Skip to content

Commit

Permalink
Built site for gh-pages
Browse files Browse the repository at this point in the history
  • Loading branch information
@ellispatrick
ellispatrick committed Dec 15, 2024
1 parent b6c476d commit e091ceb
Show file tree
Hide file tree
Showing 11 changed files with 465 additions and 16 deletions.
2 changes: 1 addition & 1 deletion .nojekyll
View file
Original file line number Diff line number Diff line change
@@ -1 +1 @@
fa4d7850
42df7a45
140 changes: 135 additions & 5 deletions Procedure1.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,40 @@
margin: 0 0.8em 0.2em -1em; /* quarto-specific, see https://github.com/quarto-dev/quarto-cli/issues/4556 */
vertical-align: middle;
}
/* CSS for syntax highlighting */
pre > code.sourceCode { white-space: pre; position: relative; }
pre > code.sourceCode > span { line-height: 1.25; }
pre > code.sourceCode > span:empty { height: 1.2em; }
.sourceCode { overflow: visible; }
code.sourceCode > span { color: inherit; text-decoration: inherit; }
div.sourceCode { margin: 1em 0; }
pre.sourceCode { margin: 0; }
@media screen {
div.sourceCode { overflow: auto; }
}
@media print {
pre > code.sourceCode { white-space: pre-wrap; }
pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; }
}
pre.numberSource code
{ counter-reset: source-line 0; }
pre.numberSource code > span
{ position: relative; left: -4em; counter-increment: source-line; }
pre.numberSource code > span > a:first-child::before
{ content: counter(source-line);
position: relative; left: -1em; text-align: right; vertical-align: baseline;
border: none; display: inline-block;
-webkit-touch-callout: none; -webkit-user-select: none;
-khtml-user-select: none; -moz-user-select: none;
-ms-user-select: none; user-select: none;
padding: 0 4px; width: 4em;
}
pre.numberSource { margin-left: 3em; padding-left: 4px; }
div.sourceCode
{ }
@media screen {
pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
}
</style>


Expand Down Expand Up @@ -158,7 +192,12 @@ <h2 id="toc-title">Table of contents</h2>

<ul>
<li><a href="#intro" id="toc-intro" class="nav-link active" data-scroll-target="#intro"><span class="header-section-number">2.1</span> Intro</a></li>
<li><a href="#next-thing" id="toc-next-thing" class="nav-link" data-scroll-target="#next-thing"><span class="header-section-number">2.2</span> Next thing</a></li>
<li><a href="#set-up-the-environment-and-data-objects" id="toc-set-up-the-environment-and-data-objects" class="nav-link" data-scroll-target="#set-up-the-environment-and-data-objects"><span class="header-section-number">2.2</span> Set up the environment and data objects</a></li>
<li><a href="#final-procedure-using-scm-classifier-with-5-of-features-selected-from-t-test" id="toc-final-procedure-using-scm-classifier-with-5-of-features-selected-from-t-test" class="nav-link" data-scroll-target="#final-procedure-using-scm-classifier-with-5-of-features-selected-from-t-test"><span class="header-section-number">3</span> ## Final Procedure using SCM Classifier with 5% of features selected from t-test</a>
<ul class="collapse">
<li><a href="#cross-validated-classification" id="toc-cross-validated-classification" class="nav-link" data-scroll-target="#cross-validated-classification"><span class="header-section-number">3.1</span> Cross-validated Classification</a></li>
<li><a href="#classification-evaluation" id="toc-classification-evaluation" class="nav-link" data-scroll-target="#classification-evaluation"><span class="header-section-number">3.2</span> Classification Evaluation</a></li>
</ul></li>
</ul>
</nav>
</div>
Expand Down Expand Up @@ -186,13 +225,104 @@ <h1 class="title"><span class="chapter-number">2</span>&nbsp; <span class="chapt

<section id="intro" class="level2" data-number="2.1">
<h2 data-number="2.1" class="anchored" data-anchor-id="intro"><span class="header-section-number">2.1</span> Intro</h2>
<p>text</p>
<p>Procedure 1 aims to compare the classification sample accuracy in bulked and pseudobulked data using an SVM classifier. Sample accuracy calcualtes the proportion of correct predicted classifications over n repeats. For example, if 70 out of 100 repeats accurately classify an individual, their sample accuracy is 0.70.</p>
<p>For this analysis, a single-cell transcriptomics dataset for 54 oestrogen receptor positive (ER+)/progesterone receptor positive (PR+) breast cancer patients is used. There are 280 genes and 6 cell types. The classification outcomes are ‘cluster 1’ and ‘cluster 2’, found by unsupervised machine learning. Cluster 1 corresponds to patients with higher expression of LPL, CAVIN2, and TIMP4 in macrophage cells, and ADIPOQ in stromal cells, associated with better survival. Cluster 2 is the opposite, associated with poorer survival. More details on the clusters can be found at https://www.biorxiv.org/content/10.1101/2024.07.02.601790v1.full.</p>
</section>
<section id="set-up-the-environment-and-data-objects" class="level2" data-number="2.2">
<h2 data-number="2.2" class="anchored" data-anchor-id="set-up-the-environment-and-data-objects"><span class="header-section-number">2.2</span> Set up the environment and data objects</h2>
<p><strong>1. Load the R packages into the R environment:</strong></p>
<p><span style="color: grey;">Timing ~ 6.5s</span></p>
<div class="cell">
<div class="sourceCode cell-code" id="cb1"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(ClassifyR)</span>
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(openxlsx)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
</section>
<section id="next-thing" class="level2" data-number="2.2">
<h2 data-number="2.2" class="anchored" data-anchor-id="next-thing"><span class="header-section-number">2.2</span> Next thing</h2>
<p>more text</p>
<section id="final-procedure-using-scm-classifier-with-5-of-features-selected-from-t-test" class="level1" data-number="3">
<h1 data-number="3"><span class="header-section-number">3</span> ## Final Procedure using SCM Classifier with 5% of features selected from t-test</h1>
<p><strong>2. Import datasets</strong></p>
<p><span style="color: grey;">Timing ~ 0.15s</span></p>
<div class="cell">
<div class="sourceCode cell-code" id="cb2"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a>p <span class="ot">&lt;-</span> <span class="fu">readRDS</span>(<span class="st">"data/procedure1/pseudobulk_overall_sum.rds"</span>)</span>
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a>p_cell <span class="ot">&lt;-</span> <span class="fu">readRDS</span>(<span class="st">"data/procedure1/pseudobulk_celltype_sum.rds"</span>)</span>
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a>data <span class="ot">=</span> <span class="fu">list</span>(<span class="st">"pseudo_bulk_overall"</span> <span class="ot">=</span> p, <span class="st">"pseudo_bulk_cell"</span> <span class="ot">=</span> p_cell)</span>
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a>clusters <span class="ot">&lt;-</span> <span class="fu">readRDS</span>(<span class="st">"data/procedure1/cluster_result_ER_and_PR_onlyER+PR+.rds"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<p>The first and second command respectively read in the bulked and pseudobulked transcriptomic datasets for the 54 individuals.</p>
<p>Both datasets are combined into a list structure for downstream analysis.</p>
<p>The final command reads in the clustering outcome to be predicted.</p>
<section id="cross-validated-classification" class="level2" data-number="3.1">
<h2 data-number="3.1" class="anchored" data-anchor-id="cross-validated-classification"><span class="header-section-number">3.1</span> Cross-validated Classification</h2>
<p><strong>3. Classifying patients into clusters</strong></p>
<p><span style="color: grey;">Timing ~ 17.0s</span></p>
<div class="cell">
<div class="sourceCode cell-code" id="cb3"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="fu">set.seed</span>(<span class="dv">1</span>)</span>
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a>nFeatures <span class="ot">=</span> <span class="fu">list</span>(<span class="at">pseudo_bulk_overall =</span> <span class="fl">0.05</span><span class="sc">*</span><span class="fu">ncol</span>(p), <span class="at">pseudo_bulk_cell =</span> <span class="fl">0.05</span><span class="sc">*</span><span class="fu">ncol</span>(p_cell))</span>
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a>classifyr_result3 <span class="ot">&lt;-</span> <span class="fu">crossValidate</span>(data, <span class="at">outcome =</span> clusters<span class="sc">$</span>cluster, <span class="at">classifier =</span> <span class="st">"SVM"</span>, <span class="at">nFeatures =</span> nFeatures, <span class="at">nFolds =</span> <span class="dv">5</span>, <span class="at">nRepeats =</span> <span class="dv">100</span>, <span class="at">nCores =</span> <span class="dv">5</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<p>The <code>set.seed(1)</code> command ensures that any subsequent operations involving randomness yield consistent results across runs.</p>
<p>The second command defines the number of features to be selected. Here, it is set to 5% of the available features in each dataset.</p>
<p>The final command uses the <code>crossValidate</code> function to perform 5-fold cross-validation with the SVM classifier on both datasets. This process is repeated 100 times and utilizes 5 CPU cores for parallel processing to speed up classification. The type of classifier, number of folds, repeats and cores used can be adjusted as wished for different analyses.<br>
<br>
</p>
</section>
<section id="classification-evaluation" class="level2" data-number="3.2">
<h2 data-number="3.2" class="anchored" data-anchor-id="classification-evaluation"><span class="header-section-number">3.2</span> Classification Evaluation</h2>
<p><strong>4. Classification Accuracy</strong></p>
<p><span style="color: grey;">Timing ~ 0.21s</span></p>
<div class="cell">
<div class="sourceCode cell-code" id="cb4"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a>classifyr_result3 <span class="ot">&lt;-</span> <span class="fu">sapply</span>(classifyr_result3, <span class="cf">function</span>(results) {</span>
<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a> <span class="fu">calcCVperformance</span>(results, <span class="at">performanceType =</span> <span class="st">"Sample Accuracy"</span>)</span>
<span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a>}) <span class="co"># loop to calculate sample accuracy</span></span>
<span id="cb4-4"><a href="#cb4-4" aria-hidden="true" tabindex="-1"></a>accuracyMatrix <span class="ot">&lt;-</span> <span class="fu">sapply</span>(classifyr_result3, <span class="cf">function</span>(result) <span class="fu">performance</span>(result)[[<span class="st">"Sample Accuracy"</span>]])</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<p>The first function uses <code>calcCVperfomance</code> to calculate the classification sample accuracy for both datasets.</p>
<p>The second function uses <code>performance</code> to output a matrix of sample accuracies.</p>
<p><strong>5. Classification Performance Visualisation</strong></p>
<p><span style="color: grey;">Timing ~ 1.7s</span></p>
<div class="cell">
<div class="sourceCode cell-code" id="cb5"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="fu">performancePlot</span>(classifyr_result3)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="cell-output-display">
<div>
<figure class="figure">
<p><img src="Procedure1_files/figure-html/unnamed-chunk-5-1.png" class="img-fluid figure-img" width="672"></p>
</figure>
</div>
</div>
</div>
<p><code>performancePlot</code> outputs a side-by-side boxplot of the balanced accuracies for each dataset.<br>
Both methods perform comparably in terms of median balanced accuracy, but the smaller range and interquartile range in balanced accuracy of the bulked datasets suggests it may be preferable for more consistent results.</p>
<div class="cell">
<div class="sourceCode cell-code" id="cb6"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="fu">samplesMetricMap</span>(classifyr_result3)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="cell-output-display">
<div>
<figure class="figure">
<p><img src="Procedure1_files/figure-html/unnamed-chunk-6-1.png" class="img-fluid figure-img" width="672"></p>
</figure>
</div>
</div>
<div class="cell-output cell-output-stdout">
<pre><code>TableGrob (2 x 1) "arrange": 2 grobs
z cells name grob
1 1 (2-2,1-1) arrange gtable[layout]
2 2 (1-1,1-1) arrange text[GRID.text.276]</code></pre>
</div>
</div>
<p><code>samplesMetricMap</code> outputs a heatmap showing the classification accuracy for each of 100 repeats in each sample. A greater proportion of samples show high sample accuracies (0.8,1] when classified by the bulked data as opposed to the pseudobulked data.</p>
<div class="cell">
<div class="sourceCode cell-code" id="cb8"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plot</span>(accuracyMatrix) <span class="co">#scatterplot of sample accuracies for both datasets</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="cell-output-display">
<div>
<figure class="figure">
<p><img src="Procedure1_files/figure-html/unnamed-chunk-7-1.png" class="img-fluid figure-img" width="672"></p>
</figure>
</div>
</div>
</div>
<p>The final command outputs a scatterplot to show the prediction accuracy of each sample in each dataset.<br>
</p>


</section>
</section>

</main> <!-- /main -->
Expand Down
Binary file added Procedure1_files/figure-html/unnamed-chunk-5-1.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added Procedure1_files/figure-html/unnamed-chunk-6-1.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added Procedure1_files/figure-html/unnamed-chunk-7-1.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
47 changes: 47 additions & 0 deletions Procedure3.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,40 @@
margin: 0 0.8em 0.2em -1em; /* quarto-specific, see https://github.com/quarto-dev/quarto-cli/issues/4556 */
vertical-align: middle;
}
/* CSS for syntax highlighting */
pre > code.sourceCode { white-space: pre; position: relative; }
pre > code.sourceCode > span { line-height: 1.25; }
pre > code.sourceCode > span:empty { height: 1.2em; }
.sourceCode { overflow: visible; }
code.sourceCode > span { color: inherit; text-decoration: inherit; }
div.sourceCode { margin: 1em 0; }
pre.sourceCode { margin: 0; }
@media screen {
div.sourceCode { overflow: auto; }
}
@media print {
pre > code.sourceCode { white-space: pre-wrap; }
pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; }
}
pre.numberSource code
{ counter-reset: source-line 0; }
pre.numberSource code > span
{ position: relative; left: -4em; counter-increment: source-line; }
pre.numberSource code > span > a:first-child::before
{ content: counter(source-line);
position: relative; left: -1em; text-align: right; vertical-align: baseline;
border: none; display: inline-block;
-webkit-touch-callout: none; -webkit-user-select: none;
-khtml-user-select: none; -moz-user-select: none;
-ms-user-select: none; user-select: none;
padding: 0 4px; width: 4em;
}
pre.numberSource { margin-left: 3em; padding-left: 4px; }
div.sourceCode
{ }
@media screen {
pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
}
</style>


Expand Down Expand Up @@ -191,6 +225,19 @@ <h2 data-number="4.1" class="anchored" data-anchor-id="intro"><span class="heade
<section id="next-thing" class="level2" data-number="4.2">
<h2 data-number="4.2" class="anchored" data-anchor-id="next-thing"><span class="header-section-number">4.2</span> Next thing</h2>
<p>more text</p>
<div class="cell">
<div class="sourceCode cell-code" id="cb1"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">set.seed</span>(<span class="dv">1</span>)</span>
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="fu">suppressPackageStartupMessages</span>(<span class="fu">library</span>(ClassifyR))</span>
<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a><span class="co"># mae &lt;- readRDS("data/procedure3/MultiAssayExperiment.rds")</span></span>
<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a><span class="co"># pp &lt;- precisionPathwaysTrain(mae, "Outcome")</span></span>
<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a><span class="co"># pp &lt;- calcCostsAndPerformance(pp, setNames(c(30, 100, 50), c("Clinical", "RNA_pair", "miRNA_pair")))</span></span>
<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a><span class="co"># summary(pp)</span></span>
<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a><span class="co"># bubblePlot(pp)</span></span>
<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a><span class="co"># strataPlot(pp, "clinical-RNA_pair")</span></span>
<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a><span class="co"># flowchart(pp, "clinical-RNA_pair")</span></span>
<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a><span class="co"># predictions &lt;- precisionPathwaysPredict(pp, mae, "Outcome")</span></span>
<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a><span class="co"># predictions$pathways</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>


</section>
Expand Down
Binary file added Procedure3_files/figure-html/unnamed-chunk-1-1.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added Procedure3_files/figure-html/unnamed-chunk-1-2.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading

0 comments on commit e091ceb

Please sign in to comment.