Remove HMM genome annotation pipeline

index.html

@@ -275,7 +275,6 @@
       <button class="tab-button active" data-tab="home">🏠 Home</button>
       <button class="tab-button" data-tab="demo">🚀 Live Demo</button>
       <button class="tab-button" data-tab="functional_tracks">💻 Functional Tracks</button>
-      <button class="tab-button" data-tab="annotation">🧬 Genome Annotation</button>
     </div>
 
     <!-- Home Tab (Content loaded from tabs/home.html) -->

tabs/annotation.html

@@ -1,147 +0,0 @@
-<div class="summary">
-  <h2>🧬 NTv3 Post-Trained Genome Annotation</h2>
-  <p>This notebook demonstrates how to use the NTv3 post-trained model to perform genome annotation directly from a DNA sequence. It relies on a pipeline that applies a Hidden Markov Model (HMM) to the per-base probabilities returned by NTv3, converting them into a coherent gene model that respects biological constraints and valid transitions between genomic elements.</p>
-  <p>The pipeline abstracts away all the underlying steps: running inference with the model, retrieving and processing the predicted probabilities, and applying the HMM to generate a consistent annotation. It returns a ready-to-use GFF file that can be visualized in any genome browser for the sequence of interest.</p>
-  <p>If you're interested in exploring the intermediate probabilities, please refer to the <a href="https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_tutorials/01_tracks_prediction.ipynb" target="_blank" rel="noopener">track-prediction notebook</a>. These probabilities can be useful for assessing model confidence and identifying potentially interesting biological regions. This notebook focuses on the higher-level task of producing gene annotations directly from raw DNA.</p>
-  <p>
-    <strong>🔗 Quick links:</strong><br>
-    • <a href="https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_pipelines/02_genome_annotation.ipynb" target="_blank" rel="noopener">View notebook on Hugging Face</a><br>
-    • <a href="https://colab.research.google.com/github/InstaDeepAI/ntv3/blob/main/notebooks_pipelines/02_genome_annotation.ipynb" target="_blank" rel="noopener">Open directly in Google Colab</a>
-  </p>
-</div>
-
-<div class="grid">
-  <div class="card" style="grid-column: span 12;">
-    <h2>0) 📦 Imports + setup</h2>
-    <p>Install dependencies:</p>
-    <div class="code"><pre><code class="language-bash">pip -q install "transformers>=4.55" "huggingface_hub>=0.23" safetensors torch pyfaidx requests seaborn matplotlib igv_notebook</code></pre></div>
-    
-    <p style="margin-top: 20px;">Import required libraries:</p>
-    <div class="code"><pre><code class="language-python">import re
-import time
-import torch
-import requests
-from transformers import pipeline</code></pre></div>
-  </div>
-
-  <div class="card" style="grid-column: span 12;">
-    <h2>1) 📦 Configuration</h2>
-    <p>Set your NTv3 model and genomic window here:</p>
-    <div class="code"><pre><code class="language-python"># Define the model and genomic window
-model_name = "InstaDeepAI/NTv3_650M_pos"
-assembly = "hg38"
-chrom = "chr19"
-start = 6_700_000
-end = 6_831_072</code></pre></div>
-  </div>
-
-  <div class="card" style="grid-column: span 12;">
-    <h2>2) 📥 Fetch chromosome sequence for the chosen window</h2>
-    <div class="code"><pre><code class="language-python"># Get the sequence from the UCSC API
-url = f"https://api.genome.ucsc.edu/getData/sequence?genome={assembly};chrom={chrom};start={start};end={end}"
-seq = requests.get(url).json()["dna"].upper()
-print(f"Original sequence length: {len(seq)}")
-
-# Crop to multiple of 128 (the pipeline will crop again, but this is a no-op once divisible)
-seq = seq[:int(len(seq) // 128) * 128]
-print(f"Cropped sequence length: {len(seq)}, {len(seq) / 128} transformer tokens")</code></pre></div>
-    <div style="margin-top: 15px; padding: 12px 16px; background: rgba(0, 0, 0, 0.4); border: 1px solid var(--border); border-radius: 8px; font-family: var(--mono); font-size: 12px; color: rgba(255, 255, 255, 0.85); line-height: 1.6;">
-      <strong style="color: var(--muted);">Output:</strong><br>
-      Original sequence length: 131072<br>
-      Cropped sequence length: 131072, 1024.0 transformer tokens
-    </div>
-  </div>
-
-  <div class="card" style="grid-column: span 12;">
-    <h2>3) ⚡ Genome annotation pipeline (pre-processing, inference, post-processing)</h2>
-    <div class="code"><pre><code class="language-python"># Build NTv3 GFF pipeline
-ntv3_gff = pipeline(
-    "ntv3-gff",
-    model=model_name,
-    trust_remote_code=True,
-    device=0 if torch.cuda.is_available() else -1,
-)
-
-# Run pipeline: DNA -> NTv3 -> HMM -> GFF3
-inputs = {
-    "sequence": seq,
-    "chrom": chrom,
-    "start": start,
-    "end": end,
-    "assembly": assembly,
-}
-
-# Run the pipeline
-start_time = time.time()
-gff_text = ntv3_gff(inputs)
-end_time = time.time()
-print(f"Inference + decoding time: {end_time - start_time:.2f} seconds")</code></pre></div>
-    <div style="margin-top: 15px; padding: 12px 16px; background: rgba(0, 0, 0, 0.4); border: 1px solid var(--border); border-radius: 8px; font-family: var(--mono); font-size: 12px; color: rgba(255, 255, 255, 0.85); line-height: 1.6;">
-      <strong style="color: var(--muted);">Output:</strong><br>
-      A new version of the following files was downloaded from https://huggingface.co/InstaDeepAI/NTv3_650M_pos:<br>
-      - ntv3_gff_pipeline.py<br>
-      . Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.<br>
-      Device set to use cpu<br>
-      Inference + decoding time: 53.09 seconds
-    </div>
-    <p style="margin-top: 15px; color: var(--muted); font-size: 13px;">
-      The pipeline performs all the necessary steps: running inference with the model, retrieving and processing the predicted probabilities, and applying the HMM to generate a consistent annotation.
-    </p>
-  </div>
-
-  <div class="card" style="grid-column: span 12;">
-    <h2>4) 📁 Save a GFF file</h2>
-    <div class="code"><pre><code class="language-python"># Save GFF3 file
-short_model_name_match = re.search(r"[^/]+$", model_name)
-short_model_name = short_model_name_match.group() if short_model_name_match else model_name
-
-output_filename = f"{short_model_name}_{assembly}_{chrom}_{start}_{end}.gff3"
-with open(output_filename, "w") as output_file:
-    output_file.write(gff_text)
-
-print(f"Saved GFF file to {output_filename}")</code></pre></div>
-    <div style="margin-top: 15px; padding: 12px 16px; background: rgba(0, 0, 0, 0.4); border: 1px solid var(--border); border-radius: 8px; font-family: var(--mono); font-size: 12px; color: rgba(255, 255, 255, 0.85); line-height: 1.6;">
-      <strong style="color: var(--muted);">Output:</strong><br>
-      Saved GFF file to NTv3_650M_pos_hg38_chr19_6700000_6831072.gff3
-    </div>
-  </div>
-
-  <div class="card" style="grid-column: span 12;">
-    <h2>5) 🌐 Create an IGV Browser</h2>
-    <div class="code"><pre><code class="language-python">import igv_notebook
-
-igv_notebook.init()
-
-config = {
-    "genome": "hg38",  # built-in hg38
-    "locus": f"{chrom}:{start}-{end}",
-}
-
-gff_track = {
-    "name": "NTv3 annotations",
-    "format": "gff3",
-    "type": "annotation",
-    "url": output_filename,  # just the filename
-}
-
-browser = igv_notebook.Browser(config)
-browser.load_track(gff_track)
-
-# Re-center on the region, just to be sure
-browser.search(f"{chrom}:{start}-{end}")
-browser  # <- just return the object, no .show()</code></pre></div>
-    <p style="margin-top: 15px; color: var(--muted); font-size: 13px;">
-      This creates an interactive IGV browser visualization of the annotations. The GFF file can also be visualized in any genome browser.
-    </p>
-  </div>
-
-  <div class="card" style="grid-column: span 12;">
-    <h2>📓 Full Notebook</h2>
-    <p>To view and run the complete notebook interactively:</p>
-    <ul>
-      <li><a href="https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_pipelines/02_genome_annotation.ipynb" target="_blank" rel="noopener">View notebook on Hugging Face</a></li>
-      <li>Download and run in Jupyter, Google Colab, or any notebook environment</li>
-    </ul>
-  </div>
-</div>
-

tabs/home.html

@@ -93,10 +93,9 @@
       <h2>📓 Pipeline notebooks (browse <a href="https://huggingface.co/spaces/InstaDeepAI/ntv3/tree/main/notebooks_pipelines" target="_blank" rel="noopener">folder</a>)</h2>
       <ul>
         <li><a href="https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_pipelines/01_functional_track_prediction.ipynb" target="_blank" rel="noopener">🎯 01 — Generate bigwig predictions for certain tracks</a></li>
-        <li><a href="https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_pipelines/02_genome_annotation.ipynb" target="_blank" rel="noopener">🏷️ 02 — Genome annotation / segmentation</a></li>
-        <li>🎯 03 — Fine-tune on bigwig tracks</li>
-        <li>🔍 04 — Interpret a given genomic region</li>
-        <li>🧪 05 — Sequence generation</li>
+        <li>🎯 02 — Fine-tune on bigwig tracks</li>
+        <li>🔍 03 — Interpret a given genomic region</li>
+        <li>🧪 04 — Sequence generation</li>
       </ul>
     </div>
     <div class="card">