Главная Обзор Помощь
Вход
limour
/
limour-blog.github.io
зеркало из https://dl.limour.top/cf/https://github.com/limour-blog/limour-blog.github.io.git
1
0
Ответвить 0
Файлы Задачи 0
Дерево: 96fb64f47c
Ветки Метки
limour-blog.git...
/
shi-yong-GATK-zhao-SNP.html

shi-yong-GATK-zhao-SNP.html 93 KB
История Исходник

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847 
  1. 

  2. 

  3. <!DOCTYPE html>
    4. 

  4. <html lang="en" data-default-color-scheme=auto>
    5. 

  5. 

  6. 

  7. 

  8. <head><!-- hexo injector head_begin start -->
    9. 

  9. <script defer src="https://api.limour.top/vue/0d2f95c1-755d-436b-adf8-eee12a80ed32/script.js"></script>
    10. 

  10. <!-- hexo injector head_begin end -->
    11. 

  11.   <meta charset="UTF-8">
    12. 

  12.   <link rel="apple-touch-icon" sizes="76x76" href="https://img.limour.top/2023/08/29/64ee07361815a.webp">
    13. 

  13.   <link rel="icon" href="https://img.limour.top/2023/08/29/64ee07361815a.webp">
    14. 

  14.   <meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=5.0, shrink-to-fit=no">
    15. 

  15.   <meta http-equiv="x-ua-compatible" content="ie=edge">
    16. 

  16.   
    17. 

  17.   <meta name="theme-color" content="#2f4154">
    18. 

  18.   <meta name="author" content="Limour">
    19. 

  19.   <meta name="keywords" content="">
    20. 

  20.   
    21. 

  21.     <meta name="description" content="配置环境  基础编程环境 GitHub 下载加速 可能需要用到的加速服务  SRA工具 1234567conda create -n sra_tools -c bioconda sra-toolsconda activate sra_toolsconda install -c conda-forge lftp -yconda install -c conda-forge pigz -y # 或许">
    22. 

  22.   
    23. 

  23.   
    24. 

  24.   
    25. 

  25.   <title>【学习】使用GATK4.0找SNP - Limour&#39;s Blog</title>
    26. 

  26. 

  27.   <link  rel="stylesheet" href="https://jscdn.limour.top/npm/bootstrap@4.6.1/dist/css/bootstrap.min.css" />
    28. 

  28. 

  29. 

  30. 

  31.   <link  rel="stylesheet" href="https://jscdn.limour.top/npm/github-markdown-css@4.0.0/github-markdown.min.css" />
    32. 

  32. 

  33.   <link  rel="stylesheet" href="https://jscdn.limour.top/npm/hint.css@2.7.0/hint.min.css" />
    34. 

  34. 

  35. 

  36. 

  37. <!-- 主题依赖的图标库，不要自行修改 -->
    38. 

  38. <!-- Do not modify the link that theme dependent icons -->
    39. 

  39. 

  40. <link rel="stylesheet" href="//at.alicdn.com/t/font_1749284_hj8rtnfg7um.css">
    41. 

  41. 

  42. 

  43. 

  44. <link rel="stylesheet" href="//at.alicdn.com/t/font_1736178_lbnruvf0jn.css">
    45. 

  45. 

  46. 

  47. <link  rel="stylesheet" href="/css/main.css" />
    48. 

  48. 

  49. 

  50.   <link id="highlight-css" rel="stylesheet" href="/css/highlight.css" />
    51. 

  51.   
    52. 

  52.     <link id="highlight-css-dark" rel="stylesheet" href="/css/highlight-dark.css" />
    53. 

  53.   
    54. 

  54. 

  55. 

  56. 

  57.   
    58. 

  58. <link rel="stylesheet" href="/theme-inject/custom.css">
    59. 

  59. <link rel="stylesheet" href="/theme-inject/iconfont.css">
    60. 

  60. 

  61. 

  62. 

  63.   <script id="fluid-configs">
    64. 

  64.     var Fluid = window.Fluid || {};
    65. 

  65.     Fluid.ctx = Object.assign({}, Fluid.ctx)
    66. 

  66.     var CONFIG = {"hostname":"hexo.limour.top","root":"/","version":"1.9.7","typing":{"enable":false,"typeSpeed":70,"cursorChar":"_","loop":false,"scope":[]},"anchorjs":{"enable":true,"element":"h1,h2,h3,h4,h5,h6","placement":"left","visible":"hover","icon":"§"},"progressbar":{"enable":true,"height_px":3,"color":"#29d","options":{"showSpinner":false,"trickleSpeed":100}},"code_language":{"enable":true,"default":"TEXT"},"copy_btn":true,"image_caption":{"enable":true},"image_zoom":{"enable":false,"img_url_replace":["",""]},"toc":{"enable":true,"placement":"right","headingSelector":"h1,h2,h3,h4,h5,h6","collapseDepth":0},"lazyload":{"enable":true,"loading_img":"https://jscdn.limour.top/gh/Limour-dev/Sakurairo_Vision/load_svg/inload.svg","onlypost":false,"offset_factor":2},"web_analytics":{"enable":false,"follow_dnt":true,"baidu":null,"google":{"measurement_id":null},"tencent":{"sid":null,"cid":null},"woyaola":null,"cnzz":null,"leancloud":{"app_id":null,"app_key":null,"server_url":null,"path":"window.location.pathname","ignore_local":false}},"search_path":"/local-search.xml","include_content_in_search":true};
    67. 

  67. 

  68.     if (CONFIG.web_analytics.follow_dnt) {
    69. 

  69.       var dntVal = navigator.doNotTrack || window.doNotTrack || navigator.msDoNotTrack;
    70. 

  70.       Fluid.ctx.dnt = dntVal && (dntVal.startsWith('1') || dntVal.startsWith('yes') || dntVal.startsWith('on'));
    71. 

  71.     }
    72. 

  72.   </script>
    73. 

  73.   <script  src="/js/utils.js" ></script>
    74. 

  74.   <script  src="/js/color-schema.js" ></script>
    75. 

  75.   
    76. 

  76. 

  77. 

  78.   
    79. 

  79.   <link rel="canonical" href="https://hexo.limour.top/shi-yong-GATK-zhao-SNP"/>
    80. 

  80. <meta name="generator" content="Hexo 7.1.1"><link rel="alternate" href="/atom.xml" title="Limour's Blog" type="application/atom+xml">
    81. 

  81. <link rel="alternate" href="/rss2.xml" title="Limour's Blog" type="application/rss+xml">
    82. 

  82. </head>
    83. 

  83. 

  84. 

  85. <body>
    86. 

  86.   
    87. 

  87. 

  88.   <header>
    89. 

  89.     
    90. 

  90. 

  91. <div class="header-inner" style="height: 70vh;">
    92. 

  92.   <nav id="navbar" class="navbar fixed-top  navbar-expand-lg navbar-dark scrolling-navbar">
    93. 

  93.   <div class="container">
    94. 

  94.     <a class="navbar-brand" href="/">
    95. 

  95.       <strong>Limour&#39;s Blog</strong>
    96. 

  96.     </a>
    97. 

  97. 

  98.     <button id="navbar-toggler-btn" class="navbar-toggler" type="button" data-toggle="collapse"
    99. 

  99.             data-target="#navbarSupportedContent"
    100. 

  100.             aria-controls="navbarSupportedContent" aria-expanded="false" aria-label="Toggle navigation">
    101. 

  101.       <div class="animated-icon"><span></span><span></span><span></span></div>
    102. 

  102.     </button>
    103. 

  103. 

  104.     <!-- Collapsible content -->
    105. 

  105.     <div class="collapse navbar-collapse" id="navbarSupportedContent">
    106. 

  106.       <ul class="navbar-nav ml-auto text-center">
    107. 

  107.         
    108. 

  108.           
    109. 

  109.           
    110. 

  110.           
    111. 

  111.           
    112. 

  112.             <li class="nav-item">
    113. 

  113.               <a class="nav-link" href="https://hexo.limour.top/" target="_self">
    114. 

  114.                 <i class="iconfont icon-home-fill"></i>
    115. 

  115.                 <span>Home</span>
    116. 

  116.               </a>
    117. 

  117.             </li>
    118. 

  118.           
    119. 

  119.         
    120. 

  120.           
    121. 

  121.           
    122. 

  122.           
    123. 

  123.           
    124. 

  124.             <li class="nav-item">
    125. 

  125.               <a class="nav-link" href="/archives/" target="_self">
    126. 

  126.                 <i class="iconfont icon-archive-fill"></i>
    127. 

  127.                 <span>Archive1</span>
    128. 

  128.               </a>
    129. 

  129.             </li>
    130. 

  130.           
    131. 

  131.         
    132. 

  132.           
    133. 

  133.           
    134. 

  134.           
    135. 

  135.           
    136. 

  136.             <li class="nav-item">
    137. 

  137.               <a class="nav-link" href="https://occdn.limour.top/archives/" target="_self">
    138. 

  138.                 <i class="iconfont icon-archive-fill"></i>
    139. 

  139.                 <span>Archive2</span>
    140. 

  140.               </a>
    141. 

  141.             </li>
    142. 

  142.           
    143. 

  143.         
    144. 

  144.           
    145. 

  145.           
    146. 

  146.           
    147. 

  147.           
    148. 

  148.             <li class="nav-item">
    149. 

  149.               <a class="nav-link" href="https://b.limour.top/archives/" target="_self">
    150. 

  150.                 <i class="iconfont icon-archive-fill"></i>
    151. 

  151.                 <span>Archive3</span>
    152. 

  152.               </a>
    153. 

  153.             </li>
    154. 

  154.           
    155. 

  155.         
    156. 

  156.           
    157. 

  157.           
    158. 

  158.           
    159. 

  159.           
    160. 

  160.             <li class="nav-item">
    161. 

  161.               <a class="nav-link" href="https://od.limour.top/" target="_self">
    162. 

  162.                 <i class="iconfont icon-onedrive"></i>
    163. 

  163.                 <span>Alist</span>
    164. 

  164.               </a>
    165. 

  165.             </li>
    166. 

  166.           
    167. 

  167.         
    168. 

  168.           
    169. 

  169.           
    170. 

  170.           
    171. 

  171.           
    172. 

  172.             <li class="nav-item">
    173. 

  173.               <a class="nav-link" href="https://orcid.org/0000-0001-8897-1685" target="_self">
    174. 

  174.                 <i class="iconfont icon-orcid"></i>
    175. 

  175.                 <span>Orcid</span>
    176. 

  176.               </a>
    177. 

  177.             </li>
    178. 

  178.           
    179. 

  179.         
    180. 

  180.           
    181. 

  181.           
    182. 

  182.           
    183. 

  183.           
    184. 

  184.             <li class="nav-item">
    185. 

  185.               <a class="nav-link" href="/links/" target="_self">
    186. 

  186.                 <i class="iconfont icon-link-fill"></i>
    187. 

  187.                 <span>Links</span>
    188. 

  188.               </a>
    189. 

  189.             </li>
    190. 

  190.           
    191. 

  191.         
    192. 

  192.           
    193. 

  193.           
    194. 

  194.           
    195. 

  195.           
    196. 

  196.             <li class="nav-item">
    197. 

  197.               <a class="nav-link" href="/atom.xml" target="_self">
    198. 

  198.                 <i class="iconfont icon-rss"></i>
    199. 

  199.                 <span>RSS</span>
    200. 

  200.               </a>
    201. 

  201.             </li>
    202. 

  202.           
    203. 

  203.         
    204. 

  204.         
    205. 

  205.           <li class="nav-item" id="search-btn">
    206. 

  206.             <a class="nav-link" target="_self" href="javascript:;" data-toggle="modal" data-target="#modalSearch" aria-label="Search">
    207. 

  207.               <i class="iconfont icon-search"></i>
    208. 

  208.             </a>
    209. 

  209.           </li>
    210. 

  210.           
    211. 

  211.         
    212. 

  212.         
    213. 

  213.           <li class="nav-item" id="color-toggle-btn">
    214. 

  214.             <a class="nav-link" target="_self" href="javascript:;" aria-label="Color Toggle">
    215. 

  215.               <i class="iconfont icon-dark" id="color-toggle-icon"></i>
    216. 

  216.             </a>
    217. 

  217.           </li>
    218. 

  218.         
    219. 

  219.       </ul>
    220. 

  220.     </div>
    221. 

  221.   </div>
    222. 

  222. </nav>
    223. 

  223. 

  224.   
    225. 

  225. 

  226. <div id="banner" class="banner" parallax=true
    227. 

  227.      style="background: url('https://img.limour.top/2023/08/29/64ee08e108638.webp') no-repeat center center; background-size: cover;">
    228. 

  228.   <div class="full-bg-img">
    229. 

  229.     <div class="mask flex-center" style="background-color: rgba(0, 0, 0, 0.3)">
    230. 

  230.       <div class="banner-text text-center fade-in-up">
    231. 

  231.         <div class="h2">
    232. 

  232.           
    233. 

  233.             <span id="subtitle">【学习】使用GATK4.0找SNP</span>
    234. 

  234.           
    235. 

  235.         </div>
    236. 

  236. 

  237.         
    238. 

  238.           
    239. 

  239.   <div class="mt-3">
    240. 

  240.     
    241. 

  241.       <span class="post-meta mr-2">
    242. 

  242.         <i class="iconfont icon-author" aria-hidden="true"></i>
    243. 

  243.         Limour
    244. 

  244.       </span>
    245. 

  245.     
    246. 

  246.     
    247. 

  247.       <span class="post-meta">
    248. 

  248.         <i class="iconfont icon-date-fill" aria-hidden="true"></i>
    249. 

  249.         <time datetime="2023-09-24 18:49" pubdate>
    250. 

  250.           September 24, 2023 pm
    251. 

  251.         </time>
    252. 

  252.       </span>
    253. 

  253.     
    254. 

  254.   </div>
    255. 

  255. 

  256.   <div class="mt-1">
    257. 

  257.     
    258. 

  258.       <span class="post-meta mr-2">
    259. 

  259.         <i class="iconfont icon-chart"></i>
    260. 

  260.         
    261. 

  261.           3.5k words
    262. 

  262.         
    263. 

  263.       </span>
    264. 

  264.     
    265. 

  265. 

  266.     
    267. 

  267.       <span class="post-meta mr-2">
    268. 

  268.         <i class="iconfont icon-clock-fill"></i>
    269. 

  269.         
    270. 

  270.         
    271. 

  271.         
    272. 

  272.           30 mins
    273. 

  273.         
    274. 

  274.       </span>
    275. 

  275.     
    276. 

  276. 

  277.     
    278. 

  278.     
    279. 

  279.   </div>
    280. 

  280. 

  281. 

  282.         
    283. 

  283.       </div>
    284. 

  284. 

  285.       
    286. 

  286.     </div>
    287. 

  287.   </div>
    288. 

  288. </div>
    289. 

  289. 

  290. </div>
    291. 

  291. 

  292.   </header>
    293. 

  293. 

  294.   <main>
    295. 

  295.     
    296. 

  296.       
    297. 

  297. 

  298. <div class="container-fluid nopadding-x">
    299. 

  299.   <div class="row nomargin-x">
    300. 

  300.     <div class="side-col d-none d-lg-block col-lg-2">
    301. 

  301.       
    302. 

  302. 

  303.     </div>
    304. 

  304. 

  305.     <div class="col-lg-8 nopadding-x-md">
    306. 

  306.       <div class="container nopadding-x-md" id="board-ctn">
    307. 

  307.         <div id="board">
    308. 

  308.           <article class="post-content mx-auto">
    309. 

  309.             <h1 id="seo-header">【学习】使用GATK4.0找SNP</h1>
    310. 

  310.             
    311. 

  311.               <p id="updated-time" class="note note-info" style="">
    312. 

  312.                 
    313. 

  313.                   
    314. 

  314.                     Last updated on March 19, 2024 pm
    315. 

  315.                   
    316. 

  316.                 
    317. 

  317.               </p>
    318. 

  318.             
    319. 

  319.             
    320. 

  320.               <div class="markdown-body">
    321. 

  321.                 
    322. 

  322.                 <p><img src="https://img.limour.top/2023/09/26/651299352bcf0.webp" srcset="https://jscdn.limour.top/gh/Limour-dev/Sakurairo_Vision/load_svg/inload.svg" lazyload alt=""></p>
    323. 

  323. <h2 id="配置环境">配置环境</h2>
    324. 

  324. <ul>
    325. 

  325. <li><a href="/-ji-lu--an-zhuang-sheng-xin-de-dai-ma-bian-xie-huan-jing">基础编程环境</a></li>
    326. 

  326. <li><a href="/-fu-ke-GitHub-wen-jian-jia-su">GitHub 下载加速</a></li>
    327. 

  327. <li><a href="/-ji-lu-SOCKS5-zhuan-QUIC">可能需要用到的加速服务</a></li>
    328. 

  328. </ul>
    329. 

  329. <h3 id="SRA工具">SRA工具</h3>
    330. 

  330. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br></pre></td><td class="code"><pre><span class="line">conda create -n sra_tools -c bioconda sra-tools</span><br><span class="line">conda activate sra_tools</span><br><span class="line">conda install -c conda-forge lftp -y</span><br><span class="line">conda install -c conda-forge pigz -y <span class="comment"># 或许换成 pbgzip 更好，此时将 -p 换成 -n 来指定线程数</span></span><br><span class="line">conda install -c bioconda pbgzip -y</span><br><span class="line">prefetch</span><br><span class="line"><span class="comment"># vdb-config -i # 设置 HTTP 代理</span></span><br></pre></td></tr></table></figure>
    331. 

  331. <h3 id="GATK4">GATK4</h3>
    332. 

  332. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br></pre></td><td class="code"><pre><span class="line">conda create -n GATK4 -c bioconda gatk4</span><br><span class="line">conda activate GATK4</span><br><span class="line">conda install -c bioconda samtools -y</span><br><span class="line">conda install -c bioconda bwa -y</span><br><span class="line">conda install -c bioconda pbgzip -y <span class="comment"># 并行版bgzip，bgzip是修改过的gzip，更适合生信领域</span></span><br><span class="line">conda install -c bioconda tabix -y <span class="comment"># 操作VCF文件，与bgzip配套</span></span><br><span class="line"><span class="comment"># conda install -c bioconda fastqc -y # 改用fastp了</span></span><br><span class="line"><span class="comment"># conda install -c bioconda trimmomatic -y # 改用fastp了</span></span><br><span class="line">conda install -c bioconda fastp -y</span><br><span class="line"><span class="comment"># conda install -c bioconda bcftools -y # 用于重命名染色体</span></span><br><span class="line"><span class="comment"># ln -s $CONDA_PREFIX/lib/libgsl.so $CONDA_PREFIX/lib/libgsl.so.25 # 无效，放弃</span></span><br><span class="line"><span class="comment"># conda create -n GATK4-VEP -c bioconda ensembl-vep -y # 根正苗红的突变注释软件，不懂有什么奇怪依赖，解析环境半天</span></span><br></pre></td></tr></table></figure>
    333. 

  333. <ul>
    334. 

  334. <li>BWA是DNA比对工具(不会跨外显子比对)，<a href="/STAR--yi-jian-jiao-ben">STAR</a>是RNA比对工具</li>
    335. 

  335. <li><a target="_blank" rel="noopener" href="https://zhuanlan.zhihu.com/p/37345954">找SNP不推荐用RNAseq的数据</a></li>
    336. 

  336. <li><a target="_blank" rel="noopener" href="https://www.jianshu.com/p/601469194b5e">各种比对工具的说明</a></li>
    337. 

  337. </ul>
    338. 

  338. <h2 id="准备数据">准备数据</h2>
    339. 

  339. <h3 id="参考数据">参考数据</h3>
    340. 

  340. <ul>
    341. 

  341. <li><a target="_blank" rel="noopener" href="https://www.ncbi.nlm.nih.gov/genome/browse">NCBI上各物种的参考序列</a>，可以找到RefSeq，比如Human是GCF_000001405</li>
    342. 

  342. <li>知道序号后可以到<a target="_blank" rel="noopener" href="https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/">FTP</a>上下载相应的<code>genomic.fna.gz</code>文件</li>
    343. 

  343. <li>比如GCF_000001405，依次进入<code>000/001/405</code>即可找到对应的文件</li>
    344. 

  344. </ul>
    345. 

  345. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br></pre></td><td class="code"><pre><span class="line">wget https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/405/GCF_000001405.40_GRCh38.p14/GCF_000001405.40_GRCh38.p14_genomic.fna.gz -O GRCh38.p14.fna.gz</span><br><span class="line">conda run -n sra_tools pigz -d GRCh38.p14.fna.gz <span class="comment"># 得到 GRCh38.p14.fna</span></span><br><span class="line"><span class="comment"># 创建索引</span></span><br><span class="line">samtools faidx GRCh38.p14.fna <span class="comment"># 得到 GRCh38.p14.fna.fai</span></span><br><span class="line"><span class="comment"># 查看一段序列</span></span><br><span class="line">samtools faidx GRCh38.p14.fna NC_000001.11:1000000-1000200</span><br><span class="line"><span class="comment"># 创建比对索引</span></span><br><span class="line">bwa index GRCh38.p14.fna <span class="comment"># 会自动在 bwtsw, is or rb2 三种算法中选择合适的</span></span><br><span class="line"><span class="comment"># 创建dict</span></span><br><span class="line">gatk CreateSequenceDictionary -R GRCh38.p14.fna</span><br></pre></td></tr></table></figure>
    346. 

  346. <ul>
    347. 

  347. <li>最后得到的RefSeq目录结构如下</li>
    348. 

  348. </ul>
    349. 

  349. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br></pre></td><td class="code"><pre><span class="line"><span class="comment"># conda create -n linux -c conda-forge tree</span></span><br><span class="line"><span class="comment"># conda run -n linux tree -f -h --du</span></span><br><span class="line">[8.5G]  .</span><br><span class="line">├── [ 79K]  ./GRCh38.p14.dict</span><br><span class="line">├── [3.1G]  ./GRCh38.p14.fna</span><br><span class="line">├── [ 21K]  ./GRCh38.p14.fna.amb</span><br><span class="line">├── [ 90K]  ./GRCh38.p14.fna.ann</span><br><span class="line">├── [3.1G]  ./GRCh38.p14.fna.bwt</span><br><span class="line">├── [ 26K]  ./GRCh38.p14.fna.fai</span><br><span class="line">├── [786M]  ./GRCh38.p14.fna.pac</span><br><span class="line">└── [1.5G]  ./GRCh38.p14.fna.sa</span><br></pre></td></tr></table></figure>
    350. 

  350. <h3 id="已知SNP">已知SNP</h3>
    351. 

  351. <ul>
    352. 

  352. <li><a target="_blank" rel="noopener" href="https://gatk.broadinstitute.org/hc/en-us/articles/360035890811-Resource-bundle">GATK官网提供了一些数据</a></li>
    353. 

  353. <li><a target="_blank" rel="noopener" href="https://ftp.ncbi.nlm.nih.gov/snp/latest_release/VCF/">NCBI提供了dbSNP</a></li>
    354. 

  354. <li><code>lftp ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/</code>，密码空，直接回车</li>
    355. 

  355. <li>下载和参考数据相对应的<a target="_blank" rel="noopener" href="https://gist.github.com/Limour-dev/2d9c0250714bec1ce5c5989363bbfa12">indels.hg38.vcf</a></li>
    356. 

  356. </ul>
    357. 

  357. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br></pre></td><td class="code"><pre><span class="line">wget https://ftp.ncbi.nlm.nih.gov/snp/latest_release/VCF/GCF_000001405.40.gz -O GRCh38.dbSNP.ncbi.vcf.gz</span><br></pre></td></tr></table></figure>
    358. 

  358. <h4 id="转换染色体名称到NCBI的参考文件">转换染色体名称到NCBI的参考文件</h4>
    359. 

  359. <ul>
    360. 

  360. <li><code>assembly_report.txt</code> 在下载NCBI参考数据FTP目录下</li>
    361. 

  361. </ul>
    362. 

  362. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br></pre></td><td class="code"><pre><span class="line">wget https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/405/GCF_000001405.40_GRCh38.p14/GCF_000001405.40_GRCh38.p14_assembly_report.txt -O GRCh38.p14_assembly_report.txt </span><br><span class="line">grep -e <span class="string">&#x27;^[^#]&#x27;</span> GRCh38.p14_assembly_report.txt | awk -F<span class="string">&#x27;\t&#x27;</span> <span class="string">&#x27;&#123; print $NF, $7 &#125;&#x27;</span> | sed <span class="string">&#x27;s/\r / /g&#x27;</span> &gt; rename_file.txt</span><br><span class="line">conda create -n something_fuck -c conda-forge mamba</span><br><span class="line">conda activate something_fuck</span><br><span class="line">mamba install -c bioconda bcftools</span><br><span class="line">bcftools annotate --rename-chrs rename_file.txt -o Homo_sapiens_assembly38.known_indels.ncbi.vcf Homo_sapiens_assembly38.known_indels.vcf</span><br><span class="line">bcftools annotate --rename-chrs rename_file.txt -o hapmap_3.3.hg38.ncbi.vcf hapmap_3.3.hg38.vcf</span><br><span class="line">bcftools annotate --rename-chrs rename_file.txt -o Mills_and_1000G_gold_standard.indels.hg38.ncbi.vcf Mills_and_1000G_gold_standard.indels.hg38.vcf</span><br><span class="line">conda run -n GATK4 pbgzip -n 4 *.ncbi.vcf <span class="comment"># 似乎一次只压缩一个，多运行几次</span></span><br></pre></td></tr></table></figure>
    363. 

  363. <h4 id="建立索引">建立索引</h4>
    364. 

  364. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br></pre></td><td class="code"><pre><span class="line">nano knownSitesIndex.sh &amp;&amp; <span class="built_in">chmod</span> +x knownSitesIndex.sh</span><br><span class="line">./knownSitesIndex.sh</span><br></pre></td></tr></table></figure>
    365. 

  365. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br></pre></td><td class="code"><pre><span class="line"><span class="meta">#!/bin/bash</span></span><br><span class="line"><span class="built_in">source</span> activate GATK4</span><br><span class="line"><span class="comment">#设置knownSites数据存放目录</span></span><br><span class="line">knownSites=/home/jovyan/upload/knownSites</span><br><span class="line"><span class="keyword">for</span> file <span class="keyword">in</span> <span class="variable">$knownSites</span>/*.ncbi.vcf.gz</span><br><span class="line"><span class="keyword">do</span></span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$file</span></span><br><span class="line">gatk IndexFeatureFile \</span><br><span class="line">    -I <span class="variable">$file</span></span><br><span class="line"><span class="keyword">done</span></span><br></pre></td></tr></table></figure>
    366. 

  366. <ul>
    367. 

  367. <li>最后得到的knownSites目录结构如下</li>
    368. 

  368. </ul>
    369. 

  369. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br></pre></td><td class="code"><pre><span class="line">[ 25G]  .</span><br><span class="line">├── [ 25G]  ./GRCh38.dbSNP.ncbi.vcf.gz</span><br><span class="line">├── [4.2M]  ./GRCh38.dbSNP.ncbi.vcf.gz.tbi</span><br><span class="line">├── [ 79K]  ./GRCh38.p14_assembly_report.txt</span><br><span class="line">├── [ 61M]  ./hapmap_3.3.hg38.ncbi.vcf.gz</span><br><span class="line">├── [2.1M]  ./hapmap_3.3.hg38.ncbi.vcf.gz.tbi</span><br><span class="line">├── [ 58M]  ./Homo_sapiens_assembly38.known_indels.ncbi.vcf.gz</span><br><span class="line">├── [2.1M]  ./Homo_sapiens_assembly38.known_indels.ncbi.vcf.gz.tbi</span><br><span class="line">├── [ 20M]  ./Mills_and_1000G_gold_standard.indels.hg38.ncbi.vcf.gz</span><br><span class="line">├── [2.0M]  ./Mills_and_1000G_gold_standard.indels.hg38.ncbi.vcf.gz.tbi</span><br><span class="line">└── [ 23K]  ./rename_file.txt</span><br></pre></td></tr></table></figure>
    370. 

  370. <h3 id="测序数据">测序数据</h3>
    371. 

  371. <ul>
    372. 

  372. <li>WGS的DNA测序数据</li>
    373. 

  373. <li>以<a target="_blank" rel="noopener" href="https://www.ncbi.nlm.nih.gov/sra/SRX247249">SRX247249</a>做学习的示例数据，感谢<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220930070928/http://www.biotrainee.com/thread-1376-1-1.html">曾老师</a>指路</li>
    374. 

  374. <li>下载方式见<a href="/cong-ENI-shu-ju-ku-xia-zai-fastq-wen-jian#%E4%BB%8E-NCBI-%E6%95%B0%E6%8D%AE%E5%BA%93%E4%B8%8B%E8%BD%BD">SRA文件转FASTQ文件</a></li>
    375. 

  375. <li>也可以到<a target="_blank" rel="noopener" href="https://www.ebi.ac.uk/ena/browser/view/SRX247249">ENA数据库</a>上下载</li>
    376. 

  376. </ul>
    377. 

  377. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br></pre></td><td class="code"><pre><span class="line">conda run -n sra_tools prefetch --option-file SRR_Acc_List.txt</span><br><span class="line">nano 11.sh &amp;&amp; <span class="built_in">chmod</span> +x 11.sh</span><br><span class="line">./11.sh</span><br></pre></td></tr></table></figure>
    378. 

  378. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br><span class="line">15</span><br><span class="line">16</span><br><span class="line">17</span><br><span class="line">18</span><br><span class="line">19</span><br></pre></td><td class="code"><pre><span class="line"><span class="meta">#!/bin/bash</span></span><br><span class="line"><span class="built_in">source</span> activate sra_tools</span><br><span class="line"><span class="comment">#任务名</span></span><br><span class="line">TASKN=SRX247249</span><br><span class="line"><span class="comment">#设置SRA根目录, pwd是当前目录</span></span><br><span class="line">ROOTDIR=`<span class="built_in">pwd</span>`</span><br><span class="line"><span class="comment">#设置rawData存放目录</span></span><br><span class="line">rawData=/home/jovyan/upload/rawData/<span class="variable">$TASKN</span></span><br><span class="line"><span class="built_in">mkdir</span> -p <span class="variable">$rawData</span></span><br><span class="line"> </span><br><span class="line"><span class="built_in">cd</span> <span class="variable">$ROOTDIR</span></span><br><span class="line"><span class="keyword">for</span>  file <span class="keyword">in</span> `<span class="built_in">cat</span> SRR_Acc_List.txt`</span><br><span class="line"><span class="keyword">do</span></span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$file</span></span><br><span class="line"><span class="built_in">mkdir</span> <span class="variable">$rawData</span>/<span class="variable">$file</span></span><br><span class="line"><span class="built_in">cd</span> <span class="variable">$rawData</span>/<span class="variable">$file</span></span><br><span class="line">fasterq-dump --split-3 <span class="variable">$ROOTDIR</span>/<span class="variable">$file</span> -e 6</span><br><span class="line">pigz -p 6 *</span><br><span class="line"><span class="keyword">done</span></span><br></pre></td></tr></table></figure>
    379. 

  379. <h3 id="rawData质控">rawData质控</h3>
    380. 

  380. <ul>
    381. 

  381. <li><a target="_blank" rel="noopener" href="https://zhuanlan.zhihu.com/p/28802083">原始数据质量判断​</a></li>
    382. 

  382. <li><a target="_blank" rel="noopener" href="https://zhuanlan.zhihu.com/p/28924793">原始数据过滤工具</a></li>
    383. 

  383. </ul>
    384. 

  384. <h4 id="质量判断（可跳过）">质量判断（可跳过）</h4>
    385. 

  385. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br></pre></td><td class="code"><pre><span class="line">nano qc.sh &amp;&amp; <span class="built_in">chmod</span> +x qc.sh</span><br><span class="line">./qc.sh</span><br></pre></td></tr></table></figure>
    386. 

  386. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br><span class="line">15</span><br><span class="line">16</span><br><span class="line">17</span><br><span class="line">18</span><br></pre></td><td class="code"><pre><span class="line"><span class="meta">#!/bin/bash</span></span><br><span class="line"><span class="built_in">source</span> activate GATK4</span><br><span class="line"><span class="comment">#任务名</span></span><br><span class="line">TASKN=SRX247249</span><br><span class="line"><span class="comment">#设置rawData存放目录</span></span><br><span class="line">rawData=/home/jovyan/upload/rawData/<span class="variable">$TASKN</span></span><br><span class="line"><span class="comment">#设置qc结果的输出目录</span></span><br><span class="line">QCDIR=/home/jovyan/upload/rawData/<span class="variable">$TASKN</span><span class="string">&quot;_fastqc&quot;</span></span><br><span class="line"><span class="built_in">mkdir</span> -p <span class="variable">$QCDIR</span></span><br><span class="line"> </span><br><span class="line"><span class="keyword">for</span> file <span class="keyword">in</span> <span class="variable">$rawData</span>/*</span><br><span class="line"><span class="keyword">do</span></span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$file</span></span><br><span class="line">SAMPLE=<span class="variable">$&#123;file##*/&#125;</span></span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$QCDIR</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span></span><br><span class="line"><span class="built_in">mkdir</span> <span class="variable">$QCDIR</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span></span><br><span class="line">fastqc -o <span class="variable">$QCDIR</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span> --threads=6 `<span class="built_in">ls</span> <span class="variable">$rawData</span>/<span class="variable">$SAMPLE</span>/*`</span><br><span class="line"><span class="keyword">done</span></span><br></pre></td></tr></table></figure>
    387. 

  387. <ul>
    388. 

  388. <li>对于PE而言，正向和反向reads的测量过程是独立的，将当成两次SE来处理</li>
    389. 

  389. <li>最后的报告中：</li>
    390. 

  390. <li>Q20的碱基要在95%以上（最差不低于90%）</li>
    391. 

  391. <li>Q30要求大于85%（最差也不要低于80%）</li>
    392. 

  392. <li>对于人类来说，GC含量应该在40%左右</li>
    393. 

  393. </ul>
    394. 

  394. <h4 id="fastp一键质控">fastp一键质控</h4>
    395. 

  395. <ul>
    396. 

  396. <li><a target="_blank" rel="noopener" href="https://github.com/OpenGene/fastp">fastp的详细说明</a>; <a target="_blank" rel="noopener" href="https://zhuanlan.zhihu.com/p/33601691">中文介绍</a></li>
    397. 

  397. </ul>
    398. 

  398. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br></pre></td><td class="code"><pre><span class="line">nano qc.sh &amp;&amp; <span class="built_in">chmod</span> +x qc.sh</span><br><span class="line">./qc.sh</span><br></pre></td></tr></table></figure>
    399. 

  399. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br><span class="line">15</span><br><span class="line">16</span><br><span class="line">17</span><br><span class="line">18</span><br><span class="line">19</span><br><span class="line">20</span><br><span class="line">21</span><br><span class="line">22</span><br><span class="line">23</span><br><span class="line">24</span><br><span class="line">25</span><br><span class="line">26</span><br><span class="line">27</span><br><span class="line">28</span><br><span class="line">29</span><br><span class="line">30</span><br></pre></td><td class="code"><pre><span class="line"><span class="meta">#!/bin/bash</span></span><br><span class="line"><span class="built_in">source</span> activate GATK4</span><br><span class="line"><span class="comment">#任务名</span></span><br><span class="line">TASKN=SRX247249</span><br><span class="line"><span class="comment">#设置rawData存放目录</span></span><br><span class="line">rawData=/home/jovyan/upload/rawData/<span class="variable">$TASKN</span></span><br><span class="line"><span class="comment">#设置qc结果的输出目录</span></span><br><span class="line">QCDIR=/home/jovyan/upload/rawData/<span class="variable">$TASKN</span><span class="string">&quot;_fastp&quot;</span></span><br><span class="line"><span class="built_in">mkdir</span> -p <span class="variable">$QCDIR</span></span><br><span class="line"><span class="comment">#设置cleanData的存放目录</span></span><br><span class="line">CLEAN=/home/jovyan/upload/cleanData/<span class="variable">$TASKN</span></span><br><span class="line"><span class="built_in">mkdir</span> -p <span class="variable">$CLEAN</span></span><br><span class="line"> </span><br><span class="line"><span class="keyword">for</span> file <span class="keyword">in</span> <span class="variable">$rawData</span>/*</span><br><span class="line"><span class="keyword">do</span></span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$file</span></span><br><span class="line">SAMPLE=<span class="variable">$&#123;file##*/&#125;</span></span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$QCDIR</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span></span><br><span class="line"><span class="built_in">mkdir</span> <span class="variable">$QCDIR</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span></span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$CLEAN</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span></span><br><span class="line"><span class="built_in">mkdir</span> <span class="variable">$CLEAN</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span></span><br><span class="line"><span class="built_in">cd</span> <span class="variable">$QCDIR</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span></span><br><span class="line">fastp -c -w 4 \</span><br><span class="line">-o <span class="variable">$CLEAN</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/out.R1.fq.gz&quot;</span> \</span><br><span class="line">-O <span class="variable">$CLEAN</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/out.R2.fq.gz&quot;</span> \</span><br><span class="line">-h <span class="variable">$QCDIR</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/fastp.html&quot;</span> \</span><br><span class="line">-j <span class="variable">$QCDIR</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/fastp.json&quot;</span> \</span><br><span class="line">-i `<span class="built_in">ls</span> <span class="variable">$rawData</span>/<span class="variable">$SAMPLE</span>/*_1.fastq.gz` \</span><br><span class="line">-I `<span class="built_in">ls</span> <span class="variable">$rawData</span>/<span class="variable">$SAMPLE</span>/*_2.fastq.gz`</span><br><span class="line"><span class="keyword">done</span></span><br></pre></td></tr></table></figure>
    400. 

  400. <ul>
    401. 

  401. <li>最后得到的cleanData目录结构如下</li>
    402. 

  402. </ul>
    403. 

  403. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br></pre></td><td class="code"><pre><span class="line">[ 23G]  .</span><br><span class="line">├── [9.1G]  ./SRR799559</span><br><span class="line">│   ├── [4.4G]  ./SRR799559/out.R1.fq.gz</span><br><span class="line">│   └── [4.7G]  ./SRR799559/out.R2.fq.gz</span><br><span class="line">├── [7.0G]  ./SRR799560</span><br><span class="line">│   ├── [3.4G]  ./SRR799560/out.R1.fq.gz</span><br><span class="line">│   └── [3.5G]  ./SRR799560/out.R2.fq.gz</span><br><span class="line">└── [7.4G]  ./SRR799561</span><br><span class="line">    ├── [3.6G]  ./SRR799561/out.R1.fq.gz</span><br><span class="line">    └── [3.8G]  ./SRR799561/out.R2.fq.gz</span><br></pre></td></tr></table></figure>
    404. 

  404. <h2 id="数据比对">数据比对</h2>
    405. 

  405. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br></pre></td><td class="code"><pre><span class="line">nano bwa_and_markdup.sh &amp;&amp; <span class="built_in">chmod</span> +x bwa_and_markdup.sh</span><br><span class="line">./bwa_and_markdup.sh</span><br></pre></td></tr></table></figure>
    406. 

  406. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br><span class="line">15</span><br><span class="line">16</span><br><span class="line">17</span><br><span class="line">18</span><br><span class="line">19</span><br><span class="line">20</span><br><span class="line">21</span><br><span class="line">22</span><br><span class="line">23</span><br><span class="line">24</span><br><span class="line">25</span><br><span class="line">26</span><br><span class="line">27</span><br><span class="line">28</span><br><span class="line">29</span><br><span class="line">30</span><br><span class="line">31</span><br><span class="line">32</span><br><span class="line">33</span><br><span class="line">34</span><br><span class="line">35</span><br><span class="line">36</span><br><span class="line">37</span><br><span class="line">38</span><br><span class="line">39</span><br><span class="line">40</span><br><span class="line">41</span><br><span class="line">42</span><br><span class="line">43</span><br></pre></td><td class="code"><pre><span class="line"><span class="meta">#!/bin/bash</span></span><br><span class="line"><span class="built_in">source</span> activate GATK4</span><br><span class="line"><span class="comment">#任务名</span></span><br><span class="line">TASKN=SRX247249</span><br><span class="line"><span class="comment">#设置cleanData的存放目录</span></span><br><span class="line">CLEAN=/home/jovyan/upload/cleanData/<span class="variable">$TASKN</span></span><br><span class="line"><span class="comment">#设置RefSeq的存放目录</span></span><br><span class="line">RefSeq=/home/jovyan/data/refseq/GRCh38.p14.fna</span><br><span class="line"><span class="comment">#设置Read Group信息，见 https://gatk.broadinstitute.org/hc/en-us/articles/360035890671-Read-groups</span></span><br><span class="line">RGroup_PL=ILLUMINA <span class="comment"># 所用的测序平台：ILLUMINA,SLX,SOLEXA,SOLID,454,LS454,COMPLETE,PACBIO,IONTORRENT,CAPILLARY,HELICOS或UNKNOWN。CG测序为COMPLETE</span></span><br><span class="line">RGroup_SM=<span class="variable">$TASKN</span> <span class="comment"># 样本ID，同一个样本可能有多个lane，此时用样本ID相关联</span></span><br><span class="line">RGroup=<span class="string">&#x27;PL:&#x27;</span><span class="variable">$RGroup_PL</span><span class="string">&#x27;\tSM:&#x27;</span><span class="variable">$RGroup_SM</span></span><br><span class="line"><span class="comment">#设置BAM的存放目录</span></span><br><span class="line">BAM=/home/jovyan/upload/BAM/<span class="variable">$TASKN</span></span><br><span class="line"><span class="built_in">mkdir</span> -p <span class="variable">$BAM</span></span><br><span class="line"> </span><br><span class="line"><span class="keyword">for</span> file <span class="keyword">in</span> <span class="variable">$CLEAN</span>/*</span><br><span class="line"><span class="keyword">do</span></span><br><span class="line"> </span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$file</span></span><br><span class="line">SAMPLE=<span class="variable">$&#123;file##*/&#125;</span></span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$BAM</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span></span><br><span class="line"><span class="built_in">mkdir</span> <span class="variable">$BAM</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span></span><br><span class="line"><span class="built_in">echo</span> <span class="string">&#x27;@RG\tID:&#x27;</span><span class="variable">$SAMPLE</span><span class="string">&#x27;\t&#x27;</span><span class="variable">$RGroup</span></span><br><span class="line"> </span><br><span class="line"><span class="comment">#1 比对</span></span><br><span class="line">bwa mem -t 4 -M -R <span class="string">&#x27;@RG\tID:&#x27;</span><span class="variable">$SAMPLE</span><span class="string">&#x27;\t&#x27;</span><span class="variable">$RGroup</span> <span class="variable">$RefSeq</span> `<span class="built_in">ls</span> <span class="variable">$CLEAN</span>/<span class="variable">$SAMPLE</span>/*` \</span><br><span class="line">| samtools view -Sb - &gt; <span class="variable">$BAM</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/raw.bam&quot;</span></span><br><span class="line"> </span><br><span class="line"><span class="comment">#2 排序</span></span><br><span class="line">samtools <span class="built_in">sort</span> -@ 4 -m 4G -O bam -o <span class="variable">$BAM</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/sorted.bam&quot;</span> <span class="variable">$BAM</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/raw.bam&quot;</span></span><br><span class="line"><span class="built_in">rm</span> <span class="variable">$BAM</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/raw.bam&quot;</span></span><br><span class="line"> </span><br><span class="line"><span class="comment">#3 标记PCR重复</span></span><br><span class="line">gatk MarkDuplicates -I <span class="variable">$BAM</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/sorted.bam&quot;</span> \</span><br><span class="line">-O <span class="variable">$BAM</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/sorted.markdup.bam&quot;</span> \</span><br><span class="line">-M <span class="variable">$BAM</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/sorted.markdup_metrics.txt&quot;</span></span><br><span class="line"><span class="built_in">rm</span> <span class="variable">$BAM</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/sorted.bam&quot;</span></span><br><span class="line"> </span><br><span class="line"><span class="comment">#4 创建比对索引文件</span></span><br><span class="line">samtools index <span class="variable">$BAM</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/sorted.markdup.bam&quot;</span></span><br><span class="line"> </span><br><span class="line"><span class="keyword">done</span></span><br></pre></td></tr></table></figure>
    407. 

  407. <ul>
    408. 

  408. <li>最后得到的BAM目录结构如下</li>
    409. 

  409. </ul>
    410. 

  410. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br></pre></td><td class="code"><pre><span class="line">[ 30G]  .</span><br><span class="line">├── [ 11G]  ./SRR799559</span><br><span class="line">│   ├── [ 11G]  ./SRR799559/sorted.markdup.bam</span><br><span class="line">│   ├── [4.5M]  ./SRR799559/sorted.markdup.bam.bai</span><br><span class="line">│   └── [3.7K]  ./SRR799559/sorted.markdup_metrics.txt</span><br><span class="line">├── [8.8G]  ./SRR799560</span><br><span class="line">│   ├── [8.8G]  ./SRR799560/sorted.markdup.bam</span><br><span class="line">│   ├── [3.9M]  ./SRR799560/sorted.markdup.bam.bai</span><br><span class="line">│   └── [3.7K]  ./SRR799560/sorted.markdup_metrics.txt</span><br><span class="line">└── [9.6G]  ./SRR799561</span><br><span class="line">    ├── [9.5G]  ./SRR799561/sorted.markdup.bam</span><br><span class="line">    ├── [4.1M]  ./SRR799561/sorted.markdup.bam.bai</span><br><span class="line">    └── [3.7K]  ./SRR799561/sorted.markdup_metrics.txt</span><br></pre></td></tr></table></figure>
    411. 

  411. <h3 id="同样本合并">同样本合并</h3>
    412. 

  412. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br></pre></td><td class="code"><pre><span class="line">nano merge.sh &amp;&amp; <span class="built_in">chmod</span> +x merge.sh</span><br><span class="line">./merge.sh</span><br></pre></td></tr></table></figure>
    413. 

  413. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br></pre></td><td class="code"><pre><span class="line"><span class="meta">#!/bin/bash</span></span><br><span class="line"><span class="built_in">source</span> activate GATK4</span><br><span class="line"><span class="comment">#任务名</span></span><br><span class="line">TASKN=SRX247249</span><br><span class="line"><span class="comment">#设置BAM的存放目录</span></span><br><span class="line">BAM=/home/jovyan/upload/BAM/<span class="variable">$TASKN</span></span><br><span class="line"><span class="comment">#设置merge后的数据存放目录</span></span><br><span class="line">MERGEDBAM=/home/jovyan/upload/merged/<span class="variable">$TASKN</span>/SAMPLE1</span><br><span class="line"><span class="built_in">mkdir</span> -p <span class="variable">$MERGEDBAM</span></span><br><span class="line"> </span><br><span class="line">samtools merge <span class="variable">$MERGEDBAM</span><span class="string">&quot;/sorted.markdup.bam&quot;</span> \</span><br><span class="line">`find <span class="string">&quot;<span class="variable">$BAM</span>&quot;</span> -name <span class="string">&quot;sorted.markdup.bam&quot;</span> -<span class="built_in">type</span> f -<span class="built_in">exec</span> <span class="built_in">readlink</span> -f &#123;&#125; \;`</span><br><span class="line">samtools index <span class="variable">$MERGEDBAM</span><span class="string">&quot;/sorted.markdup.bam&quot;</span></span><br></pre></td></tr></table></figure>
    414. 

  414. <ul>
    415. 

  415. <li>最后得到的MERGED目录结构如下</li>
    416. 

  416. </ul>
    417. 

  417. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br></pre></td><td class="code"><pre><span class="line">[ 21G]  .</span><br><span class="line">└── [ 21G]  ./SAMPLE1</span><br><span class="line">    ├── [ 21G]  ./SAMPLE1/sorted.markdup.bam</span><br><span class="line">    └── [6.8M]  ./SAMPLE1/sorted.markdup.bam.bai</span><br></pre></td></tr></table></figure>
    418. 

  418. <h3 id="局部重比对">局部重比对</h3>
    419. 

  419. <ul>
    420. 

  420. <li>具体见<a target="_blank" rel="noopener" href="https://zhuanlan.zhihu.com/p/29485987">黄树嘉博士的相关介绍</a></li>
    421. 

  421. <li>因为本文是GATK 4.0的HaplotypeCaller模块，自带局部重比对，故用到的时候再写</li>
    422. 

  422. </ul>
    423. 

  423. <h3 id="BQSR">BQSR</h3>
    424. 

  424. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br></pre></td><td class="code"><pre><span class="line">nano BQSR.sh &amp;&amp; <span class="built_in">chmod</span> +x BQSR.sh</span><br><span class="line">./BQSR.sh</span><br></pre></td></tr></table></figure>
    425. 

  425. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br><span class="line">15</span><br><span class="line">16</span><br><span class="line">17</span><br><span class="line">18</span><br><span class="line">19</span><br><span class="line">20</span><br><span class="line">21</span><br><span class="line">22</span><br><span class="line">23</span><br><span class="line">24</span><br><span class="line">25</span><br><span class="line">26</span><br><span class="line">27</span><br><span class="line">28</span><br><span class="line">29</span><br><span class="line">30</span><br><span class="line">31</span><br><span class="line">32</span><br><span class="line">33</span><br><span class="line">34</span><br></pre></td><td class="code"><pre><span class="line"><span class="meta">#!/bin/bash</span></span><br><span class="line"><span class="built_in">source</span> activate GATK4</span><br><span class="line"><span class="comment">#任务名</span></span><br><span class="line">TASKN=SRX247249</span><br><span class="line"><span class="comment">#设置merged数据存放目录</span></span><br><span class="line">MERGED=/home/jovyan/upload/merged/<span class="variable">$TASKN</span></span><br><span class="line"><span class="comment">#设置RefSeq的存放目录</span></span><br><span class="line">RefSeq=/home/jovyan/data/refseq/GRCh38.p14.fna</span><br><span class="line"><span class="comment">#设置knownSites数据存放目录</span></span><br><span class="line">knownSites=/home/jovyan/upload/knownSites</span><br><span class="line">knownSites=$(<span class="built_in">echo</span> $(<span class="built_in">ls</span> <span class="variable">$knownSites</span>/*.ncbi.vcf.gz | sed <span class="string">&#x27;s/^/--known-sites /&#x27;</span> | <span class="built_in">tr</span> <span class="string">&#x27;\n&#x27;</span> <span class="string">&#x27; &#x27;</span>))</span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$knownSites</span></span><br><span class="line"> </span><br><span class="line"><span class="keyword">for</span> file <span class="keyword">in</span> <span class="variable">$MERGED</span>/*</span><br><span class="line"><span class="keyword">do</span></span><br><span class="line"> </span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$file</span></span><br><span class="line">SAMPLE=<span class="variable">$&#123;file##*/&#125;</span></span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$MERGED</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span></span><br><span class="line"> </span><br><span class="line">gatk BaseRecalibrator <span class="variable">$knownSites</span> \</span><br><span class="line">    -R <span class="variable">$RefSeq</span> \</span><br><span class="line">    -I <span class="variable">$MERGED</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/sorted.markdup.bam&quot;</span> \</span><br><span class="line">    -O <span class="variable">$MERGED</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/recal_data.table&quot;</span></span><br><span class="line"> </span><br><span class="line">gatk ApplyBQSR \</span><br><span class="line">    -R <span class="variable">$RefSeq</span> \</span><br><span class="line">    -I <span class="variable">$MERGED</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/sorted.markdup.bam&quot;</span> \</span><br><span class="line">    --bqsr-recal-file <span class="variable">$MERGED</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/recal_data.table&quot;</span> \</span><br><span class="line">    -O <span class="variable">$MERGED</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/sorted.markdup.BQSR.bam&quot;</span></span><br><span class="line"> </span><br><span class="line">samtools index <span class="variable">$MERGED</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/sorted.markdup.BQSR.bam&quot;</span></span><br><span class="line"> </span><br><span class="line"><span class="keyword">done</span></span><br></pre></td></tr></table></figure>
    426. 

  426. <ul>
    427. 

  427. <li>最后得到的MERGED目录结构如下</li>
    428. 

  428. </ul>
    429. 

  429. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br></pre></td><td class="code"><pre><span class="line">[ 54G]  .</span><br><span class="line">└── [ 54G]  ./SAMPLE1</span><br><span class="line">    ├── [2.5M]  ./SAMPLE1/recal_data.table</span><br><span class="line">    ├── [ 21G]  ./SAMPLE1/sorted.markdup.bam</span><br><span class="line">    ├── [6.8M]  ./SAMPLE1/sorted.markdup.bam.bai</span><br><span class="line">    ├── [8.8M]  ./SAMPLE1/sorted.markdup.BQSR.bai</span><br><span class="line">    ├── [ 33G]  ./SAMPLE1/sorted.markdup.BQSR.bam</span><br><span class="line">    └── [7.6M]  ./SAMPLE1/sorted.markdup.BQSR.bam.bai</span><br></pre></td></tr></table></figure>
    430. 

  430. <h2 id="两步法变异检测">两步法变异检测</h2>
    431. 

  431. <h3 id="HaplotypeCaller">HaplotypeCaller</h3>
    432. 

  432. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br></pre></td><td class="code"><pre><span class="line">nano HaplotypeCaller.sh &amp;&amp; <span class="built_in">chmod</span> +x HaplotypeCaller.sh</span><br><span class="line">./HaplotypeCaller.sh</span><br></pre></td></tr></table></figure>
    433. 

  433. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br><span class="line">15</span><br><span class="line">16</span><br><span class="line">17</span><br><span class="line">18</span><br><span class="line">19</span><br><span class="line">20</span><br><span class="line">21</span><br><span class="line">22</span><br><span class="line">23</span><br></pre></td><td class="code"><pre><span class="line"><span class="meta">#!/bin/bash</span></span><br><span class="line"><span class="built_in">source</span> activate GATK4</span><br><span class="line"> </span><br><span class="line"><span class="comment">#任务名</span></span><br><span class="line">TASKN=SRX247249</span><br><span class="line"><span class="comment">#设置BQSR数据存放目录</span></span><br><span class="line">MERGED=/home/jovyan/upload/merged/<span class="variable">$TASKN</span></span><br><span class="line"><span class="comment">#设置RefSeq的存放目录</span></span><br><span class="line">RefSeq=/home/jovyan/data/refseq/GRCh38.p14.fna</span><br><span class="line"> </span><br><span class="line"><span class="keyword">for</span> file <span class="keyword">in</span> <span class="variable">$MERGED</span>/*</span><br><span class="line"><span class="keyword">do</span></span><br><span class="line"> </span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$file</span></span><br><span class="line">SAMPLE=<span class="variable">$&#123;file##*/&#125;</span></span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$MERGED</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span></span><br><span class="line"> </span><br><span class="line">gatk --java-options <span class="string">&quot;-Xmx4g&quot;</span> HaplotypeCaller -ERC GVCF \</span><br><span class="line">    -R <span class="variable">$RefSeq</span> \</span><br><span class="line">    -I <span class="variable">$MERGED</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/sorted.markdup.BQSR.bam&quot;</span> \</span><br><span class="line">    -O <span class="variable">$MERGED</span><span class="string">&quot;/&quot;</span><span class="variable">$SAMPLE</span><span class="string">&quot;/HC.g.vcf.gz&quot;</span></span><br><span class="line"> </span><br><span class="line"><span class="keyword">done</span></span><br></pre></td></tr></table></figure>
    434. 

  434. <h3 id="CombineGVCFs">CombineGVCFs</h3>
    435. 

  435. <h4 id="单样本">单样本</h4>
    436. 

  436. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br></pre></td><td class="code"><pre><span class="line">VCFPATH=<span class="variable">$MERGED</span><span class="string">&#x27;/SAMPLE1&#x27;</span></span><br></pre></td></tr></table></figure>
    437. 

  437. <h4 id="多样本">多样本</h4>
    438. 

  438. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br></pre></td><td class="code"><pre><span class="line">nano CombineGVCFs.sh &amp;&amp; <span class="built_in">chmod</span> +x CombineGVCFs.sh</span><br><span class="line">./CombineGVCFs.sh</span><br></pre></td></tr></table></figure>
    439. 

  439. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br><span class="line">15</span><br><span class="line">16</span><br><span class="line">17</span><br><span class="line">18</span><br><span class="line">19</span><br></pre></td><td class="code"><pre><span class="line"><span class="meta">#!/bin/bash</span></span><br><span class="line"><span class="built_in">source</span> activate GATK4</span><br><span class="line"> </span><br><span class="line"><span class="comment">#任务名</span></span><br><span class="line">TASKN=SRX247249</span><br><span class="line"><span class="comment">#设置BQSR数据存放目录</span></span><br><span class="line">MERGED=/home/jovyan/upload/merged/<span class="variable">$TASKN</span></span><br><span class="line"><span class="comment">#设置RefSeq的存放目录</span></span><br><span class="line">RefSeq=/home/jovyan/data/refseq/GRCh38.p14.fna</span><br><span class="line"><span class="comment">#设置最后输出的路径</span></span><br><span class="line">VCFPATH=/home/jovyan/upload/VCF/<span class="variable">$TASKN</span></span><br><span class="line"><span class="built_in">mkdir</span> -p <span class="variable">$VCFPATH</span></span><br><span class="line"> </span><br><span class="line">variant=$(<span class="built_in">echo</span> $(<span class="built_in">ls</span> <span class="variable">$MERGED</span>/*/HC.g.vcf.gz | sed <span class="string">&#x27;s/^/--variant /&#x27;</span> | <span class="built_in">tr</span> <span class="string">&#x27;\n&#x27;</span> <span class="string">&#x27; &#x27;</span>))</span><br><span class="line"><span class="built_in">echo</span> <span class="variable">$variant</span></span><br><span class="line"> </span><br><span class="line">gatk CombineGVCFs $<span class="variable">$variant</span> \</span><br><span class="line">    -R <span class="variable">$RefSeq</span> \</span><br><span class="line">    -O <span class="variable">$VCFPATH</span><span class="string">&#x27;/HC.g.vcf.gz&#x27;</span></span><br></pre></td></tr></table></figure>
    440. 

  440. <h3 id="GenotypeGVCFs">GenotypeGVCFs</h3>
    441. 

  441. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br></pre></td><td class="code"><pre><span class="line">nano GenotypeGVCFs.sh &amp;&amp; <span class="built_in">chmod</span> +x GenotypeGVCFs.sh</span><br><span class="line">./GenotypeGVCFs.sh</span><br></pre></td></tr></table></figure>
    442. 

  442. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br><span class="line">15</span><br><span class="line">16</span><br><span class="line">17</span><br></pre></td><td class="code"><pre><span class="line"><span class="meta">#!/bin/bash</span></span><br><span class="line"><span class="built_in">source</span> activate GATK4</span><br><span class="line"> </span><br><span class="line"><span class="comment">#任务名</span></span><br><span class="line">TASKN=SRX247249</span><br><span class="line"><span class="comment">#设置BQSR数据存放目录</span></span><br><span class="line">MERGED=/home/jovyan/upload/merged/<span class="variable">$TASKN</span></span><br><span class="line"><span class="comment">#设置RefSeq的存放目录</span></span><br><span class="line">RefSeq=/home/jovyan/data/refseq/GRCh38.p14.fna</span><br><span class="line"><span class="comment">#设置最后输出的路径</span></span><br><span class="line">VCFPATH=<span class="variable">$MERGED</span><span class="string">&#x27;/SAMPLE1&#x27;</span></span><br><span class="line"><span class="built_in">mkdir</span> -p <span class="variable">$VCFPATH</span></span><br><span class="line"> </span><br><span class="line">gatk --java-options <span class="string">&quot;-Xmx4g&quot;</span> GenotypeGVCFs \</span><br><span class="line">    -R <span class="variable">$RefSeq</span> \</span><br><span class="line">    -V <span class="variable">$VCFPATH</span><span class="string">&#x27;/HC.g.vcf.gz&#x27;</span> \</span><br><span class="line">    -O <span class="variable">$VCFPATH</span><span class="string">&#x27;/HC.vcf.gz&#x27;</span></span><br></pre></td></tr></table></figure>
    443. 

  443. <ul>
    444. 

  444. <li>最后得到的结果如下</li>
    445. 

  445. </ul>
    446. 

  446. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br></pre></td><td class="code"><pre><span class="line">├── [6.8G]  ./HC.g.vcf.gz</span><br><span class="line">├── [5.0M]  ./HC.g.vcf.gz.tbi</span><br><span class="line">├── [127M]  ./HC.vcf.gz</span><br><span class="line">├── [2.0M]  ./HC.vcf.gz.tbi</span><br></pre></td></tr></table></figure>
    447. 

  447. <h2 id="VQSR">VQSR</h2>
    448. 

  448. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br></pre></td><td class="code"><pre><span class="line">nano VQSR.sh &amp;&amp; <span class="built_in">chmod</span> +x VQSR.sh</span><br><span class="line">./VQSR.sh</span><br></pre></td></tr></table></figure>
    449. 

  449. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br><span class="line">15</span><br><span class="line">16</span><br><span class="line">17</span><br><span class="line">18</span><br><span class="line">19</span><br><span class="line">20</span><br><span class="line">21</span><br><span class="line">22</span><br><span class="line">23</span><br><span class="line">24</span><br><span class="line">25</span><br><span class="line">26</span><br><span class="line">27</span><br><span class="line">28</span><br><span class="line">29</span><br><span class="line">30</span><br><span class="line">31</span><br><span class="line">32</span><br><span class="line">33</span><br><span class="line">34</span><br><span class="line">35</span><br><span class="line">36</span><br><span class="line">37</span><br><span class="line">38</span><br><span class="line">39</span><br><span class="line">40</span><br><span class="line">41</span><br><span class="line">42</span><br><span class="line">43</span><br><span class="line">44</span><br><span class="line">45</span><br><span class="line">46</span><br><span class="line">47</span><br><span class="line">48</span><br><span class="line">49</span><br><span class="line">50</span><br><span class="line">51</span><br><span class="line">52</span><br><span class="line">53</span><br></pre></td><td class="code"><pre><span class="line"><span class="meta">#!/bin/bash</span></span><br><span class="line"><span class="built_in">source</span> activate GATK4</span><br><span class="line"> </span><br><span class="line"><span class="comment">#任务名</span></span><br><span class="line">TASKN=SRX247249</span><br><span class="line"><span class="comment">#设置BQSR数据存放目录</span></span><br><span class="line">MERGED=/home/jovyan/upload/merged/<span class="variable">$TASKN</span></span><br><span class="line"><span class="comment">#设置RefSeq的存放目录</span></span><br><span class="line">RefSeq=/home/jovyan/data/refseq/GRCh38.p14.fna</span><br><span class="line"><span class="comment">#设置最后输出的路径</span></span><br><span class="line">VCFPATH=<span class="variable">$MERGED</span><span class="string">&#x27;/SAMPLE1&#x27;</span></span><br><span class="line"><span class="comment">#设置knownSites数据存放目录</span></span><br><span class="line">knownSites=/home/jovyan/upload/knownSites</span><br><span class="line"> </span><br><span class="line">gatk VariantRecalibrator \</span><br><span class="line">    -R <span class="variable">$RefSeq</span> \</span><br><span class="line">    -V <span class="variable">$VCFPATH</span><span class="string">&#x27;/HC.vcf.gz&#x27;</span> \</span><br><span class="line">    --resource:hapmap,known=<span class="literal">false</span>,training=<span class="literal">true</span>,truth=<span class="literal">true</span>,prior=15.0 <span class="variable">$knownSites</span>/hapmap_3.3.hg38.ncbi.vcf.gz \</span><br><span class="line">    --resource:dbsnp,known=<span class="literal">true</span>,training=<span class="literal">false</span>,truth=<span class="literal">false</span>,prior=2.0 <span class="variable">$knownSites</span>/GRCh38.dbSNP.ncbi.vcf.gz \</span><br><span class="line">    -an QD -an MQ -an MQRankSum -an ReadPosRankSum -an FS -an SOR \</span><br><span class="line">    -mode SNP \</span><br><span class="line">    -O <span class="variable">$VCFPATH</span>/snp.recal \</span><br><span class="line">    --tranches-file <span class="variable">$VCFPATH</span>/snp.tranches \</span><br><span class="line">    --rscript-file <span class="variable">$VCFPATH</span>/snp.plots.R</span><br><span class="line"> </span><br><span class="line">gatk ApplyVQSR \</span><br><span class="line">    -R <span class="variable">$RefSeq</span> \</span><br><span class="line">    -V <span class="variable">$VCFPATH</span><span class="string">&#x27;/HC.vcf.gz&#x27;</span> \</span><br><span class="line">    -O <span class="variable">$VCFPATH</span><span class="string">&#x27;/snp.VQSR.vcf.gz&#x27;</span> \</span><br><span class="line">    --truth-sensitivity-filter-level 99.0 \</span><br><span class="line">    --tranches-file <span class="variable">$VCFPATH</span>/snp.tranches \</span><br><span class="line">    --recal-file <span class="variable">$VCFPATH</span>/snp.recal \</span><br><span class="line">    -mode SNP</span><br><span class="line"> </span><br><span class="line">gatk VariantRecalibrator \</span><br><span class="line">    -R <span class="variable">$RefSeq</span> \</span><br><span class="line">    -V <span class="variable">$VCFPATH</span><span class="string">&#x27;/snp.VQSR.vcf.gz&#x27;</span> \</span><br><span class="line">    --resource:dbindel,known=<span class="literal">true</span>,training=<span class="literal">false</span>,truth=<span class="literal">false</span>,prior=2.0 <span class="variable">$knownSites</span>/Homo_sapiens_assembly38.known_indels.ncbi.vcf.gz \</span><br><span class="line">    --resource:mills,known=<span class="literal">true</span>,training=<span class="literal">true</span>,truth=<span class="literal">true</span>,prior=12.0 <span class="variable">$knownSites</span>/Mills_and_1000G_gold_standard.indels.hg38.ncbi.vcf.gz \</span><br><span class="line">    -an QD -an MQ -an MQRankSum -an ReadPosRankSum -an FS -an SOR \</span><br><span class="line">    -mode INDEL --max-gaussians 6 \</span><br><span class="line">    -O <span class="variable">$VCFPATH</span>/snp.indel.recal \</span><br><span class="line">    --tranches-file <span class="variable">$VCFPATH</span>/snp.indel.tranches \</span><br><span class="line">    --rscript-file <span class="variable">$VCFPATH</span>/snp.indel.plots.R</span><br><span class="line"> </span><br><span class="line">gatk ApplyVQSR \</span><br><span class="line">    -R <span class="variable">$RefSeq</span> \</span><br><span class="line">    -V <span class="variable">$VCFPATH</span><span class="string">&#x27;/snp.VQSR.vcf.gz&#x27;</span> \</span><br><span class="line">    -O <span class="variable">$VCFPATH</span><span class="string">&#x27;/snp.indel.VQSR.vcf.gz&#x27;</span> \</span><br><span class="line">    --truth-sensitivity-filter-level 99.0 \</span><br><span class="line">    --tranches-file <span class="variable">$VCFPATH</span>/snp.indel.tranches \</span><br><span class="line">    --recal-file <span class="variable">$VCFPATH</span>/snp.indel.recal \</span><br><span class="line">    -mode INDEL</span><br></pre></td></tr></table></figure>
    450. 

  450. <ul>
    451. 

  451. <li>最后得到的结果如下</li>
    452. 

  452. </ul>
    453. 

  453. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br><span class="line">15</span><br></pre></td><td class="code"><pre><span class="line">├── [2.7M]  ./snp.plots.R</span><br><span class="line">├── [6.2M]  ./snp.plots.R.pdf</span><br><span class="line">├── [199M]  ./snp.recal</span><br><span class="line">├── [7.5M]  ./snp.recal.idx</span><br><span class="line">├── [ 584]  ./snp.tranches</span><br><span class="line">├── [7.5K]  ./snp.tranches.pdf</span><br><span class="line">├── [151M]  ./snp.VQSR.vcf.gz</span><br><span class="line">├── [2.0M]  ./snp.VQSR.vcf.gz.tbi</span><br><span class="line">├── [2.8M]  ./snp.indel.plots.R</span><br><span class="line">├── [6.2M]  ./snp.indel.plots.R.pdf</span><br><span class="line">├── [ 35M]  ./snp.indel.recal</span><br><span class="line">├── [256K]  ./snp.indel.recal.idx</span><br><span class="line">├── [ 595]  ./snp.indel.tranches</span><br><span class="line">├── [153M]  ./snp.indel.VQSR.vcf.gz</span><br><span class="line">├── [2.0M]  ./snp.indel.VQSR.vcf.gz.tbi</span><br></pre></td></tr></table></figure>
    454. 

  454. <ul>
    455. 

  455. <li>SNP内容示例</li>
    456. 

  456. </ul>
    457. 

  457. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br></pre></td><td class="code"><pre><span class="line"><span class="comment"># tabix snp.VQSR.vcf.gz  NC_000001.11 | head -n 5</span></span><br><span class="line">NC_000001.11    16378   .       T       C       35.32   VQSRTrancheSNP99.90to100.00     AC=2;AF=1.00;AN=2;DP=2;ExcessHet=0.0000;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=20.00;QD=17.66;SOR=2.303;VQSLOD=-1.018e+01;culprit=MQ GT:AD:DP:GQ:PL  1/1:0,2:2:6:47,6,0</span><br><span class="line">NC_000001.11    17020   .       G       A       59.32   VQSRTrancheSNP99.90to100.00     AC=2;AF=1.00;AN=2;DP=2;ExcessHet=0.0000;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=31.66;QD=29.66;SOR=0.693;VQSLOD=-5.480e+00;culprit=MQ GT:AD:DP:GQ:PL  1/1:0,2:2:6:71,6,0</span><br><span class="line">NC_000001.11    17385   .       G       A       60.32   VQSRTrancheSNP99.90to100.00     AC=2;AF=1.00;AN=2;DP=2;ExcessHet=0.0000;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=32.28;QD=30.16;SOR=2.303;VQSLOD=-2.357e+00;culprit=MQ GT:AD:DP:GQ:PL  1/1:0,2:2:6:72,6,0</span><br><span class="line">NC_000001.11    20254   .       G       A       64.64   VQSRTrancheSNP99.90to100.00     AC=1;AF=0.500;AN=2;BaseQRankSum=2.37;DP=8;ExcessHet=0.0000;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=24.89;MQRankSum=-2.030e-01;QD=8.08;ReadPosRankSum=-1.611e+00;SOR=1.034;VQSLOD=-1.317e+01;culprit=MQ      GT:AD:DP:GQ:PGT:PID:PL:PS       0|1:5,3:8:72:1|0:20250_T_C:72,0,126:20250</span><br><span class="line">NC_000001.11    39230   .       G       A       83.64   VQSRTrancheSNP99.90to100.00     AC=1;AF=0.500;AN=2;BaseQRankSum=-1.078e+00;DP=15;ExcessHet=0.0000;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=26.72;MQRankSum=2.20;QD=5.58;ReadPosRankSum=-1.917e+00;SOR=1.022;VQSLOD=-1.362e+01;culprit=MQ     GT:AD:DP:GQ:PL  0/1:10,5:15:91:91,0,239</span><br></pre></td></tr></table></figure>
    458. 

  458. <h2 id="变异注释">变异注释</h2>
    459. 

  459. <h3 id="安装-VEP">安装 VEP</h3>
    460. 

  460. <ul>
    461. 

  461. <li><a target="_blank" rel="noopener" href="http://www.ensembl.org/info/docs/tools/vep/index.html">VEP官网地址</a></li>
    462. 

  462. </ul>
    463. 

  463. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br></pre></td><td class="code"><pre><span class="line">sudo docker pull ensemblorg/ensembl-vep</span><br><span class="line">sudo docker run --<span class="built_in">rm</span> -t -i -v ~/upload:/data:z ensemblorg/ensembl-vep <span class="built_in">pwd</span></span><br><span class="line">sudo docker run --<span class="built_in">rm</span> -t -i -v ~/upload:/data:z ensemblorg/ensembl-vep <span class="built_in">ls</span> -al /opt/vep/</span><br><span class="line">sudo <span class="built_in">mkdir</span> -p ~/upload/vep &amp;&amp; sudo <span class="built_in">chmod</span> 777 ~/upload/vep</span><br><span class="line">sudo docker run --<span class="built_in">rm</span> -t -i -v ~/upload:/data:z -v ~/upload/vep:/opt/vep/.vep:z ensemblorg/ensembl-vep INSTALL.pl</span><br><span class="line"><span class="comment"># sudo docker run --rm -t -i -v ~/upload:/data:Z ensemblorg/ensembl-vep cat INSTALL.pl &gt; INSTALL.pl</span></span><br><span class="line"><span class="comment"># 自行分析 INSTALL.pl，构造下载后的结构，以下是104版本的</span></span><br><span class="line"><span class="comment"># 太慢了，手动下载，请各显神通，下载地址来自上一步的输出</span></span><br><span class="line">wget https://ftp.ensembl.org/pub/release-104/variation/indexed_vep_cache/homo_sapiens_vep_104_GRCh38.tar.gz -O ~/upload/vep</span><br><span class="line">tar -zxvf homo_sapiens_vep_104_GRCh38.tar.gz</span><br></pre></td></tr></table></figure>
    464. 

  464. <h3 id="进行注释">进行注释</h3>
    465. 

  465. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br></pre></td><td class="code"><pre><span class="line"><span class="built_in">mkdir</span> -p ~/upload/VEP/SRX247249 &amp;&amp; <span class="built_in">chmod</span> -R 777 ~/upload/VEP/SRX247249</span><br><span class="line"><span class="comment"># mv ~/data/refseq ~/upload</span></span><br><span class="line"><span class="comment"># chmod -R 777 ~/upload/refseq</span></span><br><span class="line"><span class="comment"># chmod -R 777 ~/upload/vep</span></span><br><span class="line"><span class="comment"># chmod -R 777 ~/upload/merged/SRX247249</span></span><br><span class="line">sudo docker run --<span class="built_in">rm</span> -t -i -v ~/upload:/data:z ensemblorg/ensembl-vep \</span><br><span class="line">    vep --fasta /data/refseq/GRCh38.p14.fna \</span><br><span class="line">        --format vcf --vcf --fork 4 --hgvs --force_overwrite --everything \</span><br><span class="line">        --offline --dir_cache /data/vep \</span><br><span class="line">        -i /data/merged/SRX247249/SAMPLE1/snp.indel.VQSR.vcf.gz \</span><br><span class="line">        -o /data/merged/SRX247249/SAMPLE1/snp.indel.VQSR.VEP.vcf</span><br><span class="line"><span class="comment"># sudo chmod 777 ~/upload/merged/SRX247249/SAMPLE1/snp.indel.VQSR.VEP.vcf</span></span><br><span class="line"><span class="comment"># pbgzip -n 4 snp.indel.VQSR.VEP.vcf</span></span><br><span class="line"><span class="comment"># tabix -p vcf snp.indel.VQSR.VEP.vcf.gz</span></span><br></pre></td></tr></table></figure>
    466. 

  466. <ul>
    467. 

  467. <li>最后得到的结果如下</li>
    468. 

  468. </ul>
    469. 

  469. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br></pre></td><td class="code"><pre><span class="line">├── [346M]  ./snp.indel.VQSR.VEP.vcf.gz</span><br><span class="line">├── [210K]  ./snp.indel.VQSR.VEP.vcf.gz_summary.html</span><br><span class="line">├── [1.6M]  ./snp.indel.VQSR.VEP.vcf.gz.tbi</span><br><span class="line">├── [8.2K]  ./snp.indel.VQSR.VEP.vcf.gz_warnings.txt</span><br></pre></td></tr></table></figure>
    470. 

  470. <figure class="highlight bash"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br></pre></td><td class="code"><pre><span class="line"><span class="comment"># tabix snp.indel.VQSR.VEP.vcf.gz  NC_000001.11 | head -n 2</span></span><br><span class="line">NC_000001.11    16378   .       T       C       35.32   VQSRTrancheSNP99.90to100.00     AC=2;AF=1.00;AN=2;DP=2;ExcessHet=0.0000;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=20.00;QD=17.66;SOR=2.303;VQSLOD=-1.018e+01;culprit=MQ;CSQ=C|downstream_gene_variant|MODIFIER|DDX11L1|ENSG00000223972|Transcript|ENST00000450305|transcribed_unprocessed_pseudogene||||||||||rs148220436|2708|1||SNV|HGNC|HGNC:37102|YES||||||||||||||||||||||||||||||||||||||||||||,C|downstream_gene_variant|MODIFIER|DDX11L1|ENSG00000223972|Transcript|ENST00000456328|processed_transcript||||||||||rs148220436|1969|1||SNV|HGNC|HGNC:37102||||1|||||||||||||||||||||||||||||||||||||||||,C|intron_variant&amp;non_coding_transcript_variant|MODIFIER|WASH7P|ENSG00000227232|Transcript|ENST00000488147|unprocessed_pseudogene||8/10|ENST00000488147.1:n.1067+229A&gt;G|||||||rs148220436||-1||SNV|HGNC|HGNC:38034|YES||||||||||||||||||||||||||||||||||||||||||||,C|downstream_gene_variant|MODIFIER|MIR6859-1|ENSG00000278267|Transcript|ENST00000619216|miRNA||||||||||rs148220436|991|-1||SNV|HGNC|HGNC:50039|YES||||||||||||||||||||||||||||||||||||||||||||,C|regulatory_region_variant|MODIFIER|||RegulatoryFeature|ENSR00000344266|CTCF_binding_site||||||||||rs148220436||||SNV|||||||||||||||||||||||||||||||||||||||||||||||,C|regulatory_region_variant|MODIFIER|||RegulatoryFeature|ENSR00001164745|promoter_flanking_region||||||||||rs148220436||||SNV||||||||||||||||||||||||||||||||||||||||||||||| GT:AD:DP:GQ:PL  1/1:0,2:2:6:47,6,0</span><br><span class="line">NC_000001.11    17020   .       G       A       59.32   VQSRTrancheSNP99.90to100.00     AC=2;AF=1.00;AN=2;DP=2;ExcessHet=0.0000;FS=0.000;MLEAC=1;MLEAF=0.500;MQ=31.66;QD=29.66;SOR=0.693;VQSLOD=-5.480e+00;culprit=MQ;CSQ=A|downstream_gene_variant|MODIFIER|DDX11L1|ENSG00000223972|Transcript|ENST00000450305|transcribed_unprocessed_pseudogene||||||||||rs199740902|3350|1||SNV|HGNC|HGNC:37102|YES||||||||||||||||||||||||||||||||||||||||||||,A|downstream_gene_variant|MODIFIER|DDX11L1|ENSG00000223972|Transcript|ENST00000456328|processed_transcript||||||||||rs199740902|2611|1||SNV|HGNC|HGNC:37102||||1|||||||||||||||||||||||||||||||||||||||||,A|non_coding_transcript_exon_variant|MODIFIER|WASH7P|ENSG00000227232|Transcript|ENST00000488147|unprocessed_pseudogene|7/11||ENST00000488147.1:n.746C&gt;T||746|||||rs199740902||-1||SNV|HGNC|HGNC:38034|YES||||||||||||||||||||||||||||||||||||||||||||,A|downstream_gene_variant|MODIFIER|MIR6859-1|ENSG00000278267|Transcript|ENST00000619216|miRNA||||||||||rs199740902|349|-1||SNV|HGNC|HGNC:50039|YES||||||||||||||||||||||||||||||||||||||||||||      GT:AD:DP:GQ:PL  1/1:0,2:2:6:71,6,0</span><br></pre></td></tr></table></figure>
    471. 

  471.                 
    472. 

  472.               </div>
    473. 

  473.             
    474. 

  474.             <hr/>
    475. 

  475.             <div>
    476. 

  476.               <div class="post-metas my-3">
    477. 

  477.   
    478. 

  478.   
    479. 

  479.     <div class="post-meta">
    480. 

  480.       <i class="iconfont icon-tags"></i>
    481. 

  481.       
    482. 

  482.         <a href="/tags/GATK/" class="print-no-link">#GATK</a>
    483. 

  483.       
    484. 

  484.         <a href="/tags/SNP/" class="print-no-link">#SNP</a>
    485. 

  485.       
    486. 

  486.         <a href="/tags/WGS/" class="print-no-link">#WGS</a>
    487. 

  487.       
    488. 

  488.     </div>
    489. 

  489.   
    490. 

  490. </div>
    491. 

  491. 

  492. 

  493.               
    494. 

  494.   
    495. 

  495. 

  496.   <div class="license-box my-3">
    497. 

  497.     <div class="license-title">
    498. 

  498.       <div>【学习】使用GATK4.0找SNP</div>
    499. 

  499.       <div>https://hexo.limour.top/shi-yong-GATK-zhao-SNP</div>
    500. 

  500.     </div>
    501. 

  501.     <div class="license-meta">
    502. 

  502.       
    503. 

  503.         <div class="license-meta-item">
    504. 

  504.           <div>Author</div>
    505. 

  505.           <div>Limour</div>
    506. 

  506.         </div>
    507. 

  507.       
    508. 

  508.       
    509. 

  509.         <div class="license-meta-item license-meta-date">
    510. 

  510.           <div>Posted on</div>
    511. 

  511.           <div>September 24, 2023</div>
    512. 

  512.         </div>
    513. 

  513.       
    514. 

  514.       
    515. 

  515.         <div class="license-meta-item license-meta-date">
    516. 

  516.           <div>Updated on</div>
    517. 

  517.           <div>March 19, 2024</div>
    518. 

  518.         </div>
    519. 

  519.       
    520. 

  520.       
    521. 

  521.         <div class="license-meta-item">
    522. 

  522.           <div>Licensed under</div>
    523. 

  523.           <div>
    524. 

  524.             
    525. 

  525.               
    526. 

  526.               
    527. 

  527.                 <a class="print-no-link" target="_blank" href="https://creativecommons.org/licenses/by-nc-sa/4.0/">
    528. 

  528.                   <span class="hint--top hint--rounded" aria-label="BY - Attribution">
    529. 

  529.                     <i class="iconfont icon-by"></i>
    530. 

  530.                   </span>
    531. 

  531.                 </a>
    532. 

  532.               
    533. 

  533.                 <a class="print-no-link" target="_blank" href="https://creativecommons.org/licenses/by-nc-sa/4.0/">
    534. 

  534.                   <span class="hint--top hint--rounded" aria-label="NC - Non-commercial">
    535. 

  535.                     <i class="iconfont icon-nc"></i>
    536. 

  536.                   </span>
    537. 

  537.                 </a>
    538. 

  538.               
    539. 

  539.                 <a class="print-no-link" target="_blank" href="https://creativecommons.org/licenses/by-nc-sa/4.0/">
    540. 

  540.                   <span class="hint--top hint--rounded" aria-label="SA - Share-alike">
    541. 

  541.                     <i class="iconfont icon-sa"></i>
    542. 

  542.                   </span>
    543. 

  543.                 </a>
    544. 

  544.               
    545. 

  545.             
    546. 

  546.           </div>
    547. 

  547.         </div>
    548. 

  548.       
    549. 

  549.     </div>
    550. 

  550.     <div class="license-icon iconfont"></div>
    551. 

  551.   </div>
    552. 

  552. 

  553. 

  554. 

  555.               
    556. 

  556.                 <div class="post-prevnext my-3">
    557. 

  557.                   <article class="post-prev col-6">
    558. 

  558.                     
    559. 

  559.                     
    560. 

  560.                       <a href="/The-Academy-System-Civilization-From-Hundreds-of-Millions-of-Years-Ago" title="【设定】亿万年前的学院制文明">
    561. 

  561.                         <i class="iconfont icon-arrowleft"></i>
    562. 

  562.                         <span class="hidden-mobile">【设定】亿万年前的学院制文明</span>
    563. 

  563.                         <span class="visible-mobile">Previous</span>
    564. 

  564.                       </a>
    565. 

  565.                     
    566. 

  566.                   </article>
    567. 

  567.                   <article class="post-next col-6">
    568. 

  568.                     
    569. 

  569.                     
    570. 

  570.                       <a href="/dan-xi-bao-zui-jia-shi-jian-de-liu-cheng" title="【复习】单细胞最佳实践的流程">
    571. 

  571.                         <span class="hidden-mobile">【复习】单细胞最佳实践的流程</span>
    572. 

  572.                         <span class="visible-mobile">Next</span>
    573. 

  573.                         <i class="iconfont icon-arrowright"></i>
    574. 

  574.                       </a>
    575. 

  575.                     
    576. 

  576.                   </article>
    577. 

  577.                 </div>
    578. 

  578.               
    579. 

  579.             </div>
    580. 

  580. 

  581.             
    582. 

  582.   
    583. 

  583.   
    584. 

  584.     <article id="comments" lazyload>
    585. 

  585.       
    586. 

  586.   <div id="waline"></div>
    587. 

  587.   <script type="text/javascript">
    588. 

  588.     Fluid.utils.loadComments('#waline', function() {
    589. 

  589.       Fluid.utils.createCssLink('https://cdn.staticfile.org/waline/2.15.5/waline.min.css')
    590. 

  590.       Fluid.utils.createScript('https://cdn.staticfile.org/waline/2.15.5/waline.min.js', function() {
    591. 

  591.         var options = Object.assign(
    592. 

  592.           {"serverURL":"https://comments.limour.top","path":"window.location.pathname","meta":["nick","mail","link"],"requiredMeta":["nick"],"lang":"zh-CN","emoji":["https://jscdn.limour.top/gh/walinejs/emojis/weibo"],"dark":"html[data-user-color-scheme=\"dark\"]","wordLimit":0,"pageSize":10},
    593. 

  593.           {
    594. 

  594.             el: '#waline',
    595. 

  595.             path: window.location.pathname
    596. 

  596.           }
    597. 

  597.         )
    598. 

  598.         Waline.init(options);
    599. 

  599.         Fluid.utils.waitElementVisible('#waline .vcontent', () => {
    600. 

  600.           var imgSelector = '#waline .vcontent img:not(.vemoji)';
    601. 

  601.           Fluid.plugins.imageCaption(imgSelector);
    602. 

  602.           Fluid.plugins.fancyBox(imgSelector);
    603. 

  603.         })
    604. 

  604.       });
    605. 

  605.     });
    606. 

  606.   </script>
    607. 

  607.   <noscript>Please enable JavaScript to view the comments</noscript>
    608. 

  608. 

  609. 

  610.     </article>
    611. 

  611.   
    612. 

  612. 

  613. 

  614.           </article>
    615. 

  615.         </div>
    616. 

  616.       </div>
    617. 

  617.     </div>
    618. 

  618. 

  619.     <div class="side-col d-none d-lg-block col-lg-2">
    620. 

  620.       
    621. 

  621.   <aside class="sidebar" style="margin-left: -1rem">
    622. 

  622.     <div id="toc">
    623. 

  623.   <p class="toc-header">
    624. 

  624.     <i class="iconfont icon-list"></i>
    625. 

  625.     <span>Table of Contents</span>
    626. 

  626.   </p>
    627. 

  627.   <div class="toc-body" id="toc-body"></div>
    628. 

  628. </div>
    629. 

  629. 

  630. 

  631. 

  632.   </aside>
    633. 

  633. 

  634. 

  635.     </div>
    636. 

  636.   </div>
    637. 

  637. </div>
    638. 

  638. 

  639. 

  640. 

  641. 

  642. 

  643.   
    644. 

  644. 

  645. 

  646. 

  647.   
    648. 

  648. 

  649. 

  650. 

  651.   
    652. 

  652. 

  653. 

  654. 

  655. 

  656.   
    657. 

  657. 

  658. 

  659. 

  660. 

  661. 

  662. 

  663. 

  664.     
    665. 

  665. 

  666.     
    667. 

  667.       <a id="scroll-top-button" aria-label="TOP" href="#" role="button">
    668. 

  668.         <i class="iconfont icon-arrowup" aria-hidden="true"></i>
    669. 

  669.       </a>
    670. 

  670.     
    671. 

  671. 

  672.     
    673. 

  673.       <div class="modal fade" id="modalSearch" tabindex="-1" role="dialog" aria-labelledby="ModalLabel"
    674. 

  674.      aria-hidden="true">
    675. 

  675.   <div class="modal-dialog modal-dialog-scrollable modal-lg" role="document">
    676. 

  676.     <div class="modal-content">
    677. 

  677.       <div class="modal-header text-center">
    678. 

  678.         <h4 class="modal-title w-100 font-weight-bold">Search</h4>
    679. 

  679.         <button type="button" id="local-search-close" class="close" data-dismiss="modal" aria-label="Close">
    680. 

  680.           <span aria-hidden="true">&times;</span>
    681. 

  681.         </button>
    682. 

  682.       </div>
    683. 

  683.       <div class="modal-body mx-3">
    684. 

  684.         <div class="md-form mb-5">
    685. 

  685.           <input type="text" id="local-search-input" class="form-control validate">
    686. 

  686.           <label data-error="x" data-success="v" for="local-search-input">Keyword</label>
    687. 

  687.         </div>
    688. 

  688.         <div class="list-group" id="local-search-result"></div>
    689. 

  689.       </div>
    690. 

  690.     </div>
    691. 

  691.   </div>
    692. 

  692. </div>
    693. 

  693. 

  694.     
    695. 

  695. 

  696.     
    697. 

  697.   </main>
    698. 

  698. 

  699.   <footer>
    700. 

  700.     <div class="footer-inner">
    701. 

  701.   
    702. 

  702.     <div class="footer-content">
    703. 

  703.        <a target="_blank" rel="nofollow noopener" href="http://www.beian.gov.cn/portal/registerSystemInfo?recordcode=43130202000203"><img src="https://img.limour.top/2023/08/27/64eadeb81d6a0.webp" srcset="https://jscdn.limour.top/gh/Limour-dev/Sakurairo_Vision/load_svg/inload.svg" lazyload>湘公网安备43130202000203号  </a> <a target="_blank" rel="nofollow noopener" href="https://beian.miit.gov.cn/">湘ICP备20008299号 </a> <a target="_blank" rel="nofollow noopener" href="https://icp.gov.moe/?keyword=20210128">萌ICP备20210128号</a> <br> <a href="https://www.foreverblog.cn/" target="_blank"> <img src="https://img.foreverblog.cn/logo_en_default.png" srcset="https://jscdn.limour.top/gh/Limour-dev/Sakurairo_Vision/load_svg/inload.svg" lazyload alt="" style="width:auto;height:24px"> </a> <br> <a href="https://hexo.io" target="_blank" rel="nofollow noopener"><span>Hexo</span></a> <i class="iconfont icon-love"></i> <a href="https://github.com/fluid-dev/hexo-theme-fluid" target="_blank" rel="nofollow noopener"><span>Fluid</span></a> <i class="iconfont icon-love"></i> <a href="https://github.com/limour-blog/limour-blog.github.io" target="_blank" rel="nofollow noopener"><span>SRC</span></a> <i class="iconfont icon-love"></i> <a href="https://web.archive.org/web/20231130095837/https://effectiveacceleration.tech/" target="_blank" rel="nofollow noopener"><span>e/Acc</span></a> 
    704. 

  704.     </div>
    705. 

  705.   
    706. 

  706.   
    707. 

  707.   
    708. 

  708.   
    709. 

  709. </div>
    710. 

  710. 

  711.   </footer>
    712. 

  712. 

  713.   <!-- Scripts -->
    714. 

  714.   
    715. 

  715.   <script  src="https://jscdn.limour.top/npm/nprogress@0.2.0/nprogress.min.js" ></script>
    716. 

  716.   <link  rel="stylesheet" href="https://jscdn.limour.top/npm/nprogress@0.2.0/nprogress.min.css" />
    717. 

  717. 

  718.   <script>
    719. 

  719.     NProgress.configure({"showSpinner":false,"trickleSpeed":100})
    720. 

  720.     NProgress.start()
    721. 

  721.     window.addEventListener('load', function() {
    722. 

  722.       NProgress.done();
    723. 

  723.     })
    724. 

  724.   </script>
    725. 

  725. 

  726. 

  727. <script  src="https://jscdn.limour.top/npm/jquery@3.6.4/dist/jquery.min.js" ></script>
    728. 

  728. <script  src="https://jscdn.limour.top/npm/bootstrap@4.6.1/dist/js/bootstrap.min.js" ></script>
    729. 

  729. <script  src="/js/events.js" ></script>
    730. 

  730. <script  src="/js/plugins.js" ></script>
    731. 

  731. 

  732. 

  733. 

  734. 

  735. 

  736.   
    737. 

  737.     <script  src="/js/img-lazyload.js" ></script>
    738. 

  738.   
    739. 

  739. 

  740. 

  741. 

  742. 

  743.   
    744. 

  744. <script>
    745. 

  745.   Fluid.utils.createScript('https://jscdn.limour.top/npm/tocbot@4.20.1/dist/tocbot.min.js', function() {
    746. 

  746.     var toc = jQuery('#toc');
    747. 

  747.     if (toc.length === 0 || !window.tocbot) { return; }
    748. 

  748.     var boardCtn = jQuery('#board-ctn');
    749. 

  749.     var boardTop = boardCtn.offset().top;
    750. 

  750. 

  751.     window.tocbot.init(Object.assign({
    752. 

  752.       tocSelector     : '#toc-body',
    753. 

  753.       contentSelector : '.markdown-body',
    754. 

  754.       linkClass       : 'tocbot-link',
    755. 

  755.       activeLinkClass : 'tocbot-active-link',
    756. 

  756.       listClass       : 'tocbot-list',
    757. 

  757.       isCollapsedClass: 'tocbot-is-collapsed',
    758. 

  758.       collapsibleClass: 'tocbot-is-collapsible',
    759. 

  759.       scrollSmooth    : true,
    760. 

  760.       includeTitleTags: true,
    761. 

  761.       headingsOffset  : -boardTop,
    762. 

  762.     }, CONFIG.toc));
    763. 

  763.     if (toc.find('.toc-list-item').length > 0) {
    764. 

  764.       toc.css('visibility', 'visible');
    765. 

  765.     }
    766. 

  766. 

  767.     Fluid.events.registerRefreshCallback(function() {
    768. 

  768.       if ('tocbot' in window) {
    769. 

  769.         tocbot.refresh();
    770. 

  770.         var toc = jQuery('#toc');
    771. 

  771.         if (toc.length === 0 || !tocbot) {
    772. 

  772.           return;
    773. 

  773.         }
    774. 

  774.         if (toc.find('.toc-list-item').length > 0) {
    775. 

  775.           toc.css('visibility', 'visible');
    776. 

  776.         }
    777. 

  777.       }
    778. 

  778.     });
    779. 

  779.   });
    780. 

  780. </script>
    781. 

  781. 

  782. 

  783.   <script src=https://lib.baomitu.com/clipboard.js/2.0.11/clipboard.min.js></script>
    784. 

  784. 

  785.   <script>Fluid.plugins.codeWidget();</script>
    786. 

  786. 

  787. 

  788.   
    789. 

  789. <script>
    790. 

  790.   Fluid.utils.createScript('https://jscdn.limour.top/npm/anchor-js@4.3.1/anchor.min.js', function() {
    791. 

  791.     window.anchors.options = {
    792. 

  792.       placement: CONFIG.anchorjs.placement,
    793. 

  793.       visible  : CONFIG.anchorjs.visible
    794. 

  794.     };
    795. 

  795.     if (CONFIG.anchorjs.icon) {
    796. 

  796.       window.anchors.options.icon = CONFIG.anchorjs.icon;
    797. 

  797.     }
    798. 

  798.     var el = (CONFIG.anchorjs.element || 'h1,h2,h3,h4,h5,h6').split(',');
    799. 

  799.     var res = [];
    800. 

  800.     for (var item of el) {
    801. 

  801.       res.push('.markdown-body > ' + item.trim());
    802. 

  802.     }
    803. 

  803.     if (CONFIG.anchorjs.placement === 'left') {
    804. 

  804.       window.anchors.options.class = 'anchorjs-link-left';
    805. 

  805.     }
    806. 

  806.     window.anchors.add(res.join(', '));
    807. 

  807. 

  808.     Fluid.events.registerRefreshCallback(function() {
    809. 

  809.       if ('anchors' in window) {
    810. 

  810.         anchors.removeAll();
    811. 

  811.         var el = (CONFIG.anchorjs.element || 'h1,h2,h3,h4,h5,h6').split(',');
    812. 

  812.         var res = [];
    813. 

  813.         for (var item of el) {
    814. 

  814.           res.push('.markdown-body > ' + item.trim());
    815. 

  815.         }
    816. 

  816.         if (CONFIG.anchorjs.placement === 'left') {
    817. 

  817.           anchors.options.class = 'anchorjs-link-left';
    818. 

  818.         }
    819. 

  819.         anchors.add(res.join(', '));
    820. 

  820.       }
    821. 

  821.     });
    822. 

  822.   });
    823. 

  823. </script>
    824. 

  824. 

  825. 

  826.   <script>Fluid.plugins.imageCaption();</script>
    827. 

  827. 

  828.   <script  src="/js/local-search.js" ></script>
    829. 

  829. 

  830. 

  831. 

  832. 

  833. 

  834. <!-- 主题的启动项，将它保持在最底部 -->
    835. 

  835. <!-- the boot of the theme, keep it at the bottom -->
    836. 

  836. <script  src="/js/boot.js" ></script>
    837. 

  837. 

  838. 

  839.   
    840. 

  840. 

  841.   <noscript>
    842. 

  842.     <div class="noscript-warning">Blog works best with JavaScript enabled</div>
    843. 

  843.   </noscript>
    844. 

  844. <!-- hexo injector body_end start -->
    845. 

  845.   <script defer src="/theme-inject/timeliness.js"></script>
    846. 

  846. <!-- hexo injector body_end end --></body>
    847. 

  847. </html>
    848.