ryan
/
resume
镜像自地址 https://github.com/DarwinAwardWinner/resume.git


			
				
					
						
						
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163
							<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"
   "http://www.w3.org/TR/html4/strict.dtd">

<html>
<head>
  <title></title>
  <meta http-equiv="content-type" content="text/html; charset=utf-8">
  <style type="text/css">
td.linenos { background-color: #f0f0f0; padding-right: 10px; }
span.lineno { background-color: #f0f0f0; padding: 0 5px 0 5px; }
pre { line-height: 125%; }
body .hll { background-color: #ffffcc }
body  { background: #f8f8f8; }
body .c { color: #408080; font-style: italic } /* Comment */
body .err { border: 1px solid #FF0000 } /* Error */
body .k { color: #008000; font-weight: bold } /* Keyword */
body .o { color: #666666 } /* Operator */
body .ch { color: #408080; font-style: italic } /* Comment.Hashbang */
body .cm { color: #408080; font-style: italic } /* Comment.Multiline */
body .cp { color: #BC7A00 } /* Comment.Preproc */
body .cpf { color: #408080; font-style: italic } /* Comment.PreprocFile */
body .c1 { color: #408080; font-style: italic } /* Comment.Single */
body .cs { color: #408080; font-style: italic } /* Comment.Special */
body .gd { color: #A00000 } /* Generic.Deleted */
body .ge { font-style: italic } /* Generic.Emph */
body .gr { color: #FF0000 } /* Generic.Error */
body .gh { color: #000080; font-weight: bold } /* Generic.Heading */
body .gi { color: #00A000 } /* Generic.Inserted */
body .go { color: #888888 } /* Generic.Output */
body .gp { color: #000080; font-weight: bold } /* Generic.Prompt */
body .gs { font-weight: bold } /* Generic.Strong */
body .gu { color: #800080; font-weight: bold } /* Generic.Subheading */
body .gt { color: #0044DD } /* Generic.Traceback */
body .kc { color: #008000; font-weight: bold } /* Keyword.Constant */
body .kd { color: #008000; font-weight: bold } /* Keyword.Declaration */
body .kn { color: #008000; font-weight: bold } /* Keyword.Namespace */
body .kp { color: #008000 } /* Keyword.Pseudo */
body .kr { color: #008000; font-weight: bold } /* Keyword.Reserved */
body .kt { color: #B00040 } /* Keyword.Type */
body .m { color: #666666 } /* Literal.Number */
body .s { color: #BA2121 } /* Literal.String */
body .na { color: #7D9029 } /* Name.Attribute */
body .nb { color: #008000 } /* Name.Builtin */
body .nc { color: #0000FF; font-weight: bold } /* Name.Class */
body .no { color: #880000 } /* Name.Constant */
body .nd { color: #AA22FF } /* Name.Decorator */
body .ni { color: #999999; font-weight: bold } /* Name.Entity */
body .ne { color: #D2413A; font-weight: bold } /* Name.Exception */
body .nf { color: #0000FF } /* Name.Function */
body .nl { color: #A0A000 } /* Name.Label */
body .nn { color: #0000FF; font-weight: bold } /* Name.Namespace */
body .nt { color: #008000; font-weight: bold } /* Name.Tag */
body .nv { color: #19177C } /* Name.Variable */
body .ow { color: #AA22FF; font-weight: bold } /* Operator.Word */
body .w { color: #bbbbbb } /* Text.Whitespace */
body .mb { color: #666666 } /* Literal.Number.Bin */
body .mf { color: #666666 } /* Literal.Number.Float */
body .mh { color: #666666 } /* Literal.Number.Hex */
body .mi { color: #666666 } /* Literal.Number.Integer */
body .mo { color: #666666 } /* Literal.Number.Oct */
body .sa { color: #BA2121 } /* Literal.String.Affix */
body .sb { color: #BA2121 } /* Literal.String.Backtick */
body .sc { color: #BA2121 } /* Literal.String.Char */
body .dl { color: #BA2121 } /* Literal.String.Delimiter */
body .sd { color: #BA2121; font-style: italic } /* Literal.String.Doc */
body .s2 { color: #BA2121 } /* Literal.String.Double */
body .se { color: #BB6622; font-weight: bold } /* Literal.String.Escape */
body .sh { color: #BA2121 } /* Literal.String.Heredoc */
body .si { color: #BB6688; font-weight: bold } /* Literal.String.Interpol */
body .sx { color: #008000 } /* Literal.String.Other */
body .sr { color: #BB6688 } /* Literal.String.Regex */
body .s1 { color: #BA2121 } /* Literal.String.Single */
body .ss { color: #19177C } /* Literal.String.Symbol */
body .bp { color: #008000 } /* Name.Builtin.Pseudo */
body .fm { color: #0000FF } /* Name.Function.Magic */
body .vc { color: #19177C } /* Name.Variable.Class */
body .vg { color: #19177C } /* Name.Variable.Global */
body .vi { color: #19177C } /* Name.Variable.Instance */
body .vm { color: #19177C } /* Name.Variable.Magic */
body .il { color: #666666 } /* Literal.Number.Integer.Long */

  </style>
</head>
<body>
<h2></h2>

<div class="highlight"><pre><span></span><span class="c1">#!/usr/bin/env Rscript</span>

<span class="c1"># Script to check reproducibility of fRMA training process</span>

<span class="kn">library</span><span class="p">(</span>xlsx<span class="p">)</span>
<span class="kn">library</span><span class="p">(</span>frma<span class="p">)</span>
<span class="kn">library</span><span class="p">(</span>frmaTools<span class="p">)</span>
<span class="kn">library</span><span class="p">(</span>stringr<span class="p">)</span>
<span class="kn">library</span><span class="p">(</span>magrittr<span class="p">)</span>
<span class="kn">library</span><span class="p">(</span>plyr<span class="p">)</span>
<span class="kn">library</span><span class="p">(</span>affy<span class="p">)</span>
<span class="kn">library</span><span class="p">(</span>preprocessCore<span class="p">)</span>
<span class="kn">library</span><span class="p">(</span>ggplot2<span class="p">)</span>
<span class="kn">library</span><span class="p">(</span>proto<span class="p">)</span>
<span class="kn">library</span><span class="p">(</span>dplyr<span class="p">)</span>
<span class="kp">load</span><span class="p">(</span><span class="s">&quot;consistency.rda&quot;</span><span class="p">)</span>

<span class="c1">## Select a random subset of 20 arrays from each tissue (Would rather</span>
<span class="c1">## use entire dataset but ENOMEM)</span>
<span class="kp">set.seed</span><span class="p">(</span><span class="m">1986</span><span class="p">)</span>
norm.exprs <span class="o">&lt;-</span> <span class="kp">lapply</span><span class="p">(</span><span class="kp">names</span><span class="p">(</span>vectors<span class="p">),</span> <span class="kr">function</span><span class="p">(</span>ttype<span class="p">)</span> <span class="p">{</span>
    stab <span class="o">&lt;-</span> sample.tables<span class="p">[[</span>ttype<span class="p">]]</span> <span class="o">%&gt;%</span> sample_n<span class="p">(</span><span class="m">20</span><span class="p">)</span>
    tsmsg<span class="p">(</span><span class="s">&quot;Reading 20 random arrays for &quot;</span><span class="p">,</span> ttype<span class="p">)</span>
    affy <span class="o">&lt;-</span> ReadAffy<span class="p">(</span>filenames<span class="o">=</span>stab<span class="o">$</span>Filename<span class="p">,</span> sampleNames<span class="o">=</span><span class="kp">rownames</span><span class="p">(</span>stab<span class="p">))</span>
    tsmsg<span class="p">(</span><span class="s">&quot;Normalizing with RMA for comparison&quot;</span><span class="p">)</span>
    eset.rma <span class="o">&lt;-</span> rma<span class="p">(</span>affy<span class="p">)</span>
    rma.exprs <span class="o">&lt;-</span> eset.rma <span class="o">%&gt;%</span> exprs <span class="o">%&gt;%</span> <span class="kp">as.vector</span>
    tsmsg<span class="p">(</span><span class="s">&quot;Normalizing with 5 trains fRMA vector sets&quot;</span><span class="p">)</span>
    esets.frma <span class="o">&lt;-</span> <span class="kp">lapply</span><span class="p">(</span>vectors<span class="p">[[</span>ttype<span class="p">]],</span> <span class="m">.</span> <span class="o">%&gt;%</span> frma<span class="p">(</span>affy<span class="p">,</span> input.vecs<span class="o">=</span><span class="m">.</span><span class="p">))</span>
    frma.exprs <span class="o">&lt;-</span> <span class="kp">sapply</span><span class="p">(</span>esets.frma<span class="p">,</span> <span class="m">.</span> <span class="o">%&gt;%</span> exprs <span class="o">%&gt;%</span> <span class="kp">as.vector</span><span class="p">)</span>
    <span class="kt">data.frame</span><span class="p">(</span>RMA<span class="o">=</span>rma.exprs<span class="p">,</span> fRMA<span class="o">=</span>frma.exprs<span class="p">)</span>
<span class="p">})</span> <span class="o">%&gt;%</span> setNames<span class="p">(</span><span class="kp">names</span><span class="p">(</span>vectors<span class="p">))</span>

<span class="c1">## Save because the above takes a while</span>
<span class="kp">save.image</span><span class="p">(</span><span class="s">&quot;consistency.rda&quot;</span><span class="p">)</span>

<span class="kp">dir.create</span><span class="p">(</span><span class="s">&quot;fRMA_consistency_results&quot;</span><span class="p">,</span> <span class="kc">FALSE</span><span class="p">)</span>

<span class="c1">## Compute M/A data for all pairwise comparisons</span>
ma.data <span class="o">&lt;-</span> <span class="kp">lapply</span><span class="p">(</span>norm.exprs<span class="p">,</span> <span class="kr">function</span><span class="p">(</span>normexprs<span class="p">)</span> <span class="p">{</span>
    normexprs <span class="o">%&gt;%</span> names <span class="o">%&gt;%</span> combn<span class="p">(</span><span class="m">2</span><span class="p">,</span> simplify<span class="o">=</span><span class="kc">FALSE</span><span class="p">)</span> <span class="o">%&gt;%</span> ldply<span class="p">(</span><span class="m">.</span> <span class="o">%&gt;%</span> <span class="p">{</span>
        col1 <span class="o">&lt;-</span> <span class="m">.</span><span class="p">[</span><span class="m">1</span><span class="p">]</span>
        col2 <span class="o">&lt;-</span> <span class="m">.</span><span class="p">[</span><span class="m">2</span><span class="p">]</span>
        x1 <span class="o">&lt;-</span> normexprs<span class="p">[[</span>col1<span class="p">]]</span>
        x2 <span class="o">&lt;-</span> normexprs<span class="p">[[</span>col2<span class="p">]]</span>
        <span class="kt">data.frame</span><span class="p">(</span>Comparison <span class="o">=</span> str_c<span class="p">(</span>col1<span class="p">,</span><span class="s">&quot;.vs.&quot;</span><span class="p">,</span>col2<span class="p">),</span>
                   x1<span class="o">=</span>x1<span class="p">,</span> x2<span class="o">=</span>x2<span class="p">,</span>
                   M <span class="o">=</span> x2 <span class="o">-</span> x1<span class="p">,</span>
                   A <span class="o">=</span> <span class="p">(</span>x1<span class="o">+</span>x2<span class="p">)</span><span class="o">/</span><span class="m">2</span><span class="p">)</span>
    <span class="p">})</span>
<span class="p">})</span>

<span class="kr">for</span> <span class="p">(</span>ttype <span class="kr">in</span> <span class="kp">names</span><span class="p">(</span>norm.exprs<span class="p">))</span> <span class="p">{</span>
    madata <span class="o">&lt;-</span> ma.data<span class="p">[[</span>ttype<span class="p">]]</span>

    pdf<span class="p">(</span>str_c<span class="p">(</span><span class="s">&quot;fRMA_consistency_results/MA Plots for &quot;</span><span class="p">,</span> ttype<span class="p">,</span> <span class="s">&quot;.pdf&quot;</span><span class="p">))</span>
    <span class="c1">## MA plot for every pair of normalizations</span>
    ddply<span class="p">(</span>madata<span class="p">,</span> <span class="m">.</span><span class="p">(</span>Comparison<span class="p">),</span> <span class="m">.</span> <span class="o">%$%</span> <span class="p">{</span>
        smoothScatter<span class="p">(</span>x<span class="o">=</span>A<span class="p">,</span> y<span class="o">=</span>M<span class="p">,</span> nbin<span class="o">=</span><span class="m">512</span><span class="p">,</span> main<span class="o">=</span>Comparison<span class="p">[</span><span class="m">1</span><span class="p">],</span> xlab<span class="o">=</span><span class="s">&quot;A&quot;</span><span class="p">,</span> ylab<span class="o">=</span><span class="s">&quot;M&quot;</span><span class="p">)</span>
    <span class="p">})</span>
    dev.off<span class="p">()</span>

    <span class="c1">## M boxplots &amp; violin plots</span>
    pdf<span class="p">(</span>str_c<span class="p">(</span><span class="s">&quot;fRMA_consistency_results/M Boxplots for &quot;</span><span class="p">,</span> ttype<span class="p">,</span> <span class="s">&quot;.pdf&quot;</span><span class="p">),</span>
        width<span class="o">=</span><span class="m">8</span><span class="p">,</span> height<span class="o">=</span><span class="m">12</span><span class="p">)</span>
    p <span class="o">&lt;-</span> ggplot<span class="p">(</span>madata<span class="p">)</span> <span class="o">+</span> aes<span class="p">(</span>x<span class="o">=</span>Comparison<span class="p">,</span> y<span class="o">=</span>M<span class="p">)</span> <span class="o">+</span>
        scale_x_discrete<span class="p">(</span>limits <span class="o">=</span> <span class="kp">rev</span><span class="p">(</span><span class="kp">levels</span><span class="p">(</span>madata<span class="o">$</span>Comparison<span class="p">)))</span> <span class="o">+</span>
            coord_flip<span class="p">()</span>
    <span class="kp">print</span><span class="p">(</span>p <span class="o">+</span> geom_boxplot<span class="p">(</span>notch<span class="o">=</span><span class="kc">TRUE</span><span class="p">,</span> outlier.shape <span class="o">=</span> <span class="kc">NA</span><span class="p">)</span> <span class="o">+</span>
          ggtitle<span class="p">(</span>str_c<span class="p">(</span><span class="s">&quot;Boxplots of M value distributions for &quot;</span><span class="p">,</span> ttype<span class="p">)))</span>
    <span class="kp">print</span><span class="p">(</span>p <span class="o">+</span> geom_violin<span class="p">(</span>scale<span class="o">=</span><span class="s">&quot;width&quot;</span><span class="p">)</span> <span class="o">+</span>
          ggtitle<span class="p">(</span>str_c<span class="p">(</span><span class="s">&quot;Violin plots of M value distributions for &quot;</span><span class="p">,</span> ttype<span class="p">)))</span>
    dev.off<span class="p">()</span>
<span class="p">}</span>
</pre></div>
</body>
</html>