fix: remove functional_tracks

tabs/functional_tracks.html

@@ -1,253 +0,0 @@
-<div class="summary">
-  <h2>🧬 NTv3 Post-Trained Functional Track Prediction</h2>
-  <p>This notebook demonstrates how to use the NTv3 post-trained model to predict functional tracks and genome annotation directly from a DNA sequence.</p>
-  <p>The pipeline abstracts away all the underlying steps: running inference with the model and plotting the predictions per tracks.</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 noreferrer">track-prediction notebook</a>.</p>
-  <p>
-    <strong>🔗 Quick links:</strong><br>
-    • <a href="https://huggingface.co/spaces/InstaDeepAI/ntv3/blob/main/notebooks_pipelines/01_functional_track_prediction.ipynb" target="_blank" rel="noopener noreferrer">View notebook on Hugging Face</a><br>
-    • <a href="https://colab.research.google.com/github/InstaDeepAI/ntv3/blob/main/notebooks_pipelines/01_functional_track_prediction.ipynb" target="_blank" rel="noopener noreferrer">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 pyBigWig</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 os
-import torch
-import requests
-import numpy as np
-import pyBigWig
-from transformers import pipeline, AutoConfig</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"
-
-species = "human"  # will use for condition the model on species
-assembly = "hg38"  # will use for fetching the chromosome sequence
-
-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) ⚡ Functional track prediction pipeline (pre-processing, inference, plotting)</h2>
-    <div class="code"><pre><code class="language-python"># Build NTv3 tracks pipeline
-ntv3_tracks = pipeline(
-    "ntv3-tracks",
-    model=model_name,
-    trust_remote_code=True,
-    device=0 if torch.cuda.is_available() else -1,
-)
-
-# Select tracks to plot
-tracks_to_plot = {
-    "K562 RNA-seq": "ENCSR056HPM",
-    "K562 DNAse": "ENCSR921NMD",
-    "K562 H3k4me3": "ENCSR000DWD",
-    "K562 CTCF": "ENCSR000AKO",
-    "HepG2 RNA-seq": "ENCSR561FEE_P",
-    "HepG2 DNAse": "ENCSR000EJV",
-    "HepG2 H3k4me3": "ENCSR000AMP",
-    "HepG2 CTCF": "ENCSR000BIE",
-}
-elements_to_plot = ["protein_coding_gene", "exon", "intron", "splice_donor", "splice_acceptor"]
-
-# Run pipeline: DNA -> NTv3 -> Tracks -> plot
-start_time = time.time()
-
-ntv3_predictions = ntv3_tracks(
-    {"chrom": "chr19", "start": 6_700_000, "end": 6_831_072, "species": species},
-    plot=True,
-    tracks_to_plot=tracks_to_plot,
-    elements_to_plot=elements_to_plot,
-)
-
-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>
-      Device set to use cpu<br>
-      Running on device: cpu<br>
-      Inference + decoding time: 38.32 seconds
-    </div>
-    <div style="margin-top: 20px;">
-      <img src="assets/output_tracks.png" alt="Output tracks plot" style="width: 100%; height: auto; border-radius: 12px; border: 1px solid var(--border);" />
-    </div>
-    <p style="margin-top: 15px; color: var(--muted); font-size: 13px;">
-      The pipeline performs all the necessary steps: running inference with the model and plotting the predictions for the specified tracks and genomic elements.
-    </p>
-  </div>
-
-  <div class="card" style="grid-column: span 12;">
-    <h2>4) 📁 Save as BigWig file</h2>
-    <div class="code"><pre><code class="language-python"># Load config to get track names and find indices for tracks_to_plot
-cfg = AutoConfig.from_pretrained(model_name, trust_remote_code=True)
-all_bigwig_names = cfg.bigwigs_per_file_assembly[assembly]
-
-# Find indices of tracks we want to save
-# Use display names (keys) for filenames, but track IDs (values) to find indices
-track_data_list = []  # List of (display_name, track_id, index) tuples
-for display_name, track_id in tracks_to_plot.items():
-    try:
-        idx = all_bigwig_names.index(track_id)
-        track_data_list.append((display_name, track_id, idx))
-    except ValueError:
-        print(f"Warning: Track '{track_id}' ({display_name}) not found in config. Skipping...")
-
-print(f"Found {len(track_data_list)} tracks to save from tracks_to_plot")
-
-# Get predictions (shape: (49152, 7362))
-bigwig_logits = ntv3_predictions.bigwig_tracks_logits
-if isinstance(bigwig_logits, torch.Tensor):
-    bigwig_logits = bigwig_logits.detach().cpu().numpy()
-
-# Calculate genomic coordinates for the center 37.5% region
-# The predictions cover the center 37.5% of the input sequence
-input_length = end - start
-center_start_offset = int(input_length * 0.3125)  # (1 - 0.375) / 2 = 0.3125
-center_length = int(input_length * 0.375)
-center_start = start + center_start_offset
-center_end = center_start + center_length
-
-print(f"Input region: {chrom}:{start}-{end} (length: {input_length:,} bp)")
-print(f"Prediction region: {chrom}:{center_start}-{center_end} (length: {center_length:,} bp)")
-print(f"Number of positions: {bigwig_logits.shape[0]}")
-
-# Create output directory
-output_dir = "bigwig_outputs"
-os.makedirs(output_dir, exist_ok=True)
-
-# Save each track as a separate BigWig file
-print(f"\nSaving BigWig files to '{output_dir}/' directory...")
-for i, (display_name, track_id, track_idx) in enumerate(track_data_list):
-    # Get track data (logits for this track)
-    track_data = bigwig_logits[:, track_idx].astype(np.float32)
-    
-    # Create BigWig file using display name (key) for filename
-    # Clean the display name for use as filename (replace spaces, special chars)
-    track_clean_name = display_name.replace(" ", "_").replace("/", "_").replace("-", "_")
-    bw_filename = os.path.join(output_dir, f"{track_clean_name}.bw")
-    bw = pyBigWig.open(bw_filename, "w")
-    
-    # Add header (chromosome and size)
-    bw.addHeader([(chrom, end)])
-    
-    # Add entries (intervals with values)
-    # Each position in track_data corresponds to one base pair
-    starts = np.arange(center_start, center_start + len(track_data), dtype=np.int64)
-    ends = starts + 1
-    values = track_data.tolist()
-    
-    bw.addEntries(
-        chroms=[chrom] * len(starts),
-        starts=starts.tolist(),
-        ends=ends.tolist(),
-        values=values
-    )
-    
-    bw.close()
-    
-    print(f"  Saved {i + 1}/{len(track_data_list)}: {display_name} ({track_clean_name}.bw)")
-
-print(f"\n✅ Successfully saved {len(track_data_list)} BigWig files to '{output_dir}/'")
-print(f"   Files: {', '.join([name.replace(' ', '_').replace('/', '_').replace('-', '_') for name, _, _ in track_data_list])}")</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; white-space: pre-wrap;">
-      <strong style="color: var(--muted);">Output:</strong><br>Found 8 tracks to save from tracks_to_plot
-Input region: chr19:6700000-6831072 (length: 131,072 bp)
-Prediction region: chr19:6740960-6790112 (length: 49,152 bp)
-Number of positions: 49152
-
-Saving BigWig files to 'bigwig_outputs/' directory...
-  Saved 1/8: K562 RNA-seq (K562_RNA_seq.bw)
-  Saved 2/8: K562 DNAse (K562_DNAse.bw)
-  Saved 3/8: K562 H3k4me3 (K562_H3k4me3.bw)
-  Saved 4/8: K562 CTCF (K562_CTCF.bw)
-  Saved 5/8: HepG2 RNA-seq (HepG2_RNA_seq.bw)
-  Saved 6/8: HepG2 DNAse (HepG2_DNAse.bw)
-  Saved 7/8: HepG2 H3k4me3 (HepG2_H3k4me3.bw)
-  Saved 8/8: HepG2 CTCF (HepG2_CTCF.bw)
-
-✅ Successfully saved 8 BigWig files to 'bigwig_outputs/'
-   Files: K562_RNA_seq, K562_DNAse, K562_H3k4me3, K562_CTCF, HepG2_RNA_seq, HepG2_DNAse, HepG2_H3k4me3, HepG2_CTCF
-    </div>
-    <p style="margin-top: 15px; color: var(--muted); font-size: 13px;">
-      This saves each selected functional track as a separate BigWig file that can be visualized in genome browsers. The files are saved with user-friendly display names (e.g., "K562_RNA_seq.bw").
-    </p>
-  </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()
-
-# Build tracks array with all BigWig files we saved
-tracks = []
-for track_display_name, track_id in tracks_to_plot.items():
-    # Clean the display name to match the filename we saved
-    track_clean_name = track_display_name.replace(" ", "_").replace("/", "_").replace("-", "_")
-    bigwig_path = os.path.join(output_dir, f"{track_clean_name}.bw")
-    bigwig_track = {
-        "name": track_display_name,
-        "format": "bigwig",
-        "url": bigwig_path,
-        "height": 70,
-        "autoscale": True,
-        "displayMode": "EXPANDED",
-    }
-    tracks.append(bigwig_track)
-
-config = {
-    "genome": assembly,
-    "locus": f"{chrom}:{center_start}-{center_end}",
-    "tracks": tracks,
-    "theme": "dark",
-}
-
-browser = igv_notebook.Browser(config)
-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 with a dark theme showing all the predicted functional tracks. The BigWig files 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/01_functional_track_prediction.ipynb" target="_blank" rel="noopener noreferrer">View notebook on Hugging Face</a></li>
-      <li>Download and run in Jupyter, Google Colab, or any notebook environment</li>
-    </ul>
-  </div>
-</div>
-