deploy: 6c79c67

DLS5-Omics · Oct 9, 2024 · d91a5bf · d91a5bf
1 parent 48e10f1
commit d91a5bf
Show file tree

Hide file tree

Showing 29 changed files with 4,319 additions and 249 deletions.
diff --git a/datasets/bprna-new/index.html b/datasets/bprna-new/index.html
@@ -672,6 +672,8 @@
 
 
 
+
+
 
 
 
@@ -931,11 +933,32 @@
 
 
     <li class="md-nav__item">
-      <a href="../eternabench/" class="md-nav__link">
+      <a href="../eternabench-cm/" class="md-nav__link">
+
+
+  <span class="md-ellipsis">
+    EternaBench-ChemMapping
+  </span>
+
+
+      </a>
+    </li>
+
+
+
+
+
+
+
+
+
+
+    <li class="md-nav__item">
+      <a href="../eternabench-switch/" class="md-nav__link">
 
 
   <span class="md-ellipsis">
-    EternaBench
+    EternaBench-RiboSwitch
   </span>
 
 

diff --git a/datasets/bprna-spot/index.html b/datasets/bprna-spot/index.html
@@ -672,6 +672,8 @@
 
 
 
+
+
 
 
 
@@ -931,11 +933,32 @@
 
 
     <li class="md-nav__item">
-      <a href="../eternabench/" class="md-nav__link">
+      <a href="../eternabench-cm/" class="md-nav__link">
+
+
+  <span class="md-ellipsis">
+    EternaBench-ChemMapping
+  </span>
+
+
+      </a>
+    </li>
+
+
+
+
+
+
+
+
+
+
+    <li class="md-nav__item">
+      <a href="../eternabench-switch/" class="md-nav__link">
 
 
   <span class="md-ellipsis">
-    EternaBench
+    EternaBench-RiboSwitch
   </span>
 
 

diff --git a/datasets/bprna/index.html b/datasets/bprna/index.html
@@ -672,6 +672,8 @@
 
 
 
+
+
 
 
 
@@ -958,11 +960,32 @@
 
 
     <li class="md-nav__item">
-      <a href="../eternabench/" class="md-nav__link">
+      <a href="../eternabench-cm/" class="md-nav__link">
+
+
+  <span class="md-ellipsis">
+    EternaBench-ChemMapping
+  </span>
+
+
+      </a>
+    </li>
+
+
+
+
+
+
+
+
+
+
+    <li class="md-nav__item">
+      <a href="../eternabench-switch/" class="md-nav__link">
 
 
   <span class="md-ellipsis">
-    EternaBench
+    EternaBench-RiboSwitch
   </span>
 
 

diff --git a/datasets/eternabench/index.html → datasets/eternabench-cm/index.html b/datasets/eternabench/index.html → datasets/eternabench-cm/index.html
@@ -27,13 +27,13 @@
         <meta name="author" content="MultiMolecule">
 
 
-        <link rel="canonical" href="https://multimolecule.danling.org/datasets/eternabench/">
+        <link rel="canonical" href="https://multimolecule.danling.org/datasets/eternabench-cm/">
 
 
         <link rel="prev" href="../ryos/">
 
 
-        <link rel="next" href="../../module/">
+        <link rel="next" href="../eternabench-switch/">
 
 
         <link rel="alternate" type="application/rss+xml" title="RSS feed" href="../../feed_rss_created.xml">
@@ -44,7 +44,7 @@
 
 
 
-        <title>EternaBench - MultiMolecule</title>
+        <title>EternaBench-ChemMapping - MultiMolecule</title>
 
 
 
@@ -106,7 +106,7 @@
     <div data-md-component="skip">
 
 
-        <a href="#eternabench" class="md-skip">
+        <a href="#eternabench-chemmapping" class="md-skip">
           Skip to content
         </a>
 
@@ -141,7 +141,7 @@
         <div class="md-header__topic" data-md-component="header-topic">
           <span class="md-ellipsis">
 
-              EternaBench
+              EternaBench-ChemMapping
 
           </span>
         </div>
@@ -194,7 +194,7 @@
           </li>
 
           <li class="md-select__item">
-            <a href="../../zh/datasets/eternabench/" hreflang="zh" class="md-select__link">
+            <a href="../../zh/datasets/eternabench-cm/" hreflang="zh" class="md-select__link">
               汉语
             </a>
           </li>
@@ -672,6 +672,8 @@
 
 
 
+
+
 
 
 
@@ -859,7 +861,7 @@
 
 
   <span class="md-ellipsis">
-    EternaBench
+    EternaBench-ChemMapping
   </span>
 
 
@@ -870,7 +872,7 @@
 
 
   <span class="md-ellipsis">
-    EternaBench
+    EternaBench-ChemMapping
   </span>
 
 
@@ -928,9 +930,9 @@
 </li>
 
         <li class="md-nav__item">
-  <a href="#variations" class="md-nav__link">
+  <a href="#related-datasets" class="md-nav__link">
     <span class="md-ellipsis">
-      Variations
+      Related Datasets
     </span>
   </a>
 
@@ -963,6 +965,27 @@
 
 
 
+
+
+
+
+
+
+    <li class="md-nav__item">
+      <a href="../eternabench-switch/" class="md-nav__link">
+
+
+  <span class="md-ellipsis">
+    EternaBench-RiboSwitch
+  </span>
+
+
+      </a>
+    </li>
+
+
+
+
           </ul>
         </nav>
 
@@ -1254,9 +1277,9 @@
 </li>
 
         <li class="md-nav__item">
-  <a href="#variations" class="md-nav__link">
+  <a href="#related-datasets" class="md-nav__link">
     <span class="md-ellipsis">
-      Variations
+      Related Datasets
     </span>
   </a>
 
@@ -1298,55 +1321,94 @@
 
 
 
-<h1 id="eternabench">EternaBench<a class="headerlink" href="#eternabench" title="Permanent link">&para;</a></h1>
-<p><img alt="EternaBench" src="https://eternagame.org/sites/default/files/thumb_eternabench_paper.png" /></p>
-<p>EternaBench is a database comprising the diverse high-throughput structural data gathered through the crowdsourced RNA design project Eterna, to evaluate the performance of a wide set of structure algorithms.</p>
+<h1 id="eternabench-chemmapping">EternaBench-ChemMapping<a class="headerlink" href="#eternabench-chemmapping" title="Permanent link">&para;</a></h1>
+<p><img alt="EternaBench-ChemMapping" src="https://eternagame.org/sites/default/files/thumb_eternabench_paper.png" /></p>
+<p>EternaBench-ChemMapping is a synthetic RNA dataset comprising 12,711 RNA constructs that have been chemically mapped using SHAPE and MAP-seq methods.
+These RNA sequences are probed to obtain experimental data on their nucleotide reactivity, which indicates whether specific regions of the RNA are flexible or structured.
+The dataset provides high-resolution, large-scale data that can be used for studying RNA folding and stability.</p>
 <h2 id="disclaimer">Disclaimer<a class="headerlink" href="#disclaimer" title="Permanent link">&para;</a></h2>
-<p>This is an UNOFFICIAL release of the <a href="https://github.com/eternagame/EternaBench">EternaBench</a> by Hannah K. Wayment-Steele, et al.</p>
-<p><strong>The team releasing EternaBench did not write this dataset card for this dataset so this dataset card has been written by the MultiMolecule team.</strong></p>
+<p>This is an UNOFFICIAL release of the <a href="https://github.com/eternagame/EternaBench">EternaBench-ChemMapping</a> by Hannah K. Wayment-Steele, et al.</p>
+<p><strong>The team releasing EternaBench-ChemMapping did not write this dataset card for this dataset so this dataset card has been written by the MultiMolecule team.</strong></p>
 <h2 id="dataset-description">Dataset Description<a class="headerlink" href="#dataset-description" title="Permanent link">&para;</a></h2>
 <ul>
-<li><strong>Homepage</strong>: <a href="https://multimolecule.danling.org/datasets/eternabench">https://multimolecule.danling.org/datasets/eternabench</a></li>
+<li><strong>Homepage</strong>: <a href="https://multimolecule.danling.org/datasets/eternabench_cm">https://multimolecule.danling.org/datasets/eternabench_cm</a></li>
+<li><strong>datasets</strong>: <a href="https://huggingface.co/datasets/multimolecule/eternabench-cm">https://huggingface.co/datasets/multimolecule/eternabench-cm</a></li>
 <li><strong>Point of Contact</strong>: <a href="https://biochemistry.stanford.edu/people/rhiju-das/">Rhiju Das</a></li>
 </ul>
+<p>The dataset includes a large set of synthetic RNA sequences with experimental chemical mapping data, which provides a quantitative readout of RNA nucleotide reactivity. These data are ensemble-averaged and serve as a critical benchmark for evaluating secondary structure prediction algorithms in their ability to model RNA folding dynamics.</p>
 <h2 id="example-entry">Example Entry<a class="headerlink" href="#example-entry" title="Permanent link">&para;</a></h2>
-<p>| ID | design_name | sequence | structure | reactivity | errors | signal_to_noise |
-| 769337-1 | d+m plots weaker again | GGAAAAAAAAAAA&hellip; | ................ | [0.642,1.4853,0.1629, &hellip;] | [0.3181,0.4221,0.1823, &hellip;] | 3.227 |</p>
+<table>
+<thead>
+<tr>
+<th>index</th>
+<th>design</th>
+<th>sequence</th>
+<th>secondary_structure</th>
+<th>reactivity</th>
+<th>errors</th>
+<th>signal_to_noise</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>769337-1</td>
+<td>d+m plots weaker again</td>
+<td>GGAAAAAAAAAAA&hellip;</td>
+<td>................</td>
+<td>[0.642,1.4853,0.1629, &hellip;]</td>
+<td>[0.3181,0.4221,0.1823, &hellip;]</td>
+<td>3.227</td>
+</tr>
+</tbody>
+</table>
 <h2 id="column-description">Column Description<a class="headerlink" href="#column-description" title="Permanent link">&para;</a></h2>
-<p>The EternaBench dataset consists of the following columns, providing crucial insights for understanding RNA stability for vaccine design:</p>
 <ul>
 <li>
-<p><strong>ID</strong>:
-  A unique identifier for each RNA sequence entry.</p>
+<p><strong>id</strong>:
+    A unique identifier for each RNA sequence entry.</p>
 </li>
 <li>
-<p><strong>design_name</strong>:
-  The name given to each RNA design by contributors, used for easy reference.</p>
+<p><strong>design</strong>:
+    The name given to each RNA design by contributors, used for easy reference.</p>
 </li>
 <li>
 <p><strong>sequence</strong>:
-  The nucleotide sequence of the RNA, using standard bases.</p>
+    The nucleotide sequence of the RNA molecule, represented using the standard RNA bases:</p>
+<ul>
+<li><strong>A</strong>: Adenine</li>
+<li><strong>C</strong>: Cytosine</li>
+<li><strong>G</strong>: Guanine</li>
+<li><strong>U</strong>: Uracil</li>
+</ul>
 </li>
 <li>
-<p><strong>structure</strong>:
-  The predicted secondary structure of the RNA, represented using dot-bracket notation.
-  The structure helps determine the likely secondary interactions within each RNA molecule.</p>
+<p><strong>secondary_structure</strong>:
+    The secondary structure of the RNA represented in dot-bracket notation, using up to three types of symbols to indicate base pairing and unpaired regions, as per bpRNA&rsquo;s standard:</p>
+<ul>
+<li><strong>Dots (<code>.</code>)</strong>: Represent unpaired nucleotides.</li>
+<li><strong>Parentheses (<code>(</code> and <code>)</code>)</strong>: Represent base pairs in standard stems (page 1).</li>
+<li><strong>Square Brackets (<code>[</code> and <code>]</code>)</strong>: Represent base pairs in pseudoknots (page 2).</li>
+<li><strong>Curly Braces (<code>{</code> and <code>}</code>)</strong>: Represent base pairs in additional pseudoknots (page 3).</li>
+</ul>
 </li>
 <li>
 <p><strong>reactivity</strong>:
-  A list of floating-point values that provide an estimate of the likelihood of the RNA backbone being cut at each nucleotide position.
-  These values help determine the stability of the RNA structure under various experimental conditions.</p>
+    A list of normalized reactivity values for each nucleotide, representing the likelihood that a nucleotide is unpaired.
+    High reactivity indicates high flexibility (unpaired regions), and low reactivity corresponds to paired or structured regions.</p>
 </li>
 <li>
 <p><strong>errors</strong>:
-  Arrays of floating-point numbers indicating the experimental errors corresponding to the measurements in the <strong>reactivity</strong>.
-  These values help quantify the uncertainty in the degradation rates and reactivity measurements.</p>
+    Arrays of floating-point numbers indicating the experimental errors corresponding to the measurements in the <strong>reactivity</strong>.
+    These values help quantify the uncertainty in the degradation rates and reactivity measurements.</p>
+</li>
+<li>
+<p><strong>signal_to_noise</strong>:
+    The signal-to-noise ratio calculated from the reactivity and error values, providing a measure of data quality.</p>
 </li>
 </ul>
-<h2 id="variations">Variations<a class="headerlink" href="#variations" title="Permanent link">&para;</a></h2>
-<p>This dataset is available in two subsets:</p>
+<h2 id="related-datasets">Related Datasets<a class="headerlink" href="#related-datasets" title="Permanent link">&para;</a></h2>
 <ul>
-<li><a href="https://huggingface.co/datasets/multimolecule/eternabench-cm">EternaBench-CM</a></li>
+<li><a href="https://huggingface.co/datasets/multimolecule/eternabench-cm">EternaBench-ChemMapping</a></li>
 <li><a href="https://huggingface.co/datasets/multimolecule/eternabench-switch">EternaBench-Switch</a></li>
 </ul>
 <h2 id="license">License<a class="headerlink" href="#license" title="Permanent link">&para;</a></h2>
@@ -1501,13 +1563,13 @@ <h2 id="citation">Citation<a class="headerlink" href="#citation" title="Permanen
 
 
 
-          <a href="../../module/" class="md-footer__link md-footer__link--next" aria-label="Next: module">
+          <a href="../eternabench-switch/" class="md-footer__link md-footer__link--next" aria-label="Next: EternaBench-RiboSwitch">
             <div class="md-footer__title">
               <span class="md-footer__direction">
                 Next
               </span>
               <div class="md-ellipsis">
-                module
+                EternaBench-RiboSwitch
               </div>
             </div>
             <div class="md-footer__button md-icon">