{"id":682,"date":"2018-08-18T22:32:40","date_gmt":"2018-08-18T13:32:40","guid":{"rendered":"http:\/\/www.ecobioinfo.com\/?p=682"},"modified":"2022-06-05T22:52:08","modified_gmt":"2022-06-05T13:52:08","slug":"dna%e7%9b%b8%e5%90%8c%e6%80%a7%e6%a4%9c%e7%b4%a2%e3%81%a8ai5-16srdna%e5%a1%a9%e5%9f%ba%e9%85%8d%e5%88%97%e3%81%a7%e7%b4%b0%e8%8f%8c%e5%88%86%e9%a1%9e4","status":"publish","type":"post","link":"https:\/\/www.ecobioinfo.com\/?p=682","title":{"rendered":"AI\u8ab2\u984c1\uff1aDNA\u76f8\u540c\u6027\u691c\u7d22\u3068AI(5) 16SrDNA\u5869\u57fa\u914d\u5217\u3067\u7d30\u83cc\u5206\u985e(4)"},"content":{"rendered":"

\uff08\u300c16SrDNA\u5869\u57fa\u914d\u5217\u3067\u7d30\u83cc\u5206\u985e(3)\u300d<\/a>\u306e\u7d9a\u304d\u3067\u3059\u3002\uff09<\/p>\n

\u4eca\u5ea6\u306f\u5b66\u7fd2\u7528\u306e\u30c7\u30fc\u30bf\u91cf\u3092\u5897\u3084\u3057\u3066\u300116SrDNA\u306e\u5869\u57fa\u914d\u5217\u304c 2000\u4ef6\u4ee5\u4e0a\u767b\u9332\u3055\u308c\u3066\u3044\u308b53\u7a2e\u985e\u306e\u5c5e\u306b\u3064\u3044\u3066\u3001\u9577\u3055 1280bp\u5206\u3092\u56fa\u5b9a\u9577\u3092\u5b66\u7fd2\u30c7\u30fc\u30bf\u3068\u3057\u3066\u5b66\u7fd2\u3055\u305b\u3066\u307f\u307e\u3057\u305f\u3002
\n\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306f\u3001\u30ce\u30fc\u30c94096\u306e\u5168\u7d50\u54086\u5c64\u3001\u6d3b\u6027\u5316\u95a2\u6570 ReLU \u306b\u3057\u3066\u3001\u51fa\u529b\u5c64\u306f sigmoid \u3068\u3057\u3001epoch=70 \u3067\u5b66\u7fd2\u3057\u307e\u3057\u305f\u3002<\/p>\n

\u5404 Python \u30d7\u30ed\u30b0\u30e9\u30e0\u306f\u3001\u6587\u5b57\u30b3\u30fc\u30c9 UTF-8\u3001\u30e9\u30a4\u30d6\u30e9\u30ea\u306f tensorflow, keras\u3092\u4f7f\u7528\u3057\u3066\u3044\u307e\u3059\u3002
\n\u30d7\u30ed\u30b0\u30e9\u30e0\u4e2d\u3067\u5b66\u7fd2\u30c7\u30fc\u30bf\u3068\u5b66\u7fd2\u6e08\u307f\u30e2\u30c7\u30eb\u306e\u4fdd\u5b58\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u306f\u3001.\/data\/dna2\/\u3068\u3057\u3066\u3001\u30e2\u30c7\u30eb\u306f JSON\u5f62\u5f0f keras_dna_model.json\u3001\u30a6\u30a8\u30a4\u30c8\u306f h5 \u5f62\u5f0f keras_dna_weights.h5 \u3068\u3057\u3066\u4fdd\u5b58\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n

(1) \u8a72\u5f53\u3059\u308b\u5869\u57fa\u914d\u5217\u3092\u62bd\u51fa<\/p>\n

dnaread2.py<\/a><\/p>\n

(2) DNA\u5869\u57fa\u914d\u5217\u3068\u6b63\u89e3\u306e\u30d5\u30a1\u30a4\u30eb\u3092\u4f5c\u6210<\/p>\n

converttfdata2.py<\/a><\/p>\n

(3) \u5b66\u7fd2\u7528 Pyhon\u30d7\u30ed\u30b0\u30e9\u30e0<\/p>\n

kerasdna53g.py<\/a><\/p>\n

\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u69cb\u6210\u306e\u90e8\u5206\uff08\u4e00\u90e8\u629c\u7c8b\uff09\u2015\u2015\u2015\u2015\u2015\u2015\u2015\u2015\u2015\u2015\u2015\u2015\u2015
\n# \u5168\u7d50\u5408\u578b\u30cd\u30c3\u30c8\u30ef\u30fc\u30af
\nmodel = kr.models.Sequential()
\nmodel.add(kr.layers.Dense(units=4096, input_shape=(maxdnalength,), activation=’relu’))
\nmodel.add(kr.layers.Dense(units=4096, activation=’relu’))
\nmodel.add(kr.layers.Dense(units=4096, activation=’relu’))
\nmodel.add(kr.layers.Dense(units=4096, activation=’relu’))
\nmodel.add(kr.layers.Dense(units=4096, activation=’relu’))
\nmodel.add(kr.layers.Dense(units=4096, activation=’relu’))
\n# \u51fa\u529b\u5c64
\nmodel.add(kr.layers.Dense(units=generacount, activation=’sigmoid’))<\/p>\n

\u7d50\u679c ———
\n\u30c6\u30b9\u30c8 11826\u4ef6 \u6b63\u89e3\u7387 98.2
\n——end<\/p>\n

\u5b9f\u884c\u7d50\u679c\u306f\u3001\u4ee5\u524d\u3088\u308a\u3082\u9ad8\u304f\u51fa\u307e\u3057\u305f\u3002<\/p>\n

(4) \u5b66\u7fd2\u7d50\u679c\u3092\u8aad\u307f\u8fbc\u307f\u30c6\u30b9\u30c8<\/p>\n

\u5b66\u7fd2\u7d50\u679c\u3092\u8aad\u307f\u8fbc\u307f\u3001\u5c5e\u3054\u3068\u306e\u7cbe\u5ea6\u3092\u7b97\u51fa\u3057\u3066\u307f\u307e\u3057\u305f\u3002<\/p>\n

kerasdna53gtest.py<\/a><\/p>\n

\u5b9f\u884c\u7d50\u679c ———<\/p>\n

\u7d50\u679c \u5c5e\u3054\u3068\u306b\u6b63\u89e3\u7387\u3092\u7b97\u51fa———
\nSphingomonas 177\u4ef6\u4e2d \u25ce 99.4 % \u25b3 0.6 % \u2613 0.0 %
\nPseudoalteromonas 251\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nVibrio 116\u4ef6\u4e2d \u25ce 99.1 % \u25b3 0.9 % \u2613 0.0 %
\nPseudomonas 120\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nLactobacillus 240\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nStreptococcus 329\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nBacillus 271\u4ef6\u4e2d \u25ce 99.3 % \u25b3 0.7 % \u2613 0.0 %
\nShewanella 229\u4ef6\u4e2d \u25ce 99.6 % \u25b3 0.0 % \u2613 0.4 %
\nLeuconostoc 239\u4ef6\u4e2d \u25ce 97.5 % \u25b3 1.7 % \u2613 0.8 %
\nPantoea 187\u4ef6\u4e2d \u25ce 98.4 % \u25b3 1.6 % \u2613 0.0 %
\nMicrobacterium 161\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nCorynebacterium 264\u4ef6\u4e2d \u25ce 98.9 % \u25b3 1.1 % \u2613 0.0 %
\nEnterobacter 204\u4ef6\u4e2d \u25ce 92.6 % \u25b3 7.4 % \u2613 0.0 %
\nSerratia 223\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nKlebsiella 366\u4ef6\u4e2d \u25ce 99.7 % \u25b3 0.3 % \u2613 0.0 %
\nBradyrhizobium 229\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nAgrobacterium 195\u4ef6\u4e2d \u25ce 93.8 % \u25b3 5.1 % \u2613 1.0 %
\nStreptomyces 140\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nBurkholderia 274\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nFlavobacterium 166\u4ef6\u4e2d \u25ce 99.4 % \u25b3 0.6 % \u2613 0.0 %
\nLactococcus 230\u4ef6\u4e2d \u25ce 98.3 % \u25b3 1.3 % \u2613 0.4 %
\nBrevundimonas 188\u4ef6\u4e2d \u25ce 98.4 % \u25b3 0.0 % \u2613 1.6 %
\nStenotrophomonas 185\u4ef6\u4e2d \u25ce 99.5 % \u25b3 0.5 % \u2613 0.0 %
\nMycobacterium 180\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nArthrobacter 190\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nStaphylococcus 286\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nCandidatus 260\u4ef6\u4e2d \u25ce 99.2 % \u25b3 0.8 % \u2613 0.0 %
\nAchromobacter 188\u4ef6\u4e2d \u25ce 96.8 % \u25b3 2.1 % \u2613 1.1 %
\nRhodococcus 216\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nEnterococcus 237\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nAcinetobacter 251\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nMesorhizobium 277\u4ef6\u4e2d \u25ce 96.8 % \u25b3 1.4 % \u2613 1.8 %
\nHalomonas 238\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nPsychrobacter 218\u4ef6\u4e2d \u25ce 97.7 % \u25b3 1.4 % \u2613 0.9 %
\nMarinobacter 180\u4ef6\u4e2d \u25ce 95.6 % \u25b3 2.2 % \u2613 2.2 %
\nClostridium 325\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nPaenibacillus 282\u4ef6\u4e2d \u25ce 99.6 % \u25b3 0.4 % \u2613 0.0 %
\nMicrococcus 143\u4ef6\u4e2d \u25ce 93.7 % \u25b3 4.9 % \u2613 1.4 %
\nNocardia 215\u4ef6\u4e2d \u25ce 98.6 % \u25b3 1.4 % \u2613 0.0 %
\nMethylobacterium 192\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nAeromonas 194\u4ef6\u4e2d \u25ce 99.0 % \u25b3 1.0 % \u2613 0.0 %
\nEscherichia 380\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nChryseobacterium 223\u4ef6\u4e2d \u25ce 95.1 % \u25b3 2.7 % \u2613 2.2 %
\nCitrobacter 225\u4ef6\u4e2d \u25ce 80.4 % \u25b3 12.4 % \u2613 7.1 %
\nMicromonospora 272\u4ef6\u4e2d \u25ce 97.8 % \u25b3 1.5 % \u2613 0.7 %
\nRhizobium 238\u4ef6\u4e2d \u25ce 95.0 % \u25b3 5.0 % \u2613 0.0 %
\nCampylobacter 190\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nOchrobactrum 222\u4ef6\u4e2d \u25ce 92.3 % \u25b3 4.1 % \u2613 3.6 %
\nKocuria 187\u4ef6\u4e2d \u25ce 88.2 % \u25b3 6.4 % \u2613 5.3 %
\nLysinibacillus 189\u4ef6\u4e2d \u25ce 96.8 % \u25b3 1.6 % \u2613 1.6 %
\nSalmonella 355\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nVeillonella 12\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\nNeisseria 277\u4ef6\u4e2d \u25ce 100.0 % \u25b3 0.0 % \u2613 0.0 %
\n———
\n\u5408\u8a08 11826\u4ef6\u4e2d \u25ce 98.2 % \u25b3 1.3 % \u2613 0.6 %
\n——end.<\/p>\n

\u7d50\u679c\u306e\u4e00\u89a7\u3092\u307f\u308b\u3068\u3001Citrobacter \u306a\u3069\u6b63\u89e3\u7387\u306e\u7279\u306b\u4f4e\u3044\u5c5e\u304c\u3042\u308a\u307e\u3057\u305f\u3002
\n\u5224\u5225\u304c\u96e3\u3057\u3044\u30b0\u30eb\u30fc\u30d7\u304c\u3042\u308b\u3088\u3046\u3067\u3059\u3002<\/p>\n

 <\/p>\n

(S.Onda 2018\/8\/18)<\/p>\n

 <\/p>\n

 <\/p>\n","protected":false},"excerpt":{"rendered":"\uff08\u300c16SrDNA\u5869\u57fa\u914d\u5217\u3067\u7d30\u83cc\u5206\u985e(3)\u300d\u306e\u7d9a\u304d\u3067\u3059\u3002\uff09 \u4eca\u5ea6\u306f\u5b66\u7fd2\u7528\u306e\u30c7\u30fc\u30bf\u91cf\u3092\u5897\u3084\u3057\u3066\u300116SrDNA\u306e\u5869\u57fa\u914d\u5217\u304c 2000\u4ef6\u4ee5\u4e0a\u767b\u9332\u3055\u308c\u3066\u3044\u308b53\u7a2e\u985e\u306e\u5c5e\u306b\u3064\u3044\u3066\u3001\u9577\u3055 1280bp\u5206\u3092\u56fa\u5b9a\u9577\u3092\u5b66\u7fd2\u30c7\u30fc\u30bf\u3068\u3057\u3066\u5b66 …","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[],"class_list":["post-682","post","type-post","status-publish","format-standard","hentry","category-ai_ecobio"],"_links":{"self":[{"href":"https:\/\/www.ecobioinfo.com\/index.php?rest_route=\/wp\/v2\/posts\/682","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.ecobioinfo.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.ecobioinfo.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.ecobioinfo.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.ecobioinfo.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=682"}],"version-history":[{"count":6,"href":"https:\/\/www.ecobioinfo.com\/index.php?rest_route=\/wp\/v2\/posts\/682\/revisions"}],"predecessor-version":[{"id":1492,"href":"https:\/\/www.ecobioinfo.com\/index.php?rest_route=\/wp\/v2\/posts\/682\/revisions\/1492"}],"wp:attachment":[{"href":"https:\/\/www.ecobioinfo.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=682"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.ecobioinfo.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=682"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.ecobioinfo.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=682"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}