|
|
|
|
|
|
|
|
<!DOCTYPE html> |
|
|
<html class="writer-html5" lang="en" > |
|
|
<head> |
|
|
<meta charset="utf-8" /> |
|
|
|
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
|
|
|
|
|
<title>dscript.commands.train — D-SCRIPT v1.0-beta documentation</title> |
|
|
|
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> |
|
|
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
|
|
<script src="../../../_static/jquery.js"></script> |
|
|
<script src="../../../_static/underscore.js"></script> |
|
|
<script src="../../../_static/doctools.js"></script> |
|
|
|
|
|
<script type="text/javascript" src="../../../_static/js/theme.js"></script> |
|
|
|
|
|
|
|
|
<link rel="index" title="Index" href="../../../genindex.html" /> |
|
|
<link rel="search" title="Search" href="../../../search.html" /> |
|
|
</head> |
|
|
|
|
|
<body class="wy-body-for-nav"> |
|
|
|
|
|
|
|
|
<div class="wy-grid-for-nav"> |
|
|
|
|
|
<nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
|
|
<div class="wy-side-scroll"> |
|
|
<div class="wy-side-nav-search" > |
|
|
|
|
|
|
|
|
|
|
|
<a href="../../../index.html" class="icon icon-home"> D-SCRIPT |
|
|
|
|
|
|
|
|
|
|
|
</a> |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div role="search"> |
|
|
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get"> |
|
|
<input type="text" name="q" placeholder="Search docs" /> |
|
|
<input type="hidden" name="check_keywords" value="yes" /> |
|
|
<input type="hidden" name="area" value="default" /> |
|
|
</form> |
|
|
</div> |
|
|
|
|
|
|
|
|
</div> |
|
|
|
|
|
|
|
|
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<ul> |
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../installation.html">Installation</a></li> |
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../usage.html">Usage</a></li> |
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../data.html">Data</a></li> |
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../api/index.html">API</a></li> |
|
|
</ul> |
|
|
|
|
|
|
|
|
|
|
|
</div> |
|
|
|
|
|
</div> |
|
|
</nav> |
|
|
|
|
|
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
|
|
|
|
|
|
|
|
<nav class="wy-nav-top" aria-label="top navigation"> |
|
|
|
|
|
<i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
|
|
<a href="../../../index.html">D-SCRIPT</a> |
|
|
|
|
|
</nav> |
|
|
|
|
|
|
|
|
<div class="wy-nav-content"> |
|
|
|
|
|
<div class="rst-content"> |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div role="navigation" aria-label="breadcrumbs navigation"> |
|
|
|
|
|
<ul class="wy-breadcrumbs"> |
|
|
|
|
|
<li><a href="../../../index.html" class="icon icon-home"></a> »</li> |
|
|
|
|
|
<li><a href="../../index.html">Module code</a> »</li> |
|
|
|
|
|
<li>dscript.commands.train</li> |
|
|
|
|
|
|
|
|
<li class="wy-breadcrumbs-aside"> |
|
|
|
|
|
</li> |
|
|
|
|
|
</ul> |
|
|
|
|
|
|
|
|
<hr/> |
|
|
</div> |
|
|
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
|
|
<div itemprop="articleBody"> |
|
|
|
|
|
<h1>Source code for dscript.commands.train</h1><div class="highlight"><pre> |
|
|
<span></span><span class="sd">"""</span> |
|
|
<span class="sd">Train a new model.</span> |
|
|
<span class="sd">"""</span> |
|
|
|
|
|
<span class="kn">import</span> <span class="nn">sys</span> |
|
|
<span class="kn">import</span> <span class="nn">argparse</span> |
|
|
<span class="kn">import</span> <span class="nn">h5py</span> |
|
|
<span class="kn">import</span> <span class="nn">datetime</span> |
|
|
<span class="kn">import</span> <span class="nn">subprocess</span> <span class="k">as</span> <span class="nn">sp</span> |
|
|
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
|
|
<span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span> |
|
|
<span class="kn">import</span> <span class="nn">gzip</span> <span class="k">as</span> <span class="nn">gz</span> |
|
|
<span class="kn">from</span> <span class="nn">tqdm</span> <span class="kn">import</span> <span class="n">tqdm</span> |
|
|
|
|
|
<span class="kn">import</span> <span class="nn">torch</span> |
|
|
<span class="kn">import</span> <span class="nn">torch.nn</span> <span class="k">as</span> <span class="nn">nn</span> |
|
|
<span class="kn">import</span> <span class="nn">torch.nn.functional</span> <span class="k">as</span> <span class="nn">F</span> |
|
|
<span class="kn">import</span> <span class="nn">torch.optim</span> <span class="k">as</span> <span class="nn">optim</span> |
|
|
<span class="kn">from</span> <span class="nn">torch.autograd</span> <span class="kn">import</span> <span class="n">Variable</span> |
|
|
<span class="kn">from</span> <span class="nn">torch.utils.data</span> <span class="kn">import</span> <span class="n">IterableDataset</span><span class="p">,</span> <span class="n">DataLoader</span> |
|
|
<span class="kn">from</span> <span class="nn">sklearn.metrics</span> <span class="kn">import</span> <span class="n">average_precision_score</span> <span class="k">as</span> <span class="n">average_precision</span> |
|
|
|
|
|
<span class="kn">import</span> <span class="nn">dscript</span> |
|
|
<span class="kn">from</span> <span class="nn">dscript.utils</span> <span class="kn">import</span> <span class="n">PairedDataset</span><span class="p">,</span> <span class="n">collate_paired_sequences</span> |
|
|
<span class="kn">from</span> <span class="nn">dscript.models.embedding</span> <span class="kn">import</span> <span class="p">(</span> |
|
|
<span class="n">IdentityEmbed</span><span class="p">,</span> |
|
|
<span class="n">FullyConnectedEmbed</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
<span class="kn">from</span> <span class="nn">dscript.models.contact</span> <span class="kn">import</span> <span class="n">ContactCNN</span> |
|
|
<span class="kn">from</span> <span class="nn">dscript.models.interaction</span> <span class="kn">import</span> <span class="n">ModelInteraction</span> |
|
|
|
|
|
|
|
|
<span class="k">def</span> <span class="nf">add_args</span><span class="p">(</span><span class="n">parser</span><span class="p">):</span> |
|
|
<span class="sd">"""</span> |
|
|
<span class="sd"> Create parser for command line utility.</span> |
|
|
|
|
|
<span class="sd"> :meta private:</span> |
|
|
<span class="sd"> """</span> |
|
|
|
|
|
<span class="n">data_grp</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">add_argument_group</span><span class="p">(</span><span class="s2">"Data"</span><span class="p">)</span> |
|
|
<span class="n">proj_grp</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">add_argument_group</span><span class="p">(</span><span class="s2">"Projection Module"</span><span class="p">)</span> |
|
|
<span class="n">contact_grp</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">add_argument_group</span><span class="p">(</span><span class="s2">"Contact Module"</span><span class="p">)</span> |
|
|
<span class="n">inter_grp</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">add_argument_group</span><span class="p">(</span><span class="s2">"Interaction Module"</span><span class="p">)</span> |
|
|
<span class="n">train_grp</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">add_argument_group</span><span class="p">(</span><span class="s2">"Training"</span><span class="p">)</span> |
|
|
<span class="n">misc_grp</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">add_argument_group</span><span class="p">(</span><span class="s2">"Output and Device"</span><span class="p">)</span> |
|
|
|
|
|
<span class="c1"># Data</span> |
|
|
<span class="n">data_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"--train"</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"Training data"</span><span class="p">,</span> <span class="n">required</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
|
|
<span class="n">data_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"--val"</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"Validation data"</span><span class="p">,</span> <span class="n">required</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
|
|
<span class="n">data_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"--embedding"</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"h5 file with embedded sequences"</span><span class="p">,</span> <span class="n">required</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
|
|
<span class="n">data_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span> |
|
|
<span class="s2">"--augment"</span><span class="p">,</span> |
|
|
<span class="n">action</span><span class="o">=</span><span class="s2">"store_true"</span><span class="p">,</span> |
|
|
<span class="n">help</span><span class="o">=</span><span class="s2">"Set flag to augment data by adding (B A) for all pairs (A B)"</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
|
|
|
<span class="c1"># Embedding model</span> |
|
|
<span class="n">proj_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span> |
|
|
<span class="s2">"--projection-dim"</span><span class="p">,</span> |
|
|
<span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> |
|
|
<span class="n">default</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> |
|
|
<span class="n">help</span><span class="o">=</span><span class="s2">"Dimension of embedding projection layer (default: 100)"</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
<span class="n">proj_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span> |
|
|
<span class="s2">"--dropout-p"</span><span class="p">,</span> |
|
|
<span class="nb">type</span><span class="o">=</span><span class="nb">float</span><span class="p">,</span> |
|
|
<span class="n">default</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> |
|
|
<span class="n">help</span><span class="o">=</span><span class="s2">"Parameter p for embedding dropout layer (default: 0.5)"</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
|
|
|
<span class="c1"># Contact model</span> |
|
|
<span class="n">contact_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span> |
|
|
<span class="s2">"--hidden-dim"</span><span class="p">,</span> |
|
|
<span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> |
|
|
<span class="n">default</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span> |
|
|
<span class="n">help</span><span class="o">=</span><span class="s2">"Number of hidden units for comparison layer in contact prediction (default: 50)"</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
<span class="n">contact_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span> |
|
|
<span class="s2">"--kernel-width"</span><span class="p">,</span> |
|
|
<span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> |
|
|
<span class="n">default</span><span class="o">=</span><span class="mi">7</span><span class="p">,</span> |
|
|
<span class="n">help</span><span class="o">=</span><span class="s2">"Width of convolutional filter for contact prediction (default: 7)"</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
|
|
|
<span class="c1"># Interaction Model</span> |
|
|
<span class="n">inter_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span> |
|
|
<span class="s2">"--use-w"</span><span class="p">,</span> |
|
|
<span class="n">action</span><span class="o">=</span><span class="s2">"store_true"</span><span class="p">,</span> |
|
|
<span class="n">help</span><span class="o">=</span><span class="s2">"Use weight matrix in interaction prediction model"</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
<span class="n">inter_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span> |
|
|
<span class="s2">"--pool-width"</span><span class="p">,</span> |
|
|
<span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> |
|
|
<span class="n">default</span><span class="o">=</span><span class="mi">9</span><span class="p">,</span> |
|
|
<span class="n">help</span><span class="o">=</span><span class="s2">"Size of max-pool in interaction model (default: 9)"</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
|
|
|
<span class="c1"># Training</span> |
|
|
<span class="n">train_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span> |
|
|
<span class="s2">"--negative-ratio"</span><span class="p">,</span> |
|
|
<span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> |
|
|
<span class="n">default</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> |
|
|
<span class="n">help</span><span class="o">=</span><span class="s2">"Number of negative training samples for each positive training sample (default: 10)"</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
<span class="n">train_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span> |
|
|
<span class="s2">"--epoch-scale"</span><span class="p">,</span> |
|
|
<span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> |
|
|
<span class="n">default</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> |
|
|
<span class="n">help</span><span class="o">=</span><span class="s2">"Report heldout performance every this many epochs (default: 5)"</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
<span class="n">train_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"--num-epochs"</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"Number of epochs (default: 100)"</span><span class="p">)</span> |
|
|
<span class="n">train_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"--batch-size"</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="mi">25</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"Minibatch size (default: 25)"</span><span class="p">)</span> |
|
|
<span class="n">train_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"--weight-decay"</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="nb">float</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"L2 regularization (default: 0)"</span><span class="p">)</span> |
|
|
<span class="n">train_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"--lr"</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="nb">float</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="mf">0.001</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"Learning rate (default: 0.001)"</span><span class="p">)</span> |
|
|
<span class="n">train_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span> |
|
|
<span class="s2">"--lambda"</span><span class="p">,</span> |
|
|
<span class="n">dest</span><span class="o">=</span><span class="s2">"lambda_"</span><span class="p">,</span> |
|
|
<span class="nb">type</span><span class="o">=</span><span class="nb">float</span><span class="p">,</span> |
|
|
<span class="n">default</span><span class="o">=</span><span class="mf">0.35</span><span class="p">,</span> |
|
|
<span class="n">help</span><span class="o">=</span><span class="s2">"Weight on the similarity objective (default: 0.35)"</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
|
|
|
<span class="c1"># Output</span> |
|
|
<span class="n">misc_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"-o"</span><span class="p">,</span> <span class="s2">"--outfile"</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"Output file path (default: stdout)"</span><span class="p">)</span> |
|
|
<span class="n">misc_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"--save-prefix"</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"Path prefix for saving models"</span><span class="p">)</span> |
|
|
<span class="n">misc_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"-d"</span><span class="p">,</span> <span class="s2">"--device"</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> <span class="n">default</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"Compute device to use"</span><span class="p">)</span> |
|
|
<span class="n">misc_grp</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"--checkpoint"</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"Checkpoint model to start training from"</span><span class="p">)</span> |
|
|
|
|
|
<span class="k">return</span> <span class="n">parser</span> |
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="predict_interaction"><a class="viewcode-back" href="../../../api/dscript.commands.html#dscript.commands.train.predict_interaction">[docs]</a><span class="k">def</span> <span class="nf">predict_interaction</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">n0</span><span class="p">,</span> <span class="n">n1</span><span class="p">,</span> <span class="n">tensors</span><span class="p">,</span> <span class="n">use_cuda</span><span class="p">):</span> |
|
|
<span class="sd">"""</span> |
|
|
<span class="sd"> Predict whether a list of protein pairs will interact.</span> |
|
|
|
|
|
<span class="sd"> :param model: Model to be trained</span> |
|
|
<span class="sd"> :type model: dscript.models.interaction.ModelInteraction</span> |
|
|
<span class="sd"> :param n0: First protein names</span> |
|
|
<span class="sd"> :type n0: list[str]</span> |
|
|
<span class="sd"> :param n1: Second protein names</span> |
|
|
<span class="sd"> :type n1: list[str]</span> |
|
|
<span class="sd"> :param tensors: Dictionary of protein names to embeddings</span> |
|
|
<span class="sd"> :type tensors: dict[str, torch.Tensor]</span> |
|
|
<span class="sd"> :param use_cuda: Whether to use GPU</span> |
|
|
<span class="sd"> :type use_cuda: bool</span> |
|
|
<span class="sd"> """</span> |
|
|
|
|
|
<span class="n">b</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">n0</span><span class="p">)</span> |
|
|
|
|
|
<span class="n">p_hat</span> <span class="o">=</span> <span class="p">[]</span> |
|
|
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">b</span><span class="p">):</span> |
|
|
<span class="n">z_a</span> <span class="o">=</span> <span class="n">tensors</span><span class="p">[</span><span class="n">n0</span><span class="p">[</span><span class="n">i</span><span class="p">]]</span> |
|
|
<span class="n">z_b</span> <span class="o">=</span> <span class="n">tensors</span><span class="p">[</span><span class="n">n1</span><span class="p">[</span><span class="n">i</span><span class="p">]]</span> |
|
|
<span class="k">if</span> <span class="n">use_cuda</span><span class="p">:</span> |
|
|
<span class="n">z_a</span> <span class="o">=</span> <span class="n">z_a</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span> |
|
|
<span class="n">z_b</span> <span class="o">=</span> <span class="n">z_b</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span> |
|
|
|
|
|
<span class="n">p_hat</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">z_a</span><span class="p">,</span> <span class="n">z_b</span><span class="p">))</span> |
|
|
<span class="n">p_hat</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="n">p_hat</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> |
|
|
<span class="k">return</span> <span class="n">p_hat</span></div> |
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="predict_cmap_interaction"><a class="viewcode-back" href="../../../api/dscript.commands.html#dscript.commands.train.predict_cmap_interaction">[docs]</a><span class="k">def</span> <span class="nf">predict_cmap_interaction</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">n0</span><span class="p">,</span> <span class="n">n1</span><span class="p">,</span> <span class="n">tensors</span><span class="p">,</span> <span class="n">use_cuda</span><span class="p">):</span> |
|
|
<span class="sd">"""</span> |
|
|
<span class="sd"> Predict whether a list of protein pairs will interact, as well as their contact map.</span> |
|
|
|
|
|
<span class="sd"> :param model: Model to be trained</span> |
|
|
<span class="sd"> :type model: dscript.models.interaction.ModelInteraction</span> |
|
|
<span class="sd"> :param n0: First protein names</span> |
|
|
<span class="sd"> :type n0: list[str]</span> |
|
|
<span class="sd"> :param n1: Second protein names</span> |
|
|
<span class="sd"> :type n1: list[str]</span> |
|
|
<span class="sd"> :param tensors: Dictionary of protein names to embeddings</span> |
|
|
<span class="sd"> :type tensors: dict[str, torch.Tensor]</span> |
|
|
<span class="sd"> :param use_cuda: Whether to use GPU</span> |
|
|
<span class="sd"> :type use_cuda: bool</span> |
|
|
<span class="sd"> """</span> |
|
|
|
|
|
<span class="n">b</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">n0</span><span class="p">)</span> |
|
|
|
|
|
<span class="n">p_hat</span> <span class="o">=</span> <span class="p">[]</span> |
|
|
<span class="n">c_map_mag</span> <span class="o">=</span> <span class="p">[]</span> |
|
|
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">b</span><span class="p">):</span> |
|
|
<span class="n">z_a</span> <span class="o">=</span> <span class="n">tensors</span><span class="p">[</span><span class="n">n0</span><span class="p">[</span><span class="n">i</span><span class="p">]]</span> |
|
|
<span class="n">z_b</span> <span class="o">=</span> <span class="n">tensors</span><span class="p">[</span><span class="n">n1</span><span class="p">[</span><span class="n">i</span><span class="p">]]</span> |
|
|
<span class="k">if</span> <span class="n">use_cuda</span><span class="p">:</span> |
|
|
<span class="n">z_a</span> <span class="o">=</span> <span class="n">z_a</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span> |
|
|
<span class="n">z_b</span> <span class="o">=</span> <span class="n">z_b</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span> |
|
|
|
|
|
<span class="n">cm</span><span class="p">,</span> <span class="n">ph</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">map_predict</span><span class="p">(</span><span class="n">z_a</span><span class="p">,</span> <span class="n">z_b</span><span class="p">)</span> |
|
|
<span class="n">p_hat</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">ph</span><span class="p">)</span> |
|
|
<span class="n">c_map_mag</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">cm</span><span class="p">))</span> |
|
|
<span class="n">p_hat</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="n">p_hat</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> |
|
|
<span class="n">c_map_mag</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="n">c_map_mag</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> |
|
|
<span class="k">return</span> <span class="n">c_map_mag</span><span class="p">,</span> <span class="n">p_hat</span></div> |
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="interaction_grad"><a class="viewcode-back" href="../../../api/dscript.commands.html#dscript.commands.train.interaction_grad">[docs]</a><span class="k">def</span> <span class="nf">interaction_grad</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">n0</span><span class="p">,</span> <span class="n">n1</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">tensors</span><span class="p">,</span> <span class="n">use_cuda</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="mf">0.35</span><span class="p">):</span> |
|
|
<span class="sd">"""</span> |
|
|
<span class="sd"> Compute gradient and backpropagate loss for a batch.</span> |
|
|
|
|
|
<span class="sd"> :param model: Model to be trained</span> |
|
|
<span class="sd"> :type model: dscript.models.interaction.ModelInteraction</span> |
|
|
<span class="sd"> :param n0: First protein names</span> |
|
|
<span class="sd"> :type n0: list[str]</span> |
|
|
<span class="sd"> :param n1: Second protein names</span> |
|
|
<span class="sd"> :type n1: list[str]</span> |
|
|
<span class="sd"> :param y: Interaction labels</span> |
|
|
<span class="sd"> :type y: torch.Tensor</span> |
|
|
<span class="sd"> :param tensors: Dictionary of protein names to embeddings</span> |
|
|
<span class="sd"> :type tensors: dict[str, torch.Tensor]</span> |
|
|
<span class="sd"> :param use_cuda: Whether to use GPU</span> |
|
|
<span class="sd"> :type use_cuda: bool</span> |
|
|
<span class="sd"> :param weight: Weight on the contact map magnitude objective. BCE loss is :math:`1 - \\text{weight}`.</span> |
|
|
<span class="sd"> :type weight: float</span> |
|
|
|
|
|
<span class="sd"> :return: (Loss, number correct, mean square error, batch size)</span> |
|
|
<span class="sd"> :rtype: (torch.Tensor, int, torch.Tensor, int)</span> |
|
|
<span class="sd"> """</span> |
|
|
|
|
|
<span class="n">c_map_mag</span><span class="p">,</span> <span class="n">p_hat</span> <span class="o">=</span> <span class="n">predict_cmap_interaction</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">n0</span><span class="p">,</span> <span class="n">n1</span><span class="p">,</span> <span class="n">tensors</span><span class="p">,</span> <span class="n">use_cuda</span><span class="p">)</span> |
|
|
<span class="k">if</span> <span class="n">use_cuda</span><span class="p">:</span> |
|
|
<span class="n">y</span> <span class="o">=</span> <span class="n">y</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span> |
|
|
<span class="n">y</span> <span class="o">=</span> <span class="n">Variable</span><span class="p">(</span><span class="n">y</span><span class="p">)</span> |
|
|
|
|
|
<span class="n">bce_loss</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">binary_cross_entropy</span><span class="p">(</span><span class="n">p_hat</span><span class="o">.</span><span class="n">float</span><span class="p">(),</span> <span class="n">y</span><span class="o">.</span><span class="n">float</span><span class="p">())</span> |
|
|
<span class="n">cmap_loss</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">c_map_mag</span><span class="p">)</span> |
|
|
<span class="n">loss</span> <span class="o">=</span> <span class="p">(</span><span class="n">weight</span> <span class="o">*</span> <span class="n">bce_loss</span><span class="p">)</span> <span class="o">+</span> <span class="p">((</span><span class="mi">1</span> <span class="o">-</span> <span class="n">weight</span><span class="p">)</span> <span class="o">*</span> <span class="n">cmap_loss</span><span class="p">)</span> |
|
|
<span class="n">b</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">p_hat</span><span class="p">)</span> |
|
|
|
|
|
<span class="c1"># backprop loss</span> |
|
|
<span class="n">loss</span><span class="o">.</span><span class="n">backward</span><span class="p">()</span> |
|
|
|
|
|
<span class="k">if</span> <span class="n">use_cuda</span><span class="p">:</span> |
|
|
<span class="n">y</span> <span class="o">=</span> <span class="n">y</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span> |
|
|
<span class="n">p_hat</span> <span class="o">=</span> <span class="n">p_hat</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span> |
|
|
|
|
|
<span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span> |
|
|
<span class="n">guess_cutoff</span> <span class="o">=</span> <span class="mf">0.5</span> |
|
|
<span class="n">p_hat</span> <span class="o">=</span> <span class="n">p_hat</span><span class="o">.</span><span class="n">float</span><span class="p">()</span> |
|
|
<span class="n">p_guess</span> <span class="o">=</span> <span class="p">(</span><span class="n">guess_cutoff</span> <span class="o">*</span> <span class="n">torch</span><span class="o">.</span><span class="n">ones</span><span class="p">(</span><span class="n">b</span><span class="p">)</span> <span class="o"><</span> <span class="n">p_hat</span><span class="p">)</span><span class="o">.</span><span class="n">float</span><span class="p">()</span> |
|
|
<span class="n">y</span> <span class="o">=</span> <span class="n">y</span><span class="o">.</span><span class="n">float</span><span class="p">()</span> |
|
|
<span class="n">correct</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">p_guess</span> <span class="o">==</span> <span class="n">y</span><span class="p">)</span><span class="o">.</span><span class="n">item</span><span class="p">()</span> |
|
|
<span class="n">mse</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">mean</span><span class="p">((</span><span class="n">y</span><span class="o">.</span><span class="n">float</span><span class="p">()</span> <span class="o">-</span> <span class="n">p_hat</span><span class="p">)</span> <span class="o">**</span> <span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">item</span><span class="p">()</span> |
|
|
|
|
|
<span class="k">return</span> <span class="n">loss</span><span class="p">,</span> <span class="n">correct</span><span class="p">,</span> <span class="n">mse</span><span class="p">,</span> <span class="n">b</span></div> |
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="interaction_eval"><a class="viewcode-back" href="../../../api/dscript.commands.html#dscript.commands.train.interaction_eval">[docs]</a><span class="k">def</span> <span class="nf">interaction_eval</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">test_iterator</span><span class="p">,</span> <span class="n">tensors</span><span class="p">,</span> <span class="n">use_cuda</span><span class="p">):</span> |
|
|
<span class="sd">"""</span> |
|
|
<span class="sd"> Evaluate test data set performance.</span> |
|
|
|
|
|
<span class="sd"> :param model: Model to be trained</span> |
|
|
<span class="sd"> :type model: dscript.models.interaction.ModelInteraction</span> |
|
|
<span class="sd"> :param test_iterator: Test data iterator</span> |
|
|
<span class="sd"> :type test_iterator: torch.utils.data.DataLoader</span> |
|
|
<span class="sd"> :param tensors: Dictionary of protein names to embeddings</span> |
|
|
<span class="sd"> :type tensors: dict[str, torch.Tensor]</span> |
|
|
<span class="sd"> :param use_cuda: Whether to use GPU</span> |
|
|
<span class="sd"> :type use_cuda: bool</span> |
|
|
|
|
|
<span class="sd"> :return: (Loss, number correct, mean square error, precision, recall, F1 Score, AUPR)</span> |
|
|
<span class="sd"> :rtype: (torch.Tensor, int, torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor)</span> |
|
|
<span class="sd"> """</span> |
|
|
<span class="n">p_hat</span> <span class="o">=</span> <span class="p">[]</span> |
|
|
<span class="n">true_y</span> <span class="o">=</span> <span class="p">[]</span> |
|
|
|
|
|
<span class="k">for</span> <span class="n">n0</span><span class="p">,</span> <span class="n">n1</span><span class="p">,</span> <span class="n">y</span> <span class="ow">in</span> <span class="n">test_iterator</span><span class="p">:</span> |
|
|
<span class="n">p_hat</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">predict_interaction</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">n0</span><span class="p">,</span> <span class="n">n1</span><span class="p">,</span> <span class="n">tensors</span><span class="p">,</span> <span class="n">use_cuda</span><span class="p">))</span> |
|
|
<span class="n">true_y</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">y</span><span class="p">)</span> |
|
|
|
|
|
<span class="n">y</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cat</span><span class="p">(</span><span class="n">true_y</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> |
|
|
<span class="n">p_hat</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cat</span><span class="p">(</span><span class="n">p_hat</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> |
|
|
|
|
|
<span class="k">if</span> <span class="n">use_cuda</span><span class="p">:</span> |
|
|
<span class="n">y</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span> |
|
|
<span class="n">p_hat</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">([</span><span class="n">x</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">p_hat</span><span class="p">])</span> |
|
|
<span class="n">p_hat</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span> |
|
|
|
|
|
<span class="n">loss</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">binary_cross_entropy</span><span class="p">(</span><span class="n">p_hat</span><span class="o">.</span><span class="n">float</span><span class="p">(),</span> <span class="n">y</span><span class="o">.</span><span class="n">float</span><span class="p">())</span><span class="o">.</span><span class="n">item</span><span class="p">()</span> |
|
|
<span class="n">b</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">y</span><span class="p">)</span> |
|
|
|
|
|
<span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span> |
|
|
<span class="n">guess_cutoff</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">([</span><span class="mf">0.5</span><span class="p">])</span><span class="o">.</span><span class="n">float</span><span class="p">()</span> |
|
|
<span class="n">p_hat</span> <span class="o">=</span> <span class="n">p_hat</span><span class="o">.</span><span class="n">float</span><span class="p">()</span> |
|
|
<span class="n">y</span> <span class="o">=</span> <span class="n">y</span><span class="o">.</span><span class="n">float</span><span class="p">()</span> |
|
|
<span class="n">p_guess</span> <span class="o">=</span> <span class="p">(</span><span class="n">guess_cutoff</span> <span class="o">*</span> <span class="n">torch</span><span class="o">.</span><span class="n">ones</span><span class="p">(</span><span class="n">b</span><span class="p">)</span> <span class="o"><</span> <span class="n">p_hat</span><span class="p">)</span><span class="o">.</span><span class="n">float</span><span class="p">()</span> |
|
|
<span class="n">correct</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">p_guess</span> <span class="o">==</span> <span class="n">y</span><span class="p">)</span><span class="o">.</span><span class="n">item</span><span class="p">()</span> |
|
|
<span class="n">mse</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">mean</span><span class="p">((</span><span class="n">y</span><span class="o">.</span><span class="n">float</span><span class="p">()</span> <span class="o">-</span> <span class="n">p_hat</span><span class="p">)</span> <span class="o">**</span> <span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">item</span><span class="p">()</span> |
|
|
|
|
|
<span class="n">tp</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">y</span> <span class="o">*</span> <span class="n">p_hat</span><span class="p">)</span><span class="o">.</span><span class="n">item</span><span class="p">()</span> |
|
|
<span class="n">pr</span> <span class="o">=</span> <span class="n">tp</span> <span class="o">/</span> <span class="n">torch</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">p_hat</span><span class="p">)</span><span class="o">.</span><span class="n">item</span><span class="p">()</span> |
|
|
<span class="n">re</span> <span class="o">=</span> <span class="n">tp</span> <span class="o">/</span> <span class="n">torch</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">y</span><span class="p">)</span><span class="o">.</span><span class="n">item</span><span class="p">()</span> |
|
|
<span class="n">f1</span> <span class="o">=</span> <span class="mi">2</span> <span class="o">*</span> <span class="n">pr</span> <span class="o">*</span> <span class="n">re</span> <span class="o">/</span> <span class="p">(</span><span class="n">pr</span> <span class="o">+</span> <span class="n">re</span><span class="p">)</span> |
|
|
|
|
|
<span class="n">y</span> <span class="o">=</span> <span class="n">y</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span><span class="o">.</span><span class="n">numpy</span><span class="p">()</span> |
|
|
<span class="n">p_hat</span> <span class="o">=</span> <span class="n">p_hat</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span><span class="o">.</span><span class="n">numpy</span><span class="p">()</span> |
|
|
|
|
|
<span class="n">aupr</span> <span class="o">=</span> <span class="n">average_precision</span><span class="p">(</span><span class="n">y</span><span class="p">,</span> <span class="n">p_hat</span><span class="p">)</span> |
|
|
|
|
|
<span class="k">return</span> <span class="n">loss</span><span class="p">,</span> <span class="n">correct</span><span class="p">,</span> <span class="n">mse</span><span class="p">,</span> <span class="n">pr</span><span class="p">,</span> <span class="n">re</span><span class="p">,</span> <span class="n">f1</span><span class="p">,</span> <span class="n">aupr</span></div> |
|
|
|
|
|
|
|
|
<span class="k">def</span> <span class="nf">main</span><span class="p">(</span><span class="n">args</span><span class="p">):</span> |
|
|
<span class="sd">"""</span> |
|
|
<span class="sd"> Run training from arguments.</span> |
|
|
|
|
|
<span class="sd"> :meta private:</span> |
|
|
<span class="sd"> """</span> |
|
|
|
|
|
<span class="n">output</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">outfile</span> |
|
|
<span class="k">if</span> <span class="n">output</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
|
|
<span class="n">output</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">stdout</span> |
|
|
<span class="k">else</span><span class="p">:</span> |
|
|
<span class="n">output</span> <span class="o">=</span> <span class="nb">open</span><span class="p">(</span><span class="n">output</span><span class="p">,</span> <span class="s2">"w"</span><span class="p">)</span> |
|
|
|
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">'# Called as: </span><span class="si">{</span><span class="s2">" "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">)</span><span class="si">}</span><span class="s1">'</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="k">if</span> <span class="n">output</span> <span class="ow">is</span> <span class="ow">not</span> <span class="n">sys</span><span class="o">.</span><span class="n">stdout</span><span class="p">:</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">'Called as: </span><span class="si">{</span><span class="s2">" "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">)</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
|
|
|
|
|
<span class="c1"># Set device</span> |
|
|
<span class="n">device</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">device</span> |
|
|
<span class="n">use_cuda</span> <span class="o">=</span> <span class="p">(</span><span class="n">device</span> <span class="o">>=</span> <span class="mi">0</span><span class="p">)</span> <span class="ow">and</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">is_available</span><span class="p">()</span> |
|
|
<span class="k">if</span> <span class="n">use_cuda</span><span class="p">:</span> |
|
|
<span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">set_device</span><span class="p">(</span><span class="n">device</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span> |
|
|
<span class="sa">f</span><span class="s2">"# Using CUDA device </span><span class="si">{</span><span class="n">device</span><span class="si">}</span><span class="s2"> - </span><span class="si">{</span><span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">get_device_name</span><span class="p">(</span><span class="n">device</span><span class="p">)</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> |
|
|
<span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
<span class="k">else</span><span class="p">:</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"# Using CPU"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="n">device</span> <span class="o">=</span> <span class="s2">"cpu"</span> |
|
|
|
|
|
<span class="n">batch_size</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">batch_size</span> |
|
|
|
|
|
<span class="n">train_fi</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">train</span> |
|
|
<span class="n">test_fi</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">val</span> |
|
|
<span class="n">augment</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">augment</span> |
|
|
<span class="n">embedding_h5</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">embedding</span> |
|
|
<span class="n">h5fi</span> <span class="o">=</span> <span class="n">h5py</span><span class="o">.</span><span class="n">File</span><span class="p">(</span><span class="n">embedding_h5</span><span class="p">,</span> <span class="s2">"r"</span><span class="p">)</span> |
|
|
|
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"# Loading training pairs from </span><span class="si">{</span><span class="n">train_fi</span><span class="si">}</span><span class="s2">..."</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="n">output</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span> |
|
|
|
|
|
<span class="n">train_df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">read_csv</span><span class="p">(</span><span class="n">train_fi</span><span class="p">,</span> <span class="n">sep</span><span class="o">=</span><span class="s2">"</span><span class="se">\t</span><span class="s2">"</span><span class="p">,</span> <span class="n">header</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span> |
|
|
<span class="k">if</span> <span class="n">augment</span><span class="p">:</span> |
|
|
<span class="n">train_n0</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">((</span><span class="n">train_df</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">train_df</span><span class="p">[</span><span class="mi">1</span><span class="p">]),</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span> |
|
|
<span class="n">train_n1</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">((</span><span class="n">train_df</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">train_df</span><span class="p">[</span><span class="mi">0</span><span class="p">]),</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span> |
|
|
<span class="n">train_y</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">from_numpy</span><span class="p">(</span><span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">((</span><span class="n">train_df</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="mi">1</span> <span class="o">-</span> <span class="n">train_df</span><span class="p">[</span><span class="mi">2</span><span class="p">]))</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> |
|
|
<span class="k">else</span><span class="p">:</span> |
|
|
<span class="n">train_n0</span><span class="p">,</span> <span class="n">train_n1</span> <span class="o">=</span> <span class="n">train_df</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">train_df</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> |
|
|
<span class="n">train_y</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">from_numpy</span><span class="p">(</span><span class="n">train_df</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> |
|
|
|
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"# Loading testing pairs from </span><span class="si">{</span><span class="n">test_fi</span><span class="si">}</span><span class="s2">..."</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="n">output</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span> |
|
|
|
|
|
<span class="n">test_df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">read_csv</span><span class="p">(</span><span class="n">test_fi</span><span class="p">,</span> <span class="n">sep</span><span class="o">=</span><span class="s2">"</span><span class="se">\t</span><span class="s2">"</span><span class="p">,</span> <span class="n">header</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span> |
|
|
<span class="k">if</span> <span class="n">augment</span><span class="p">:</span> |
|
|
<span class="n">test_n0</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">((</span><span class="n">test_df</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">test_df</span><span class="p">[</span><span class="mi">1</span><span class="p">]),</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span> |
|
|
<span class="n">test_n1</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">((</span><span class="n">test_df</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">test_df</span><span class="p">[</span><span class="mi">0</span><span class="p">]),</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span> |
|
|
<span class="n">test_y</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">from_numpy</span><span class="p">(</span><span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">((</span><span class="n">test_df</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="mi">1</span> <span class="o">-</span> <span class="n">test_df</span><span class="p">[</span><span class="mi">2</span><span class="p">]))</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> |
|
|
<span class="k">else</span><span class="p">:</span> |
|
|
<span class="n">test_n0</span><span class="p">,</span> <span class="n">test_n1</span> <span class="o">=</span> <span class="n">test_df</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">test_df</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> |
|
|
<span class="n">test_y</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">from_numpy</span><span class="p">(</span><span class="n">test_df</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> |
|
|
<span class="n">output</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span> |
|
|
|
|
|
<span class="n">train_pairs</span> <span class="o">=</span> <span class="n">PairedDataset</span><span class="p">(</span><span class="n">train_n0</span><span class="p">,</span> <span class="n">train_n1</span><span class="p">,</span> <span class="n">train_y</span><span class="p">)</span> |
|
|
<span class="n">pairs_train_iterator</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">DataLoader</span><span class="p">(</span> |
|
|
<span class="n">train_pairs</span><span class="p">,</span> |
|
|
<span class="n">batch_size</span><span class="o">=</span><span class="n">batch_size</span><span class="p">,</span> |
|
|
<span class="n">collate_fn</span><span class="o">=</span><span class="n">collate_paired_sequences</span><span class="p">,</span> |
|
|
<span class="n">shuffle</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
|
|
|
<span class="n">test_pairs</span> <span class="o">=</span> <span class="n">PairedDataset</span><span class="p">(</span><span class="n">test_n0</span><span class="p">,</span> <span class="n">test_n1</span><span class="p">,</span> <span class="n">test_y</span><span class="p">)</span> |
|
|
<span class="n">pairs_test_iterator</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">DataLoader</span><span class="p">(</span> |
|
|
<span class="n">test_pairs</span><span class="p">,</span> |
|
|
<span class="n">batch_size</span><span class="o">=</span><span class="n">batch_size</span><span class="p">,</span> |
|
|
<span class="n">collate_fn</span><span class="o">=</span><span class="n">collate_paired_sequences</span><span class="p">,</span> |
|
|
<span class="n">shuffle</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
|
|
<span class="p">)</span> |
|
|
|
|
|
<span class="n">output</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span> |
|
|
|
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"# Loading embeddings"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="n">tensors</span> <span class="o">=</span> <span class="p">{}</span> |
|
|
<span class="n">all_proteins</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span><span class="n">train_n0</span><span class="p">)</span><span class="o">.</span><span class="n">union</span><span class="p">(</span><span class="nb">set</span><span class="p">(</span><span class="n">train_n1</span><span class="p">))</span><span class="o">.</span><span class="n">union</span><span class="p">(</span><span class="nb">set</span><span class="p">(</span><span class="n">test_n0</span><span class="p">))</span><span class="o">.</span><span class="n">union</span><span class="p">(</span><span class="nb">set</span><span class="p">(</span><span class="n">test_n1</span><span class="p">))</span> |
|
|
<span class="k">for</span> <span class="n">prot_name</span> <span class="ow">in</span> <span class="n">tqdm</span><span class="p">(</span><span class="n">all_proteins</span><span class="p">):</span> |
|
|
<span class="n">tensors</span><span class="p">[</span><span class="n">prot_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">from_numpy</span><span class="p">(</span><span class="n">h5fi</span><span class="p">[</span><span class="n">prot_name</span><span class="p">][:,</span> <span class="p">:])</span> |
|
|
|
|
|
<span class="n">use_cuda</span> <span class="o">=</span> <span class="p">(</span><span class="n">args</span><span class="o">.</span><span class="n">device</span> <span class="o">></span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span> <span class="ow">and</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">is_available</span><span class="p">()</span> |
|
|
|
|
|
<span class="k">if</span> <span class="n">args</span><span class="o">.</span><span class="n">checkpoint</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
|
|
|
|
|
<span class="n">projection_dim</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">projection_dim</span> |
|
|
<span class="n">dropout_p</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">dropout_p</span> |
|
|
<span class="n">embedding</span> <span class="o">=</span> <span class="n">FullyConnectedEmbed</span><span class="p">(</span><span class="mi">6165</span><span class="p">,</span> <span class="n">projection_dim</span><span class="p">,</span> <span class="n">dropout</span><span class="o">=</span><span class="n">dropout_p</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"# Initializing embedding model with:"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\t</span><span class="s2">projection_dim: </span><span class="si">{</span><span class="n">projection_dim</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\t</span><span class="s2">dropout_p: </span><span class="si">{</span><span class="n">dropout_p</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
|
|
|
<span class="c1"># Create contact model</span> |
|
|
<span class="n">hidden_dim</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">hidden_dim</span> |
|
|
<span class="n">kernel_width</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">kernel_width</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"# Initializing contact model with:"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\t</span><span class="s2">hidden_dim: </span><span class="si">{</span><span class="n">hidden_dim</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\t</span><span class="s2">kernel_width: </span><span class="si">{</span><span class="n">kernel_width</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
|
|
|
<span class="n">contact</span> <span class="o">=</span> <span class="n">ContactCNN</span><span class="p">(</span><span class="n">projection_dim</span><span class="p">,</span> <span class="n">hidden_dim</span><span class="p">,</span> <span class="n">kernel_width</span><span class="p">)</span> |
|
|
|
|
|
<span class="c1"># Create the full model</span> |
|
|
<span class="n">use_W</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">use_w</span> |
|
|
<span class="n">pool_width</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">pool_width</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"# Initializing interaction model with:"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\t</span><span class="s2">pool_width: </span><span class="si">{</span><span class="n">pool_width</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\t</span><span class="s2">use_w: </span><span class="si">{</span><span class="n">use_W</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="n">model</span> <span class="o">=</span> <span class="n">ModelInteraction</span><span class="p">(</span><span class="n">embedding</span><span class="p">,</span> <span class="n">contact</span><span class="p">,</span> <span class="n">use_W</span><span class="o">=</span><span class="n">use_W</span><span class="p">,</span> <span class="n">pool_size</span><span class="o">=</span><span class="n">pool_width</span><span class="p">)</span> |
|
|
|
|
|
<span class="nb">print</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
|
|
|
<span class="k">else</span><span class="p">:</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"# Loading model from checkpoint </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">args</span><span class="o">.</span><span class="n">checkpoint</span><span class="p">),</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="n">model</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">args</span><span class="o">.</span><span class="n">checkpoint</span><span class="p">)</span> |
|
|
<span class="n">model</span><span class="o">.</span><span class="n">use_cuda</span> <span class="o">=</span> <span class="n">use_cuda</span> |
|
|
|
|
|
<span class="k">if</span> <span class="n">use_cuda</span><span class="p">:</span> |
|
|
<span class="n">model</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span> |
|
|
|
|
|
<span class="c1"># Train the model</span> |
|
|
<span class="n">lr</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">lr</span> |
|
|
<span class="n">wd</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">weight_decay</span> |
|
|
<span class="n">num_epochs</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">num_epochs</span> |
|
|
<span class="n">batch_size</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">batch_size</span> |
|
|
<span class="n">report_steps</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">epoch_scale</span> |
|
|
<span class="n">inter_weight</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">lambda_</span> |
|
|
<span class="n">cmap_weight</span> <span class="o">=</span> <span class="mi">1</span> <span class="o">-</span> <span class="n">inter_weight</span> |
|
|
<span class="n">digits</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">floor</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">log10</span><span class="p">(</span><span class="n">num_epochs</span><span class="p">)))</span> <span class="o">+</span> <span class="mi">1</span> |
|
|
<span class="n">save_prefix</span> <span class="o">=</span> <span class="n">args</span><span class="o">.</span><span class="n">save_prefix</span> |
|
|
<span class="k">if</span> <span class="n">save_prefix</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
|
|
<span class="n">save_prefix</span> <span class="o">=</span> <span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span><span class="o">.</span><span class="n">strftime</span><span class="p">(</span><span class="s2">"%Y-%m-</span><span class="si">%d</span><span class="s2">-%H-%M"</span><span class="p">)</span> |
|
|
|
|
|
<span class="n">params</span> <span class="o">=</span> <span class="p">[</span><span class="n">p</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">()</span> <span class="k">if</span> <span class="n">p</span><span class="o">.</span><span class="n">requires_grad</span><span class="p">]</span> |
|
|
<span class="n">optim</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">Adam</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="n">lr</span><span class="p">,</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">wd</span><span class="p">)</span> |
|
|
|
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">'# Using save prefix "</span><span class="si">{</span><span class="n">save_prefix</span><span class="si">}</span><span class="s1">"'</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"# Training with Adam: lr=</span><span class="si">{</span><span class="n">lr</span><span class="si">}</span><span class="s2">, weight_decay=</span><span class="si">{</span><span class="n">wd</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\t</span><span class="s2">num_epochs: </span><span class="si">{</span><span class="n">num_epochs</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\t</span><span class="s2">epoch_scale: </span><span class="si">{</span><span class="n">report_steps</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\t</span><span class="s2">batch_size: </span><span class="si">{</span><span class="n">batch_size</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\t</span><span class="s2">interaction weight: </span><span class="si">{</span><span class="n">inter_weight</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\t</span><span class="s2">contact map weight: </span><span class="si">{</span><span class="n">cmap_weight</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="n">output</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span> |
|
|
|
|
|
<span class="n">batch_report_fmt</span> <span class="o">=</span> <span class="s2">"# [</span><span class="si">{}</span><span class="s2">/</span><span class="si">{}</span><span class="s2">] training </span><span class="si">{:.1%}</span><span class="s2">: Loss=</span><span class="si">{:.6}</span><span class="s2">, Accuracy=</span><span class="si">{:.3%}</span><span class="s2">, MSE=</span><span class="si">{:.6}</span><span class="s2">"</span> |
|
|
<span class="n">epoch_report_fmt</span> <span class="o">=</span> <span class="s2">"# Finished Epoch </span><span class="si">{}</span><span class="s2">/</span><span class="si">{}</span><span class="s2">: Loss=</span><span class="si">{:.6}</span><span class="s2">, Accuracy=</span><span class="si">{:.3%}</span><span class="s2">, MSE=</span><span class="si">{:.6}</span><span class="s2">, Precision=</span><span class="si">{:.6}</span><span class="s2">, Recall=</span><span class="si">{:.6}</span><span class="s2">, F1=</span><span class="si">{:.6}</span><span class="s2">, AUPR=</span><span class="si">{:.6}</span><span class="s2">"</span> |
|
|
|
|
|
<span class="n">N</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">pairs_train_iterator</span><span class="p">)</span> <span class="o">*</span> <span class="n">batch_size</span> |
|
|
<span class="k">for</span> <span class="n">epoch</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">num_epochs</span><span class="p">):</span> |
|
|
|
|
|
<span class="n">model</span><span class="o">.</span><span class="n">train</span><span class="p">()</span> |
|
|
|
|
|
<span class="n">n</span> <span class="o">=</span> <span class="mi">0</span> |
|
|
<span class="n">loss_accum</span> <span class="o">=</span> <span class="mi">0</span> |
|
|
<span class="n">acc_accum</span> <span class="o">=</span> <span class="mi">0</span> |
|
|
<span class="n">mse_accum</span> <span class="o">=</span> <span class="mi">0</span> |
|
|
|
|
|
<span class="c1"># Train batches</span> |
|
|
<span class="k">for</span> <span class="p">(</span><span class="n">z0</span><span class="p">,</span> <span class="n">z1</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span> <span class="ow">in</span> <span class="n">tqdm</span><span class="p">(</span><span class="n">pairs_train_iterator</span><span class="p">,</span> <span class="n">desc</span><span class="o">=</span><span class="sa">f</span><span class="s2">"Epoch </span><span class="si">{</span><span class="n">epoch</span><span class="o">+</span><span class="mi">1</span><span class="si">}</span><span class="s2">/</span><span class="si">{</span><span class="n">num_epochs</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span><span class="n">total</span><span class="o">=</span><span class="nb">len</span><span class="p">(</span><span class="n">pairs_train_iterator</span><span class="p">)):</span> |
|
|
|
|
|
<span class="n">loss</span><span class="p">,</span> <span class="n">correct</span><span class="p">,</span> <span class="n">mse</span><span class="p">,</span> <span class="n">b</span> <span class="o">=</span> <span class="n">interaction_grad</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">z0</span><span class="p">,</span> <span class="n">z1</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">tensors</span><span class="p">,</span> <span class="n">use_cuda</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="n">inter_weight</span><span class="p">)</span> |
|
|
|
|
|
<span class="n">n</span> <span class="o">+=</span> <span class="n">b</span> |
|
|
<span class="n">delta</span> <span class="o">=</span> <span class="n">b</span> <span class="o">*</span> <span class="p">(</span><span class="n">loss</span> <span class="o">-</span> <span class="n">loss_accum</span><span class="p">)</span> |
|
|
<span class="n">loss_accum</span> <span class="o">+=</span> <span class="n">delta</span> <span class="o">/</span> <span class="n">n</span> |
|
|
|
|
|
<span class="n">delta</span> <span class="o">=</span> <span class="n">correct</span> <span class="o">-</span> <span class="n">b</span> <span class="o">*</span> <span class="n">acc_accum</span> |
|
|
<span class="n">acc_accum</span> <span class="o">+=</span> <span class="n">delta</span> <span class="o">/</span> <span class="n">n</span> |
|
|
|
|
|
<span class="n">delta</span> <span class="o">=</span> <span class="n">b</span> <span class="o">*</span> <span class="p">(</span><span class="n">mse</span> <span class="o">-</span> <span class="n">mse_accum</span><span class="p">)</span> |
|
|
<span class="n">mse_accum</span> <span class="o">+=</span> <span class="n">delta</span> <span class="o">/</span> <span class="n">n</span> |
|
|
|
|
|
<span class="n">report</span> <span class="o">=</span> <span class="p">(</span><span class="n">n</span> <span class="o">-</span> <span class="n">b</span><span class="p">)</span> <span class="o">//</span> <span class="mi">100</span> <span class="o"><</span> <span class="n">n</span> <span class="o">//</span> <span class="mi">100</span> |
|
|
|
|
|
<span class="n">optim</span><span class="o">.</span><span class="n">step</span><span class="p">()</span> |
|
|
<span class="n">optim</span><span class="o">.</span><span class="n">zero_grad</span><span class="p">()</span> |
|
|
<span class="n">model</span><span class="o">.</span><span class="n">clip</span><span class="p">()</span> |
|
|
|
|
|
<span class="k">if</span> <span class="n">report</span><span class="p">:</span> |
|
|
<span class="n">tokens</span> <span class="o">=</span> <span class="p">[</span> |
|
|
<span class="n">epoch</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> |
|
|
<span class="n">num_epochs</span><span class="p">,</span> |
|
|
<span class="n">n</span> <span class="o">/</span> <span class="n">N</span><span class="p">,</span> |
|
|
<span class="n">loss_accum</span><span class="p">,</span> |
|
|
<span class="n">acc_accum</span><span class="p">,</span> |
|
|
<span class="n">mse_accum</span><span class="p">,</span> |
|
|
<span class="p">]</span> |
|
|
<span class="k">if</span> <span class="n">output</span> <span class="ow">is</span> <span class="ow">not</span> <span class="n">sys</span><span class="o">.</span><span class="n">stdout</span><span class="p">:</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="n">batch_report_fmt</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">*</span><span class="n">tokens</span><span class="p">),</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="n">output</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span> |
|
|
|
|
|
<span class="k">if</span> <span class="p">(</span><span class="n">epoch</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">%</span> <span class="n">report_steps</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
|
|
<span class="n">model</span><span class="o">.</span><span class="n">eval</span><span class="p">()</span> |
|
|
|
|
|
<span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span> |
|
|
|
|
|
<span class="p">(</span> |
|
|
<span class="n">inter_loss</span><span class="p">,</span> |
|
|
<span class="n">inter_correct</span><span class="p">,</span> |
|
|
<span class="n">inter_mse</span><span class="p">,</span> |
|
|
<span class="n">inter_pr</span><span class="p">,</span> |
|
|
<span class="n">inter_re</span><span class="p">,</span> |
|
|
<span class="n">inter_f1</span><span class="p">,</span> |
|
|
<span class="n">inter_aupr</span><span class="p">,</span> |
|
|
<span class="p">)</span> <span class="o">=</span> <span class="n">interaction_eval</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">pairs_test_iterator</span><span class="p">,</span> <span class="n">tensors</span><span class="p">,</span> <span class="n">use_cuda</span><span class="p">)</span> |
|
|
<span class="n">tokens</span> <span class="o">=</span> <span class="p">[</span> |
|
|
<span class="n">epoch</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> |
|
|
<span class="n">num_epochs</span><span class="p">,</span> |
|
|
<span class="n">inter_loss</span><span class="p">,</span> |
|
|
<span class="n">inter_correct</span> <span class="o">/</span> <span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">pairs_test_iterator</span><span class="p">)</span> <span class="o">*</span> <span class="n">batch_size</span><span class="p">),</span> |
|
|
<span class="n">inter_mse</span><span class="p">,</span> |
|
|
<span class="n">inter_pr</span><span class="p">,</span> |
|
|
<span class="n">inter_re</span><span class="p">,</span> |
|
|
<span class="n">inter_f1</span><span class="p">,</span> |
|
|
<span class="n">inter_aupr</span><span class="p">,</span> |
|
|
<span class="p">]</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="n">epoch_report_fmt</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">*</span><span class="n">tokens</span><span class="p">),</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="n">output</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span> |
|
|
|
|
|
<span class="c1"># Save the model</span> |
|
|
<span class="k">if</span> <span class="n">save_prefix</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
|
|
<span class="n">save_path</span> <span class="o">=</span> <span class="n">save_prefix</span> <span class="o">+</span> <span class="s2">"_epoch"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">epoch</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">zfill</span><span class="p">(</span><span class="n">digits</span><span class="p">)</span> <span class="o">+</span> <span class="s2">".sav"</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"# Saving model to </span><span class="si">{</span><span class="n">save_path</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="n">model</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span> |
|
|
<span class="n">torch</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">save_path</span><span class="p">)</span> |
|
|
<span class="k">if</span> <span class="n">use_cuda</span><span class="p">:</span> |
|
|
<span class="n">model</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span> |
|
|
|
|
|
<span class="n">output</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span> |
|
|
|
|
|
<span class="k">if</span> <span class="n">save_prefix</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
|
|
<span class="n">save_path</span> <span class="o">=</span> <span class="n">save_prefix</span> <span class="o">+</span> <span class="s2">"_final.sav"</span> |
|
|
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"# Saving final model to </span><span class="si">{</span><span class="n">save_path</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> <span class="n">file</span><span class="o">=</span><span class="n">output</span><span class="p">)</span> |
|
|
<span class="n">model</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span> |
|
|
<span class="n">torch</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">save_path</span><span class="p">)</span> |
|
|
<span class="k">if</span> <span class="n">use_cuda</span><span class="p">:</span> |
|
|
<span class="n">model</span><span class="o">.</span><span class="n">cuda</span><span class="p">()</span> |
|
|
|
|
|
<span class="n">output</span><span class="o">.</span><span class="n">close</span><span class="p">()</span> |
|
|
|
|
|
|
|
|
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span> |
|
|
<span class="n">parser</span> <span class="o">=</span> <span class="n">argparse</span><span class="o">.</span><span class="n">ArgumentParser</span><span class="p">(</span><span class="n">description</span><span class="o">=</span><span class="vm">__doc__</span><span class="p">)</span> |
|
|
<span class="n">add_args</span><span class="p">(</span><span class="n">parser</span><span class="p">)</span> |
|
|
<span class="n">main</span><span class="p">(</span><span class="n">parser</span><span class="o">.</span><span class="n">parse_args</span><span class="p">())</span> |
|
|
</pre></div> |
|
|
|
|
|
</div> |
|
|
|
|
|
</div> |
|
|
<footer> |
|
|
|
|
|
<hr/> |
|
|
|
|
|
<div role="contentinfo"> |
|
|
<p> |
|
|
© Copyright 2020, Samuel Sledzieski, Rohit Singh. |
|
|
|
|
|
</p> |
|
|
</div> |
|
|
|
|
|
|
|
|
|
|
|
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a |
|
|
|
|
|
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a> |
|
|
|
|
|
provided by <a href="https://readthedocs.org">Read the Docs</a>. |
|
|
|
|
|
</footer> |
|
|
</div> |
|
|
</div> |
|
|
|
|
|
</section> |
|
|
|
|
|
</div> |
|
|
|
|
|
|
|
|
<script type="text/javascript"> |
|
|
jQuery(function () { |
|
|
SphinxRtdTheme.Navigation.enable(true); |
|
|
}); |
|
|
</script> |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</body> |
|
|
</html> |
