remove ref

docs/build/html/_sources/index/usage_principles/aaontology.rst.txt

@@ -1,5 +1,5 @@
 AAontology: Classification of amino acid scales
 ===============================================
 
-AAontology is a two-level classification of amino acid scale, introduced in [Breimann23b]_.
+AAontology is a two-level classification of amino acid scale, introduced in.
 

docs/build/html/_sources/index/usage_principles/pu_learning.rst.txt

@@ -1,7 +1,7 @@
 Learning from unbalanced and small data
 =======================================
 
-Unbalanced and small datasets are everywhere in life science ... [Breimann23c]_.
+Unbalanced and small datasets are everywhere in life science ....
 
 In a standard binary classification setup, data with positive (1) and negative (0) labels are provided, which can be
 used for training by machine learning models. If only a view samples of the negative class exist, data augmentation
@@ -10,7 +10,7 @@ are very popular for deep learning-based image recognition, but not feasible for
 because slight amino acid mutations (sequence alterations or perturbations) can already have dramatic biological effects.
 Alternatively, negatives samples can be identified from unlabeled samples (2), which often exist in great quantities.
 These unlabeled samples should be biologically as similar as possible to the positive class, beside not containing
-the features distinguishing the positive from the negative class. For example, [Breimann23c]_.
+the features distinguishing the positive from the negative class. For example, .
 
 What is PU learning?
 --------------------

docs/build/html/_sources/index/usage_principles/xai.rst.txt

@@ -1,7 +1,7 @@
 Explainable AI at Sequence Level
 ================================
 
-Unbalanced and small datasets are everywhere in life science ... [Breimann23c]_.
+Unbalanced and small datasets are everywhere in life science ....
 
 What is explainable AI?
 -----------------------

docs/build/html/index/usage_principles/aaontology.html

@@ -6,12 +6,12 @@
 <meta property="og:type" content="website" />
 <meta property="og:url" content="index/usage_principles/aaontology.html" />
 <meta property="og:site_name" content="AAanalysis" />
-<meta property="og:description" content="AAontology is a two-level classification of amino acid scale, introduced in[Breimann23b]." />
+<meta property="og:description" content="AAontology is a two-level classification of amino acid scale, introduced in." />
 <meta property="og:image:width" content="1146" />
 <meta property="og:image:height" content="600" />
-<meta property="og:image" content="/_images/social_previews/summary_index_usage_principles_aaontology_dce8add5.png" />
-<meta property="og:image:alt" content="AAontology is a two-level classification of amino acid scale, introduced in[Breimann23b]." />
-<meta name="description" content="AAontology is a two-level classification of amino acid scale, introduced in[Breimann23b]." />
+<meta property="og:image" content="/_images/social_previews/summary_index_usage_principles_aaontology_434210d3.png" />
+<meta property="og:image:alt" content="AAontology is a two-level classification of amino acid scale, introduced in." />
+<meta name="description" content="AAontology is a two-level classification of amino acid scale, introduced in." />
 <meta name="twitter:card" content="summary_large_image" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
@@ -120,7 +120,7 @@
 
   <section id="aaontology-classification-of-amino-acid-scales">
 <h1>AAontology: Classification of amino acid scales<a class="headerlink" href="#aaontology-classification-of-amino-acid-scales" title="Permalink to this heading"></a></h1>
-<p>AAontology is a two-level classification of amino acid scale, introduced in <a class="reference internal" href="../references.html#breimann23b" id="id1"><span>[Breimann23b]</span></a>.</p>
+<p>AAontology is a two-level classification of amino acid scale, introduced in.</p>
 </section>
 
 

docs/build/html/index/usage_principles/pu_learning.html

@@ -6,12 +6,12 @@
 <meta property="og:type" content="website" />
 <meta property="og:url" content="index/usage_principles/pu_learning.html" />
 <meta property="og:site_name" content="AAanalysis" />
-<meta property="og:description" content="Unbalanced and small datasets are everywhere in life science …[Breimann23c]. In a standard binary classification setup, data with positive (1) and negative (0) labels are provided, which can be use..." />
+<meta property="og:description" content="Unbalanced and small datasets are everywhere in life science …. In a standard binary classification setup, data with positive (1) and negative (0) labels are provided, which can be used for trainin..." />
 <meta property="og:image:width" content="1146" />
 <meta property="og:image:height" content="600" />
-<meta property="og:image" content="/_images/social_previews/summary_index_usage_principles_pu_learning_fd17141c.png" />
-<meta property="og:image:alt" content="Unbalanced and small datasets are everywhere in life science …[Breimann23c]. In a standard binary classification setup, data with positive (1) and negative (..." />
-<meta name="description" content="Unbalanced and small datasets are everywhere in life science …[Breimann23c]. In a standard binary classification setup, data with positive (1) and negative (0) labels are provided, which can be use..." />
+<meta property="og:image" content="/_images/social_previews/summary_index_usage_principles_pu_learning_9a1def62.png" />
+<meta property="og:image:alt" content="Unbalanced and small datasets are everywhere in life science …. In a standard binary classification setup, data with positive (1) and negative (0) labels are..." />
+<meta name="description" content="Unbalanced and small datasets are everywhere in life science …. In a standard binary classification setup, data with positive (1) and negative (0) labels are provided, which can be used for trainin..." />
 <meta name="twitter:card" content="summary_large_image" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
@@ -123,15 +123,15 @@
 
   <section id="learning-from-unbalanced-and-small-data">
 <h1>Learning from unbalanced and small data<a class="headerlink" href="#learning-from-unbalanced-and-small-data" title="Permalink to this heading"></a></h1>
-<p>Unbalanced and small datasets are everywhere in life science … <a class="reference internal" href="../references.html#breimann23c" id="id1"><span>[Breimann23c]</span></a>.</p>
+<p>Unbalanced and small datasets are everywhere in life science ….</p>
 <p>In a standard binary classification setup, data with positive (1) and negative (0) labels are provided, which can be
 used for training by machine learning models. If only a view samples of the negative class exist, data augmentation
 techniques (e.g., SMOTE) can be used to extend the negative dataset by artificially generated sequences. Such approaches
 are very popular for deep learning-based image recognition, but not feasible for protein sequence prediction tasks
 because slight amino acid mutations (sequence alterations or perturbations) can already have dramatic biological effects.
 Alternatively, negatives samples can be identified from unlabeled samples (2), which often exist in great quantities.
 These unlabeled samples should be biologically as similar as possible to the positive class, beside not containing
-the features distinguishing the positive from the negative class. For example, <a class="reference internal" href="../references.html#breimann23c" id="id2"><span>[Breimann23c]</span></a>.</p>
+the features distinguishing the positive from the negative class. For example, .</p>
 <section id="what-is-pu-learning">
 <h2>What is PU learning?<a class="headerlink" href="#what-is-pu-learning" title="Permalink to this heading"></a></h2>
 <p>Positive Unlabeled (PU) learning is a subfield of machine learning …</p>

docs/build/html/index/usage_principles/xai.html

@@ -6,12 +6,12 @@
 <meta property="og:type" content="website" />
 <meta property="og:url" content="index/usage_principles/xai.html" />
 <meta property="og:site_name" content="AAanalysis" />
-<meta property="og:description" content="Unbalanced and small datasets are everywhere in life science …[Breimann23c]. What is explainable AI?:" />
+<meta property="og:description" content="Unbalanced and small datasets are everywhere in life science …. What is explainable AI?:" />
 <meta property="og:image:width" content="1146" />
 <meta property="og:image:height" content="600" />
-<meta property="og:image" content="/_images/social_previews/summary_index_usage_principles_xai_f2e07f59.png" />
-<meta property="og:image:alt" content="Unbalanced and small datasets are everywhere in life science …[Breimann23c]. What is explainable AI?:" />
-<meta name="description" content="Unbalanced and small datasets are everywhere in life science …[Breimann23c]. What is explainable AI?:" />
+<meta property="og:image" content="/_images/social_previews/summary_index_usage_principles_xai_c56d9fa3.png" />
+<meta property="og:image:alt" content="Unbalanced and small datasets are everywhere in life science …. What is explainable AI?:" />
+<meta name="description" content="Unbalanced and small datasets are everywhere in life science …. What is explainable AI?:" />
 <meta name="twitter:card" content="summary_large_image" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
@@ -123,7 +123,7 @@
 
   <section id="explainable-ai-at-sequence-level">
 <h1>Explainable AI at Sequence Level<a class="headerlink" href="#explainable-ai-at-sequence-level" title="Permalink to this heading"></a></h1>
-<p>Unbalanced and small datasets are everywhere in life science … <a class="reference internal" href="../references.html#breimann23c" id="id1"><span>[Breimann23c]</span></a>.</p>
+<p>Unbalanced and small datasets are everywhere in life science ….</p>
 <section id="what-is-explainable-ai">
 <h2>What is explainable AI?<a class="headerlink" href="#what-is-explainable-ai" title="Permalink to this heading"></a></h2>
 </section>

docs/source/index/usage_principles/aaontology.rst

@@ -1,5 +1,5 @@
 AAontology: Classification of amino acid scales
 ===============================================
 
-AAontology is a two-level classification of amino acid scale, introduced in [Breimann23b]_.
+AAontology is a two-level classification of amino acid scale, introduced in.
 

docs/source/index/usage_principles/pu_learning.rst

@@ -1,7 +1,7 @@
 Learning from unbalanced and small data
 =======================================
 
-Unbalanced and small datasets are everywhere in life science ... [Breimann23c]_.
+Unbalanced and small datasets are everywhere in life science ....
 
 In a standard binary classification setup, data with positive (1) and negative (0) labels are provided, which can be
 used for training by machine learning models. If only a view samples of the negative class exist, data augmentation
@@ -10,7 +10,7 @@ are very popular for deep learning-based image recognition, but not feasible for
 because slight amino acid mutations (sequence alterations or perturbations) can already have dramatic biological effects.
 Alternatively, negatives samples can be identified from unlabeled samples (2), which often exist in great quantities.
 These unlabeled samples should be biologically as similar as possible to the positive class, beside not containing
-the features distinguishing the positive from the negative class. For example, [Breimann23c]_.
+the features distinguishing the positive from the negative class. For example, .
 
 What is PU learning?
 --------------------

docs/source/index/usage_principles/xai.rst

@@ -1,7 +1,7 @@
 Explainable AI at Sequence Level
 ================================
 
-Unbalanced and small datasets are everywhere in life science ... [Breimann23c]_.
+Unbalanced and small datasets are everywhere in life science ....
 
 What is explainable AI?
 -----------------------