Merge pull request #284 from mims-harvard/amva13-ghpages-patch-1

Update index.html

benchmark/clinical_trial/overview/index.html

@@ -221,7 +221,7 @@ <h2 id="trialoutcome-prediction-benchmark-group">TrialOutcome Prediction Benchma
 
 <p class="is-size-5">Clinical trial outcome prediction is a machine learning task that aims to forecast the outcome of clinical trials, such as the approval rate of a drug or treatment. It utilizes various clinical trial features, including the drug's molecular structure, disease code representing the medical condition, and eligibility criteria that specify participant selection criteria. This task is formulated as a binary classification problem, where the machine learning model predicts whether a clinical trial will have a positive or negative outcome. </p>
 
-<p class="is-size-5">Our benchmark uses the Trial Outcome Prediction (TOP) dataset \cite{Fu2022}. TOP consists of 17,538 clinical trials with 13,880 small-molecule drugs and 5,335 diseases.</p>
+<p class="is-size-5">Our benchmark uses the Trial Outcome Prediction (TOP) dataset. TOP consists of 17,538 clinical trials with 13,880 small-molecule drugs and 5,335 diseases.</p>
 
 <p class="is-size-5">To access a benchmark in the group, use the following code:</p>
 

benchmark/counterfactual_group/overview/index.html

@@ -223,13 +223,15 @@ <h2 id="perturboutcome-prediction-benchmark-group">PerturbOutcome Prediction Ben
 perturbations, aiming to measure model generalization across cell lines and perturbation types. Understanding
  cellular responses to genetic perturbation is central to numerous biomedical applications,
 from identifying genetic interactions involved in cancer to developing methods for regenerative
-medicine. Furthermore, counterfactual prediction of drug-based perturbations at single-cell
-resolution enables cell-type specific drugs and treatments, facilitating precision medicine [ 10]. The230
+medicine. 
+  <br />
+  Furthermore, counterfactual prediction of drug-based perturbations at single-cell
+resolution enables cell-type specific drugs and treatments, facilitating precision medicine. The
 predictive, non-generative task is then formalized as a function of a cell, with corresponding attributes
 such as cell line, disease, and tissue, and a perturbation, such as a drug type or a CRISPR-based
 perturbation, which outputs a count for gene expression of the cell after the input pe </p>
 
-<p class="is-size-5">In TDC-2, we’ve used the scPerturb [ 18 ] datasets for building benchmarks for this task. More details to-be-announced. </p>
+<p class="is-size-5">In TDC-2, we’ve used the scPerturb datasets for building benchmarks for this task. More details to-be-announced. </p>
 
 <p class="is-size-5">To access a benchmark in the group, use the following code:</p>
 

benchmark/proteinpeptide_group/overview/index.html

@@ -232,7 +232,9 @@
 <div class="content">
     <h2 id="protein-peptide-interaction-benchmark-group-tcr-epitope">Protein-Peptide Interaction Benchmark Group (+TCR-Epitope)</h2>
 
-<p class="is-size-5">TDC-2 introduces the Protein-Peptide Binding Affinity prediction task. The predictive, non-generative task is to learn a model estimating a function of a protein, peptide, antigen processing pathway, biological context, and interaction features. It outputs a binding affinity value or binary label indicating strong or weak binding. The binary label can also include additional biomarkers, such as allowing for a positive label if and only if the binding interaction is specific. To account for additional biomarkers beyond binding affinity value, our task is specified with a binary label.
+<p class="is-size-5">TDC-2 introduces the Protein-Peptide Binding Affinity prediction task. The predictive, non-generative task is to learn a model estimating a function of a protein, peptide, antigen processing pathway, biological context, and interaction features. It outputs a binding affinity value or binary label indicating strong or weak binding. The binary label can also include additional biomarkers, such as allowing for a positive label if and only if the binding interaction is specific. 
+  <br />
+  To account for additional biomarkers beyond binding affinity value, our task is specified with a binary label.
 <br />
 TDC-2 provides datasets and benchmarks for a generalized protein-peptide binding interaction prediction task and a TCR-Epitope binding interaction prediction task.</p>
 
@@ -266,8 +268,6 @@ <h2 id="protein-peptide-interaction-benchmark-group-tcr-epitope">Protein-Peptide
 
 <p class="is-size-5"> Follow the <b><a href="/benchmark/overview/">instructions</a></b> on how to use the <code>BenchmarkGroup</code> class and obtain training, validation, and test sets, and how to submit your model to the leaderboard. </p>
 
-<p class="is-size-5"> The evaluation metric is AUC. For TCR-Epitope, we provide other metrics as well. See corresponding leaderboards.</p>
-
 <div class="column is-12">
     <hr />
 </div>

benchmark/scdti_group/overview/index.html

@@ -222,7 +222,7 @@ <h2 id="single-cell-drug-target-interaction-benchmark-group">Single-cell Drug-Ta
 <p class="is-size-5">We formalize the predictive, non-generative, task definition as a function taking a given protein, cell,
 and drug as input to output a score representing a probability of drug-target binding. More details to-be-announced. </p>
 
-<p class="is-size-5">A dataset containing drug-target interactions at single-cell resolution for various contextualized215
+<p class="is-size-5">A dataset containing drug-target interactions at single-cell resolution for various contextualized
 proteins and diseases must be constructed to train a model for this task. In TDC-2, we assembeled a dataset containing data points for Rheumatoid Arthritis and Inflammatory Bowel Disease. More details to-be-announced. </p>
 
 <p class="is-size-5">To access a benchmark in the group, use the following code:</p>

multi_pred_tasks/counterfactual/index.html

@@ -296,10 +296,8 @@ <h1 id="counterfactual-prediction-task-overview">Counterfactual Prediction Task
 <p class="is-size-6"> <strong> Product: </strong>  Drug Repurposing, Predicting Adverse Drug Reactions, Biopharmaceuticals</p>
 
 <p class="is-size-6"> <strong> Pipeline: </strong>  Target discovery, Phenotypic Screening. </p>
-
-&lt;/div&gt;
-
-### scPerturb 
+
+<h3 id="scperturb">scPerturb</h3>
 
 <p class="is-size-6">  <strong> Dataset Description: </strong> The scPerturb dataset is a comprehensive collection of single-cell perturbation data, harmonized to facilitate the development and benchmarking of computational methods in systems biology. It includes various types of molecular readouts, such as transcriptomics, proteomics, and epigenomics. scPerturb is a harmonized dataset that compiles single-cell perturbation-response data. This dataset is designed to support the development and validation of computational tools by providing a consistent and comprehensive resource. The data includes responses to various genetic and chemical perturbations, which are crucial for understanding cellular mechanisms and developing therapeutic strategies. Data from different sources are uniformly pre-processed to ensure consistency. Rigorous quality control measures are applied to maintain high data quality. Features across different datasets are standardized for easy comparison and integration. 
 
@@ -309,12 +307,10 @@ <h1 id="counterfactual-prediction-task-overview">Counterfactual Prediction Task
 
 <p class="is-size-6">  <strong> Dataset Split: </strong> <span class="tag is-info is-light">Random Split, Seen-unseen splits across cell line and perturbation</span> </p>
 
-``` python
-from tdc.multi_pred.perturboutcome import PerturbOutcome
-test_loader = PerturbOutcome(
-    name="scperturb_drug_SrivatsanTrapnell2020_sciplex2")
-testdf = test_loader.get_data()
-```
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="kn">from</span> <span class="nn">tdc.multi_pred.perturboutcome</span> <span class="kn">import</span> <span class="n">PerturbOutcome</span>
+<span class="n">data</span> <span class="o">=</span> <span class="n">PerturbOutcome</span><span class="p">(</span><span class="n">name</span> <span class="o">=</span> <span class="s">'scperturb_drug_SrivatsanTrapnell2020_sciplex2'</span><span class="p">)</span>
+<span class="n">split</span> <span class="o">=</span> <span class="n">data</span><span class="p">.</span><span class="n">get_split</span><span class="p">()</span>
+</code></pre></div></div>
 
 <p class="is-size-6">  <strong> References: </strong>  </p>
 

multi_pred_tasks/proteinpeptide/index.html

@@ -315,11 +315,10 @@ <h3 id="ye-x-et-al">Ye X et al</h3>
 
 <p class="is-size-6">  <strong> Dataset Split: </strong> <span class="tag is-info is-light">Random Split (stratified)</span> </p>
 
-``` python
-from tdc.multi_pred import ProteinPeptide
-data = ProteinPeptide(name="brown_mdm2_ace2_12ca5")
-data.get_split()
-```
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="kn">from</span> <span class="nn">tdc.multi_pred</span> <span class="kn">import</span> <span class="n">ProteinPeptide</span> 
+<span class="n">data</span> <span class="o">=</span> <span class="n">ProteinPeptide</span><span class="p">(</span><span class="n">name</span> <span class="o">=</span> <span class="s">'brown_mdm2_ace2_12ca5'</span><span class="p">,</span> <span class="n">path</span> <span class="o">=</span> <span class="s">'./data'</span><span class="p">)</span>
+<span class="n">split</span> <span class="o">=</span> <span class="n">data</span><span class="p">.</span><span class="n">get_split</span><span class="p">()</span>
+</code></pre></div></div>
 
 <p class="is-size-6"> <strong>Note:</strong> If listed as a "putative binder," AS-MS alone was used to isolate the ligands to the target, with KD &lt; 1 uM required and often observed in orthogonal assays, though there is some (&lt; 50%) chance that the ligand is nonspecific. </p>