2019-04-09T20:48:35","date_gmt":"2019-04-09T12:48:35","guid":{"rendered":"http:\/\/www.chenlianfu.com\/?p=2759"},"modified":"2019-04-10T00:00:09","modified_gmt":"2019-04-09T16:00:09","slug":"%e4%bd%bf%e7%94%a8animaltfdb3-0%e5%af%b9%e5%8a%a8%e7%89%a9%e5%9f%ba%e5%9b%a0%e7%bb%84%e7%9a%84%e8%bd%ac%e5%bd%95%e5%9b%a0%e5%ad%90%e8%bf%9b%e8%a1%8c%e6%b3%a8%e9%87%8a","status":"publish","type":"post","link":"http:\/\/www.chenlianfu.com\/?p=2759","title":{"rendered":"\u4f7f\u7528AnimalTFDB3.0\u5bf9\u52a8\u7269\u57fa\u56e0\u7ec4\u7684\u8f6c\u5f55\u56e0\u5b50\u8fdb\u884c\u6ce8\u91ca"},"content":{"rendered":"\n<h2>1. \u52a8\u7269\u8f6c\u5f55\u56e0\u5b50\u6570\u636eAnimalTFDB3.0\u7b80\u4ecb<\/h2>\n\n\n\n<p><a rel=\"noreferrer noopener\" aria-label=\"\u52a8\u7269\u8f6c\u5f55\u56e0\u5b50\u6570\u636e\u5e93AnimalTFDB3.0\uff08\u5728\u65b0\u7a97\u53e3\u6253\u5f00\uff09\" href=\"http:\/\/bioinfo.life.hust.edu.cn\/AnimalTFDB\/#!\/\" target=\"_blank\">\u52a8\u7269\u8f6c\u5f55\u56e0\u5b50\u6570\u636e\u5e93AnimalTFDB3.0<\/a>\u5bf997\u4e2a\u52a8\u7269\u57fa\u56e0\u7ec4\u7684\u8f6c\u5f55\u56e0\u5b50\uff08Transcription Factor\uff09\u548c\u8f6c\u5f55\u8f85\u52a9\u56e0\u5b50\uff08Transcription cofactor\uff09\u8fdb\u884c\u4e86\u5f52\u7eb3\u6574\u7406\u3002\u57fa\u4e8eDNA\u7ed3\u5408\u7ed3\u6784\u57df\uff0c\u5c06\u52a8\u7269\u8f6c\u5f55\u56e0\u5b50\u5206\u6210\u4e8673\u4e2a\u57fa\u56e0\u5bb6\u65cf\uff0c\u5c06\u8f6c\u5f55\u8f85\u52a9\u56e0\u5b50\u5206\u6210\u4e8683\u4e2a\u57fa\u56e0\u5bb6\u65cf\u3002<a rel=\"noreferrer noopener\" aria-label=\"\u6b64\u5916\uff0c\u52a8\u7269\u8f6c\u5f55\u56e0\u5b50\u5206\u4e3a\u516d\u5927\u7c7b\uff08Basic Domain Group\u3001Zinc-Coordinating Group\u3001Beta-Scaffold Factors\u3001Helix-turn-helix\u3001Other Alpha-Helix Group\u548cUnclassified Structure\uff09\uff0c\u52a8\u7269\u8f6c\u5f55\u8f85\u52a9\u56e0\u5b50\u4e5f\u5206\u4e3a\u516d\u5927\u7c7b\uff08Co-activator\/repressors\u3001Chromatin Remodeling Factors\u3001General Cofactors\u3001Histone-modifying Enzymes\u3001Cell Cycle\u548cOther Cofactors\uff09\u3002\uff08\u5728\u65b0\u7a97\u53e3\u6253\u5f00\uff09\" href=\"http:\/\/bioinfo.life.hust.edu.cn\/AnimalTFDB\/#!\/family\" target=\"_blank\">\u6b64\u5916\uff0c\u52a8\u7269\u8f6c\u5f55\u56e0\u5b50\u5206\u4e3a\u516d\u5927\u7c7b\uff08Basic Domain Group\u3001Zinc-Coordinating Group\u3001Beta-Scaffold Factors\u3001Helix-turn-helix\u3001Other Alpha-Helix Group\u548cUnclassified Structure\uff09\uff0c\u52a8\u7269\u8f6c\u5f55\u8f85\u52a9\u56e0\u5b50\u4e5f\u5206\u4e3a\u516d\u5927\u7c7b\uff08Co-activator\/repressors\u3001Chromatin Remodeling Factors\u3001General Cofactors\u3001Histone-modifying Enzymes\u3001Cell Cycle\u548cOther Cofactors\uff09\u3002<\/a><\/p>\n\n\n\n<p>\u52a8\u7269\u8f6c\u5f55\u56e0\u5b50\u6570\u636e\u5e93AnimalTFDB3.0\u63d0\u4f9b\u4e86<a rel=\"noreferrer noopener\" aria-label=\"\u7f51\u9875\u5de5\u5177\uff08\u5728\u65b0\u7a97\u53e3\u6253\u5f00\uff09\" href=\"http:\/\/bioinfo.life.hust.edu.cn\/AnimalTFDB\/#!\/predict\" target=\"_blank\">\u7f51\u9875\u5de5\u5177<\/a>\u8fdb\u884c\u8f6c\u5f55\u56e0\u5b50\u5206\u6790\u3002\u8be5\u7f51\u9875\u5de5\u5177\u4e00\u6b21\u4ec5\u652f\u6301\u4e0a\u4f20\u4e0d\u8d85\u8fc71000\u6761\u86cb\u767d\u5e8f\u5217\u3002\u8be5\u7f51\u9875\u5de5\u5177\u91c7\u7528HMM\u7b97\u6cd5\u8fdb\u884c\u8ba1\u7b97\uff0c\u5206\u6790\u901f\u5ea6\u6bd4\u8f83\u5feb\u3002<a rel=\"noreferrer noopener\" aria-label=\"\u6570\u636e\u5e93\u4f5c\u8005\u5bf9\u5927\u90e8\u5206\u8f6c\u5f55\u56e0\u5b50\u5bb6\u65cf\u91c7\u7528\u4e86PFam\u6570\u636e\u5e93\u7684HMM\u6a21\u578b\uff0c\u5e76\u81ea\u5df1\u6784\u5efa\u4e86\u4e00\u4e9b\u8f6c\u5f55\u56e0\u5b50\u5bb6\u65cf\u7684HMM\u6a21\u578b\uff08\u5728\u65b0\u7a97\u53e3\u6253\u5f00\uff09\" href=\"http:\/\/bioinfo.life.hust.edu.cn\/AnimalTFDB\/#!\/document#tf_family\" target=\"_blank\">\u6570\u636e\u5e93\u4f5c\u8005\u5bf9\u5927\u90e8\u5206\u8f6c\u5f55\u56e0\u5b50\u5bb6\u65cf\u91c7\u7528\u4e86PFam\u6570\u636e\u5e93\u7684HMM\u6a21\u578b\uff0c\u5e76\u81ea\u5df1\u6784\u5efa\u4e86\u4e00\u4e9b\u8f6c\u5f55\u56e0\u5b50\u5bb6\u65cf\u7684HMM\u6a21\u578b<\/a>\u3002\u4f46\u4f5c\u8005\u6ca1\u6709\u63d0\u4f9bHMM\u6570\u636e\u5e93\u7684\u4e0b\u8f7d\uff0c\u4ec5\u63d0\u4f9b\u4e8697\u4e2a\u52a8\u7269\u8f6c\u5f55\u56e0\u5b50\u548c\u8f6c\u5f55\u8f85\u52a9\u56e0\u5b50\u86cb\u767d\u5e8f\u5217\u7684FASTA\u683c\u5f0f\u6587\u4ef6\u4e0b\u8f7d\u3002<\/p>\n\n\n\n<p>\u4f7f\u7528AnimalTFDB3.0\u6570\u636e\u5e93\u7684\u7f51\u9875\u5de5\u5177\u4ec5\u80fd\u8fdb\u884c\u8f6c\u5f55\u56e0\u5b50\u5206\u6790\uff0c\u4e14\u7531\u4e8e\u4ec5\u80fd\u652f\u6301\u4e0d\u8d85\u8fc71000\u6761\u5e8f\u5217\u8fdb\u884c\u5206\u6790\u800c\u6bd4\u8f83\u9ebb\u70e6\uff0c\u4e0d\u5229\u4e8e\u52a8\u7269\u5168\u57fa\u56e0\u7ec4\u7684\u8f6c\u5f55\u56e0\u5b50\u5206\u6790\u3002\u4ee5\u4e0b\u8bb2\u89e3\u4e0b\u8f7dAnimalTFDB3.0\u6570\u636e\u5e93FASTA\u6587\u4ef6\uff0c\u5e76\u81ea\u884c\u7f16\u5199\u7a0b\u5e8f\u8fdb\u884c\u8f6c\u5f55\u56e0\u5b50\u548c\u8f6c\u5f55\u8f85\u52a9\u56e0\u5b50\u6ce8\u91ca\u3002<\/p>\n\n\n\n<h2>2. \u4e0b\u8f7dAnimalTFDB3.0\u6570\u636e\u5e93\u86cb\u767d\u5e8f\u5217<\/h2>\n\n\n\n<p>\u9996\u5148\uff0c\u8fdb\u5165AnimalTFDB3.0\u6570\u636e\u5e93\u4e0b\u8f7d\u9875\u9762\uff0c\u91c7\u7528\u590d\u5236\u7c98\u8d34\u65b9\u5f0f\u83b7\u53d697\u4e2a\u7269\u79cd\u7684\u7269\u79cd\u540d\uff0c\u4fdd\u5b58\u5230\u6587\u4ef6species.txt\u4e2d\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>Ailuropoda melanoleuca;Anas platyrhynchos;Anolis carolinensis;Aotus nancymaae;Astyanax mexicanus;Bos taurus;Caenorhabditis elegans;Callithrix jacchus;Canis familiaris;Capra hircus;Carlito syrichta;Cavia aperea;Cavia porcellus;Cebus capucinus;Cercocebus atys;Chinchilla lanigera;Chlorocebus sabaeus;Choloepus hoffmanni;Ciona intestinalis;Ciona savignyi;Colobus angolensis palliatus;Cricetulus griseus chok1gshd;Cricetulus griseus crigri;Danio rerio;Dasypus novemcinctus;Dipodomys ordii;Drosophila melanogaster;Echinops telfairi;Equus caballus;Erinaceus europaeus;Felis catus;Ficedula albicollis;Fukomys damarensis;Gadus morhua;Gallus gallus;Gasterosteus aculeatus;Gorilla gorilla;Heterocephalus glaber female;Heterocephalus glaber male;Homo sapiens;Ictidomys tridecemlineatus;Jaculus jaculus;Latimeria chalumnae;Lepisosteus oculatus;Loxodonta africana;Macaca fascicularis;Macaca mulatta;Macaca nemestrina;Mandrillus leucophaeus;Meleagris gallopavo;Mesocricetus auratus;Microcebus murinus;Microtus ochrogaster;Monodelphis domestica;Mus caroli;Mus musculus;Mus pahari;Mus spretus;Mustela putorius furo;Myotis lucifugus;Nannospalax galili;Nomascus leucogenys;Notamacropus eugenii;Ochotona princeps;Octodon degus;Oreochromis niloticus;Ornithorhynchus anatinus;Oryctolagus cuniculus;Oryzias latipes;Otolemur garnettii;Ovis aries;Pan paniscus;Pan troglodytes;Papio anubis;Pelodiscus sinensis;Peromyscus maniculatus bairdii;Petromyzon marinus;Poecilia formosa;Pongo abelii;Procavia capensis;Propithecus coquereli;Pteropus vampyrus;Rattus norvegicus;Rhinopithecus bieti;Rhinopithecus roxellana;Saimiri boliviensis boliviensis;Sarcophilus harrisii;Sorex araneus;Sus scrofa;Taeniopygia guttata;Takifugu rubripes;Tetraodon nigroviridis;Tupaia belangeri;Tursiops truncatus;Vicugna pacos;Xenopus tropicalis;Xiphophorus maculatus<\/code><\/pre>\n\n\n\n<p>\u7136\u540e\uff0c\u6839\u636e\u7269\u79cd\u540d\uff0c\u7f16\u5199\u4e0b\u8f7d\u6570\u636e\u5e93\u6587\u4ef6\u7684\u811a\u672c\uff08\u6bcf\u4e2a\u7269\u79cd\u4e0b\u8f7d4\u4e2a\u6570\u636e\u6587\u4ef6\uff09\u5e76\u6279\u91cf\u4e0b\u8f7d\u6570\u636e\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>$ mkdir \/opt\/biosoft\/AnimalTFDB3.0\n$ cd \/opt\/biosoft\/AnimalTFDB3.0\n\n\u751f\u6210\u6587\u4ef6species.list\uff0c\u5305\u542b97\u4e2a\u7269\u79cd\u540d\uff0c\u6bcf\u884c\u4e00\u4e2a\u7269\u79cd\u540d\u3002\u6839\u636ehttp:\/\/bioinfo.life.hust.edu.cn\/AnimalTFDB\/#!\/download\u7f51>\u9875\u4e2d\u7684\u4fe1\u606f\uff0c\u4f7f\u7528vim\u7f16\u8f91\u548cperl\u5355\u884c\u547d\u4ee4\u6293\u53d6\u5168\u90e8\u7684\u7269\u79cd\u540d\u4fe1\u606f\u3002\n$ perl -p -i -e 's\/;\/\\n\/g;' species.txt\n\n$ mkdir data_of_97_species\n$ cd data_of_97_species\n$ perl -e 'while (&lt;>) { chomp; s\/\\s+\/_\/g; print \"wget http:\/\/bioinfo.life.hust.edu.cn\/static\/AnimalTFDB3\/download\/$_\\_TF_protein.fa\\nwget http:\/\/bioinfo.life.hust.edu.cn\/static\/AnimalTFDB3\/download\/$_\\_Cof_protein.fa\\nwget http:\/\/bioinfo.life.hust.edu.cn\/static\/AnimalTFDB3\/download\/$_\\_TF\\nwget http:\/\/bioinfo.life.hust.edu.cn\/static\/AnimalTFDB3\/download\/$_\\_TF_cofactors\\n\"; }' ..\/species.list > download.list\n$ ParaFly -c download.list -CPU 2\n\nCaenorhabditis_elegans\u7684FASTA\u6587\u4ef6\u6709\u95ee\u9898\uff0c\u5b58\u5728\u5e8f\u5217\u540d\u4e00\u81f4\u7684\u591a\u6761\u5e8f\u5217\uff0c\u63a8\u8350\u8fdb\u884c\u4fee\u6539\u3002\n$ perl -p -i -e 's\/>(\\S+)\\t(\\S+)\/>$2\\t$1\/' data_of_97_species\/Caenorhabditis_elegans_*_protein.fa\n$ cd ..<\/code><\/pre>\n\n\n\n<p>\u5206\u522b\u5408\u5e76\u8f6c\u5f55\u56e0\u5b50\u6570\u636e\u5e93\u548c\u8f6c\u5f55\u8f85\u52a9\u56e0\u5b50\u6570\u636e\u5e93\u7684FASTA\u6587\u4ef6\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>\u5f97\u5230\u8f6c\u5f55\u56e0\u5b50\u5e8f\u5217\u6570\u636e\u5e93\uff0cFASTA\u6587\u4ef6\u5934\u90e8\u4ec5\u5305\u542b\u5e8f\u5217\u540d\u548c\u57fa\u56e0\u5bb6\u65cf\u4fe1\u606f\u3002\n$ cat data_of_97_species\/*TF_protein.fa > AnimalTFDB3.0_TF_protein.fasta\n$ perl -p -i -e 's\/^(>\\S+)\\t.*?\\t.*?\\t\/$1\\t\/' AnimalTFDB3.0_TF_protein.fasta\n\n\n\u5f97\u5230\u8f6c\u5f55\u8f85\u52a9\u56e0\u5b50\u6570\u636e\u5e93\uff0cFASTA\u6587\u4ef6\u5934\u90e8\u4ec5\u5305\u542b\u5e8f\u5217\u540d\u548c\u57fa\u56e0\u5bb6\u65cf\u4fe1\u606f\u3002\n$ cat data_of_97_species\/*_Cof_protein.fa > AnimalTFDB3.0_Cof_protein.fasta\n\u7531\u4e8eCof_protein.fa\u6587\u4ef6\u4e2d\u4e0d\u5305\u542b\u8f6c\u5f55\u8f85\u52a9\u56e0\u5b50\u57fa\u56e0\u5bb6\u65cf\u4fe1\u606f\uff0c\u9700\u8981\u7f16\u5199\u7a0b\u5e8f\u8bfb\u53d6TF_cofactors\u6587\u4ef6\u4fe1\u606f\u5e76\u5c06\u57fa\u56e0\u5bb6\u65cf\u4fe1\u606f\u5199\u5165FASTA\u6587\u4ef6\n$ perl -e 'while (&lt;>) { @_ = split \/\\t\/; $gf{$_[2]} = $_[3]; } open IN, \"AnimalTFDB3.0_Cof_protein.fasta\"; while (&lt;IN>) { if (m\/^>(\\S+)\\t(\\S+)\/) { if (exists $gf{$1}) {print \">$1\\t$gf{$1}\\n\";} elsif (exists $gf{$2}) {print \">$2\\t$gf{$2}\\n\";} else {print STDERR \"No type: $_\\n\";} } else { print; } }' data_of_97_species\/*_TF_cofactors > aa; mv aa AnimalTFDB3.0_Cof_protein.fasta<\/code><\/pre>\n\n\n\n<h2>3. \u4f7f\u7528DIAMOND\u5c06\u6570\u636e\u5e93\u6240\u6709\u86cb\u767d\u548c\u6570\u636e\u5e93\u81ea\u8eab\u8fdb\u884c\u6bd4\u5bf9\uff0c\u8ba1\u7b97\u6bcf\u4e2a\u57fa\u56e0\u5bb6\u65cf\u7684BLAST\u9608\u503c<\/h2>\n\n\n\n<p>\u4f7f\u7528ALL_VS_ALL\u7684\u65b9\u5f0f\u5206\u522b\u5bf9\u8f6c\u5f55\u56e0\u5b50\u6570\u636e\u5e93\u548c\u8f6c\u5f55\u8f85\u52a9\u56e0\u5b50\u6570\u636e\u5e93\u8fdb\u884cDIAMOND\u6bd4\u5bf9\uff08evalue 1e-5\u3001identity 30%\u4e14coverage 30%\uff09\u3002\u6839\u636eDIAMOND\u6bd4\u5bf9\u7ed3\u679c\uff0c\u5f97\u5230\u6bcf\u4e2a\u8f6c\u5f55\u56e0\u5b50\u5bb6\u65cf\u4e2d\u6bcf\u4e2a\u57fa\u56e0\u7684\u6bd4\u5bf9\u4fe1\u606f\uff08evalue\u3001hitNum\uff09\uff0c\u7f16\u5199\u7a0b\u5e8f\u8fdb\u800c\u8ba1\u7b97\u6bcf\u4e2a\u57fa\u56e0\u5bb6\u65cf\u7684BLAST\u9608\u503c\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>$ diamond --in AnimalTFDB3.0_TF_protein.fasta --db AnimalTFDB3.0_TF_protein\n$ diamond blastp --db AnimalTFDB3.0_TF_protein --query AnimalTFDB3.0_TF_protein.fasta --out TF.tab --outfmt 6 --sensitive --max-target-seqs 50000 --evalue 1e-5 --id 30 --subject-cover 30 --block-size 20.0 --tmpdir \/dev\/shm --index-chunks 1<\/code><\/pre>\n\n\n\n<p>\u7f16\u5199\u7a0b\u5e8fgeneFamily_BLAST_threshold_of_sensitivity.pl\uff0c\u8f93\u5165DIAMOND\u7ed3\u679c\u6587\u4ef6\u548c\u6570\u636e\u5e93FASTA\u6587\u4ef6\uff0c\u5f97\u5230\u5404\u4e2asensitivity\u7ea7\u522b\u4e0a\u6bcf\u4e2a\u57fa\u56e0\u5bb6\u65cf\u7684evalue\u548chitNum\u9608\u503c\u3002<\/p>\n\n\n\n<h2>4. \u5c06\u5168\u57fa\u56e0\u7ec4\u86cb\u767d\u5e8f\u5217\u548c\u6570\u636e\u5e93\u8fdb\u884c\u6bd4\u5bf9\uff0c\u518d\u6839\u636e\u9608\u503c\u6587\u4ef6\u8fdb\u884c\u51c6\u786e\u6ce8\u91ca\u3002<\/h2>\n","protected":false},"excerpt":{"rendered":"<p>1. \u52a8\u7269\u8f6c\u5f55\u56e0\u5b50\u6570\u636eAnimalTFDB3.0\u7b80\u4ecb \u52a8\u7269\u8f6c\u5f55\u56e0\u5b50\u6570\u636e\u5e93Anim &hellip; <a href=\"http:\/\/www.chenlianfu.com\/?p=2759\">\u7ee7\u7eed\u9605\u8bfb <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=\/wp\/v2\/posts\/2759"}],"collection":[{"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2759"}],"version-history":[{"count":8,"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=\/wp\/v2\/posts\/2759\/revisions"}],"predecessor-version":[{"id":2772,"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=\/wp\/v2\/posts\/2759\/revisions\/2772"}],"wp:attachment":[{"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2759"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2759"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.chenlianfu.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2759"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}