Geonomic commited on
Commit
209e556
·
verified ·
1 Parent(s): 2463609

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +12 -6
app.py CHANGED
@@ -229,20 +229,26 @@ def gradio_inference(dna_sequence, run_mapping):
229
  # --- THE UI LAYOUT ---
230
  with gr.Blocks(theme=gr.themes.Soft(), title="🧬 The Genomic Oracle 🧬") as demo:
231
  gr.Markdown(
 
232
  """
233
- # 🧬 The Genomic Oracle 🧬
234
- **University of Maryland Global Campus (UMGC) | Bioinformatics Capstone Project**
 
 
 
 
235
 
236
  Welcome to the official interface for **The Genomic Oracle**, a cascaded machine learning pipeline designed for high-precision DNA sequence classification.
237
 
238
  ### 🧠 The 4-Stage Architecture
239
- 1. **The Gatekeeper:** Logistic Regression Model rapidly screens raw k-mer vectors to identify protein-coding vs. non-coding potential.
240
- 2. **Structural Mapper:** LightGBM Model classifies the sequence into 1 of 7 structural features (e.g., Exons, UTRs, Enhancers).
241
- 3. **Phenotype Prediction:** Sequences flagged as Coding are passed through a custom ALiBi BERT transformer to predict specific traits.
242
- 4. **Regulatory Validation:** Sequences flagged as Non-Coding Promoters are routed to a DNABERT-2 spatial attention neural network.
243
  ---
244
  """
245
  )
 
246
 
247
  with gr.Row():
248
  with gr.Column(scale=1):
 
229
  # --- THE UI LAYOUT ---
230
  with gr.Blocks(theme=gr.themes.Soft(), title="🧬 The Genomic Oracle 🧬") as demo:
231
  gr.Markdown(
232
+ gr.Markdown(
233
  """
234
+ <div style="text-align: center;">
235
+ <h1 style="font-size: 3.5rem; font-weight: bold; margin-bottom: 0.2rem;">🧬 The Genomic Oracle 🧬</h1>
236
+ <h3 style="margin-top: 0; font-weight: normal;"><b>University of Maryland Global Campus (UMGC)</b> | Bioinformatics Capstone Project</h3>
237
+ </div>
238
+
239
+ <hr>
240
 
241
  Welcome to the official interface for **The Genomic Oracle**, a cascaded machine learning pipeline designed for high-precision DNA sequence classification.
242
 
243
  ### 🧠 The 4-Stage Architecture
244
+ 1. **The Gatekeeper:** Logistic Regression model rapidly screens raw k-mer vectors to identify protein-coding vs. non-coding potential.
245
+ 2. **Structural Mapper:** LightGBM model classifies the sequence into 1 of 7 structural features (e.g., Exons, UTRs, Enhancers).
246
+ 3. **Phenotype Prediction:** Sequences flagged as Coding are passed through a custom ALiBi BERT transformer to predict specific phenotypes.
247
+ 4. **Regulatory Validation:** Sequences flagged as Non-Coding Promoters are validated by a DNABERT-2 spatial attention neural network.
248
  ---
249
  """
250
  )
251
+ )
252
 
253
  with gr.Row():
254
  with gr.Column(scale=1):